eliott/claude-mem
1
0
Fork 0
mirror of https://github.com/thedotmack/claude-mem synced 2026-04-25 17:15:04 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat: Mode system with inheritance and multilingual support (#412)

Browse Source 
* feat: add domain management system with support for multiple domain profiles

- Introduced DomainManager class for loading and managing domain profiles.
- Added support for a default domain ('code') and fallback mechanisms.
- Implemented domain configuration validation and error handling.
- Created types for domain configuration, observation types, and concepts.
- Added new directory for domain profiles and ensured its existence.
- Updated SettingsDefaultsManager to include CLAUDE_MEM_DOMAIN setting.

* Refactor domain management to mode management

- Removed DomainManager class and replaced it with ModeManager for better clarity and functionality.
- Updated types from DomainConfig to ModeConfig and DomainPrompts to ModePrompts.
- Changed references from domains to modes in the settings and paths.
- Ensured backward compatibility by maintaining the fallback mechanism to the 'code' mode.

* feat: add migration 008 to support mode-agnostic observations and refactor service layer references in documentation

* feat: add new modes for code development and email investigation with detailed observation types and concepts

* Refactor observation parsing and prompt generation to incorporate mode-specific configurations

- Updated `parseObservations` function to use 'observation' as a universal fallback type instead of 'change', utilizing active mode's valid observation types.
- Modified `buildInitPrompt` and `buildContinuationPrompt` functions to accept a `ModeConfig` parameter, allowing for dynamic prompt content based on the active mode.
- Enhanced `ModePrompts` interface to include additional guidance for observers, such as recording focus and skip guidance.
- Adjusted the SDKAgent to load the active mode and pass it to prompt generation functions, ensuring prompts are tailored to the current mode's context.

* fix: correct mode prompt injection to preserve exact wording and type list visibility

- Add script to extract prompts from main branch prompts.ts into code.yaml
- Fix prompts.ts to show type list in XML template (e.g., "[ bugfix | feature | ... ]")
- Keep 'change' as fallback type in parser.ts (maintain backwards compatibility)
- Regenerate code.yaml with exact wording from original hardcoded prompts
- Build succeeds with no TypeScript errors

* fix: update ModeManager to load JSON mode files and improve validation

- Changed ModeManager to load mode configurations from JSON files instead of YAML.
- Removed the requirement for an "observation" type and updated validation to require at least one observation type.
- Updated fallback behavior in the parser to use the first type from the active mode's type list.
- Added comprehensive tests for mode loading, prompt injection, and parser integration, ensuring correct behavior across different modes.
- Introduced new mode JSON files for "Code Development" and "Email Investigation" with detailed observation types and prompts.

* Add mode configuration loading and update licensing information for Ragtime

- Implemented loading of mode configuration in WorkerService before database initialization.
- Added PolyForm Noncommercial License 1.0.0 to Ragtime directory.
- Created README.md for Ragtime with licensing details and usage guidelines.

* fix: add datasets directory to .gitignore to prevent accidental commits

* refactor: remove unused plugin package.json file

* chore: add package.json for claude-mem plugin with version 7.4.5

* refactor: remove outdated tests and improve error handling

- Deleted tests for ChromaSync error handling, smart install, strip memory tags, and user prompt tag stripping due to redundancy or outdated logic.
- Removed vitest configuration as it is no longer needed.
- Added a comprehensive implementation plan for fixing the modes system, addressing critical issues and improving functionality.
- Created a detailed test analysis report highlighting the quality and effectiveness of the current test suite, identifying areas for improvement.
- Introduced a new plugin package.json for runtime dependencies related to claude-mem hooks.

* refactor: remove parser regression tests to streamline codebase

* docs: update CLAUDE.md to clarify test management and changelog generation

* refactor: remove migration008 for mode-agnostic observations

* Refactor observation type handling to use ModeManager for icons and emojis

- Removed direct mappings of observation types to icons and work emojis in context-generator, FormattingService, SearchManager, and TimelineService.
- Integrated ModeManager to dynamically retrieve icons and emojis based on the active mode.
- Improved maintainability by centralizing the logic for observation type representation.

* Refactor observation metadata constants and update context generator

- Removed the explicit declaration of OBSERVATION_TYPES and OBSERVATION_CONCEPTS from observation-metadata.ts.
- Introduced fallback default strings for DEFAULT_OBSERVATION_TYPES_STRING and DEFAULT_OBSERVATION_CONCEPTS_STRING.
- Updated context-generator.ts to utilize observation types and concepts from ModeManager instead of constants.

* refactor: remove intermediate error handling from hooks (Phase 1)

Apply "fail fast" error handling strategy - errors propagate and crash loud
instead of being caught, wrapped, and re-thrown at intermediate layers.

Changes:
- Remove try/catch around fetch calls in all hooks - let errors throw
- Add try/catch ONLY around JSON.parse at entry points
- Delete error-handler.ts and hook-error-handler.ts (no longer needed)
- Update worker-utils.ts: functions now throw instead of returning null
- Update transcript-parser.ts: throw on missing path, empty file, malformed JSON
- Remove all handleWorkerError, handleFetchError imports

Philosophy: If something breaks, we KNOW it broke. No silent failures.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: remove intermediate error handling from worker service (Phase 2)

Apply "fail fast" error handling strategy to worker service layer.

Changes:
- worker-service.ts: Remove try/catch from version endpoint, cleanup,
  MCP close, process enumeration, force kill, and isAlive check
- SessionRoutes.ts: Remove try/catch from JSON.stringify calls, remove
  .catch() from Chroma sync and SDK agent calls
- SettingsRoutes.ts: Remove try/catch from toggleMcp()
- DatabaseManager.ts: Remove .catch() from backfill and close operations
- SDKAgent.ts: Keep outer try/catch (top-level), remove .catch() from
  Chroma sync operations
- SSEBroadcaster.ts: Remove try/catch from broadcast and sendToClient

Philosophy: Errors propagate and crash loud. BaseRouteHandler.wrapHandler
provides top-level catching for HTTP routes.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: remove error swallowing from SQLite services (Phase 3)

Apply "fail fast" error handling strategy to database layer.

SessionStore.ts migrations:
- ensureWorkerPortColumn(): Remove outer try/catch, let it throw
- ensurePromptTrackingColumns(): Remove outer try/catch, let it throw
- removeSessionSummariesUniqueConstraint(): Keep inner transaction
  rollback, remove outer catch
- addObservationHierarchicalFields(): Remove outer try/catch
- makeObservationsTextNullable(): Keep inner transaction rollback,
  remove outer catch
- createUserPromptsTable(): Keep inner transaction rollback, remove
  outer catch
- getFilesForSession(): Remove try/catch around JSON.parse

SessionSearch.ts:
- ensureFTSTables(): Remove try/catch, let it throw

Philosophy: Migration errors that are swallowed mean we think the
database is fine when it's not. Keep only inner transaction rollback
try/catch blocks.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: remove error hiding from utilities (Phase 4)

Apply "fail fast" error handling strategy to utility layer.

logger.ts:
- formatTool(): Remove try/catch, let JSON.parse throw on malformed input

context-generator.ts:
- loadContextConfig(): Remove try/catch, let parseInt throw on invalid settings
- Transcript extraction: Remove try/catch, let file read errors propagate

ChromaSync.ts:
- close(): Remove nested try/catch blocks, let close errors propagate

Philosophy: No silent fallbacks or hidden defaults. If something breaks,
we know it broke immediately.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat: serve static UI assets and update package root path

- Added middleware to serve static UI assets (JS, CSS, fonts, etc.) in ViewerRoutes.
- Updated getPackageRoot function to correctly return the package root directory as one level up from the current directory.

* feat: Enhance mode loading with inheritance support

- Introduced parseInheritance method to handle parent--override mode IDs.
- Added deepMerge method for recursively merging mode configurations.
- Updated loadMode method to support inheritance, loading parent modes and applying overrides.
- Improved error handling for missing mode files and logging for better traceability.

* fix(modes): correct inheritance file resolution and path handling

* Refactor code structure for improved readability and maintainability

* feat: Add mode configuration documentation and examples

* fix: Improve concurrency handling in translateReadme function

* Refactor SDK prompts to enhance clarity and structure

- Updated the `buildInitPrompt` and `buildContinuationPrompt` functions in `prompts.ts` to improve the organization of prompt components, including the addition of language instructions and footer messages.
- Removed redundant instructions and emphasized the importance of recording observations.
- Modified the `ModePrompts` interface in `types.ts` to include new properties for system identity, language instructions, and output format header, ensuring better flexibility and clarity in prompt generation.

* Enhance prompts with language instructions and XML formatting

- Updated `buildInitPrompt`, `buildSummaryPrompt`, and `buildContinuationPrompt` functions to include detailed language instructions in XML comments.
- Ensured that language instructions guide users to keep XML tags in English while writing content in the specified language.
- Modified the `buildSummaryPrompt` function to accept `mode` as a parameter for consistency.
- Adjusted the call to `buildSummaryPrompt` in `SDKAgent` to pass the `mode` argument.

* Refactor XML prompt generation in SDK

- Updated the buildInitPrompt, buildSummaryPrompt, and buildContinuationPrompt functions to use new placeholders for XML elements, improving maintainability and readability.
- Removed redundant language instructions in comments for clarity.
- Added new properties to ModePrompts interface for better structure and organization of XML placeholders and section headers.

* feat: Update observation prompts and structure across multiple languages

* chore: Remove planning docs and update Ragtime README

Remove ephemeral development artifacts:
- .claude/plans/modes-system-fixes.md
- .claude/test-analysis-report.md
- PROMPT_INJECTION_ANALYSIS.md

Update ragtime/README.md to explain:
- Feature is not yet implemented
- Dependency on modes system (now complete in PR #412)
- Ready to be scripted out in future release

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* fix: Move summary prompts to mode files for multilingual support

Summary prompts were hardcoded in English in prompts.ts, breaking
multilingual support. Now properly mode-based:

- Added summary_instruction, summary_context_label,
  summary_format_instruction, summary_footer to code.json
- Updated buildSummaryPrompt() to use mode fields instead of hardcoded text
- Added summary_footer with language instructions to all 10 language modes
- Language modes keep English prompts + language requirement footer

This fixes the gaslighting where we claimed full multilingual support
but summaries were still generated in English.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* chore: Clean up README by removing local preview instructions and streamlining beta features section

* Add translated README files for Ukrainian, Vietnamese, and Chinese languages

* Add new language modes for code development in multiple languages

- Introduced JSON configurations for Code Development in Greek, Finnish, Hebrew, Hindi, Hungarian, Indonesian, Italian, Dutch, Norwegian, Polish, Brazilian Portuguese, Romanian, Swedish, Turkish, and Ukrainian.
- Each configuration includes prompts for observations, summaries, and instructions tailored to the respective language.
- Ensured that all prompts emphasize the importance of generating observations without referencing the agent's actions.

* Add multilingual support links to README files in various languages

- Updated README.id.md, README.it.md, README.ja.md, README.ko.md, README.nl.md, README.no.md, README.pl.md, README.pt-br.md, README.ro.md, README.ru.md, README.sv.md, README.th.md, README.tr.md, README.uk.md, README.vi.md, and README.zh.md to include links to other language versions.
- Each README now features a centered paragraph with flags and links for easy navigation between different language documents.

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Alex Newman
2025-12-22 20:14:18 -05:00
committed by GitHub
parent db02da148f
commit 3ea0b60b9f
141 changed files with 11834 additions and 6699 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@@ -13,6 +13,7 @@ plugin/data/
plugin/data.backup/
package-lock.json
private/
datasets/
# Generated UI files (built from viewer-template.html)
src/ui/viewer.html

17
CLAUDE.md
View File

@@ -14,7 +14,7 @@ Claude-mem is a Claude Code plugin providing persistent memory across sessions.
**Worker Service** (`src/services/worker-service.ts`) - Express API on port 37777, Bun-managed, handles AI processing asynchronously
**Database** (`src/services/sqlite/`) - SQLite3 at `~/.claude-mem/claude-mem.db` with FTS5 full-text search
**Database** (`src/services/sqlite/`) - SQLite3 at `~/.claude-mem/claude-mem.db`
**Search Skill** (`plugin/skills/mem-search/SKILL.md`) - HTTP API for searching past work, auto-invoked when users ask about history
@@ -36,22 +36,10 @@ Claude-mem is a Claude Code plugin providing persistent memory across sessions.
npm run build-and-sync # Build, sync to marketplace, restart worker
```
**Viewer UI**: http://localhost:37777
## Configuration
Settings are managed in `~/.claude-mem/settings.json`. The file is auto-created with defaults on first run.
**Core Settings:**
- `CLAUDE_MEM_MODEL` - Model for observations/summaries (default: claude-sonnet-4-5)
- `CLAUDE_MEM_CONTEXT_OBSERVATIONS` - Observations injected at SessionStart
- `CLAUDE_MEM_WORKER_PORT` - Worker service port (default: 37777)
- `CLAUDE_MEM_WORKER_HOST` - Worker bind address (default: 127.0.0.1, use 0.0.0.0 for remote access)
**System Configuration:**
- `CLAUDE_MEM_DATA_DIR` - Data directory location (default: ~/.claude-mem)
- `CLAUDE_MEM_LOG_LEVEL` - Log verbosity: DEBUG, INFO, WARN, ERROR, SILENT (default: INFO)
## File Locations
- **Source**: `<project-root>/src/`
@@ -64,7 +52,7 @@ Settings are managed in `~/.claude-mem/settings.json`. The file is auto-created
- **Bun** (all platforms - auto-installed if missing)
- **uv** (all platforms - auto-installed if missing, provides Python for Chroma)
- Node.js (build tools only)
- Node.js
## Documentation
@@ -95,3 +83,4 @@ This architecture preserves the open-source nature of the project while enabling
# Important
No need to edit the changelog ever, it's generated automatically.
No need to run tests, they are useless and are always deleted.

272
README.md
View File

@@ -1,3 +1,5 @@
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
@@ -10,6 +12,37 @@
<br>
</h1>
<p align="center">
<a href="docs/i18n/README.zh.md">🇨🇳 中文</a> •
<a href="docs/i18n/README.ja.md">🇯🇵 日本語</a> •
<a href="docs/i18n/README.pt-br.md">🇧🇷 Português</a> •
<a href="docs/i18n/README.ko.md">🇰🇷 한국어</a> •
<a href="docs/i18n/README.es.md">🇪🇸 Español</a> •
<a href="docs/i18n/README.de.md">🇩🇪 Deutsch</a> •
<a href="docs/i18n/README.fr.md">🇫🇷 Français</a>
<a href="docs/i18n/README.he.md">🇮🇱 עברית</a> •
<a href="docs/i18n/README.ar.md">🇸🇦 العربية</a> •
<a href="docs/i18n/README.ru.md">🇷🇺 Русский</a> •
<a href="docs/i18n/README.pl.md">🇵🇱 Polski</a> •
<a href="docs/i18n/README.cs.md">🇨🇿 Čeština</a> •
<a href="docs/i18n/README.nl.md">🇳🇱 Nederlands</a> •
<a href="docs/i18n/README.tr.md">🇹🇷 Türkçe</a> •
<a href="docs/i18n/README.uk.md">🇺🇦 Українська</a> •
<a href="docs/i18n/README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="docs/i18n/README.id.md">🇮🇩 Indonesia</a> •
<a href="docs/i18n/README.th.md">🇹🇭 ไทย</a> •
<a href="docs/i18n/README.hi.md">🇮🇳 हिन्दी</a> •
<a href="docs/i18n/README.bn.md">🇧🇩 বাংলা</a> •
<a href="docs/i18n/README.ro.md">🇷🇴 Română</a> •
<a href="docs/i18n/README.sv.md">🇸🇪 Svenska</a> •
<a href="docs/i18n/README.it.md">🇮🇹 Italiano</a> •
<a href="docs/i18n/README.el.md">🇬🇷 Ελληνικά</a> •
<a href="docs/i18n/README.hu.md">🇭🇺 Magyar</a> •
<a href="docs/i18n/README.fi.md">🇫🇮 Suomi</a> •
<a href="docs/i18n/README.da.md">🇩🇰 Dansk</a> •
<a href="docs/i18n/README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Persistent memory compression system built for <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
@@ -94,13 +127,6 @@ Restart Claude Code. Context from previous sessions will automatically appear in
📚 **[View Full Documentation](docs/)** - Browse markdown docs on GitHub
💻 **Local Preview**: Run Mintlify docs locally:
```bash
cd docs/public
npx mintlify dev
```
### Getting Started
- **[Installation Guide](https://docs.claude-mem.ai/installation)** - Quick start & advanced installation
@@ -133,34 +159,12 @@ npx mintlify dev
## How It Works
```
┌─────────────────────────────────────────────────────────────┐
│ Session Start → Inject recent observations as context │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ User Prompts → Create session, save user prompts │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ Tool Executions → Capture observations (Read, Write, etc.) │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ Worker Processes → Extract learnings via Claude Agent SDK │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ Session Ends → Generate summary, ready for next session │
└─────────────────────────────────────────────────────────────┘
```
**Core Components:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
2. **Smart Install** - Cached dependency checker (pre-hook script, not a lifecycle hook)
3. **Worker Service** - HTTP API on port 37777 with web viewer UI and 10 search endpoints, managed by Bun
4. **SQLite Database** - Stores sessions, observations, summaries with FTS5 full-text search
4. **SQLite Database** - Stores sessions, observations, summaries
5. **mem-search Skill** - Natural language queries with progressive disclosure
6. **Chroma Vector Database** - Hybrid semantic + keyword search for intelligent context retrieval
@@ -203,74 +207,11 @@ See [Search Tools Guide](https://docs.claude-mem.ai/usage/search-tools) for deta
---
## Beta Features & Endless Mode
## Beta Features
> **Note**: Endless Mode is an **experimental feature in the beta branch only**. It is not included in the stable release you install via the marketplace. You must manually switch to the beta channel to try it, and it comes with significant caveats (see below).
Claude-Mem offers a **beta channel** with experimental features like **Endless Mode** (biomimetic memory architecture for extended sessions). Switch between stable and beta versions from the web viewer UI at http://localhost:37777 → Settings.
Claude-Mem offers a **beta channel** with experimental features. Switch between stable and beta versions directly from the web viewer UI.
### How to Try Beta
1. Open http://localhost:37777
2. Click Settings (gear icon)
3. In **Version Channel**, click "Try Beta (Endless Mode)"
4. Wait for the worker to restart
Your memory data is preserved when switching versions.
### Endless Mode (Beta)
The flagship beta feature is **Endless Mode** - a biomimetic memory architecture that dramatically extends session length:
**The Problem**: Standard Claude Code sessions hit context limits after ~50 tool uses. Each tool adds 1-10k+ tokens, and Claude re-synthesizes all previous outputs on every response (O(N²) complexity).
**The Solution**: Endless Mode compresses tool outputs into ~500-token observations and transforms the transcript in real-time:
```
Working Memory (Context): Compressed observations (~500 tokens each)
Archive Memory (Disk): Full tool outputs preserved for recall
```
**Projected Results** (based on theoretical modeling, not production measurements):
- Significant token reduction in context window
- More tool uses before context exhaustion
- Linear O(N) scaling instead of quadratic O(N²)
- Full transcripts preserved for perfect recall
**Important Caveats**:
- **Not in stable release** - You must switch to beta branch to use this feature
- **Still in development** - May have bugs, breaking changes, or incomplete functionality
- **Slower than standard mode** - Blocking observation generation adds latency to each tool use
- **Theoretical projections** - The efficiency claims above are based on simulations, not real-world production data
See [Beta Features Documentation](https://docs.claude-mem.ai/beta-features) for details.
---
## What's New
**v6.4.9 - Context Configuration Settings:**
- 11 new settings for fine-grained control over context injection
- Configure token economics display, observation filtering by type/concept
- Control number of observations and which fields to display
**v6.4.0 - Dual-Tag Privacy System:**
- `<private>` tags for user-controlled privacy - wrap sensitive content to exclude from storage
- System-level `<claude-mem-context>` tags prevent recursive observation storage
- Edge processing ensures private content never reaches database
**v6.3.0 - Version Channel:**
- Switch between stable and beta versions from the web viewer UI
- Try experimental features like Endless Mode without manual git operations
**Previous Highlights:**
- **v6.0.0**: Major session management & transcript processing improvements
- **v5.5.0**: mem-search skill enhancement with 100% effectiveness rate
- **v5.4.0**: Skill-based search architecture (~2,250 tokens saved per session)
- **v5.1.0**: Web-based viewer UI with real-time updates
- **v5.0.0**: Hybrid search with Chroma vector database
See [CHANGELOG.md](CHANGELOG.md) for complete version history.
See **[Beta Features Documentation](https://docs.claude-mem.ai/beta-features)** for details on Endless Mode and how to try it.
---
@@ -284,162 +225,37 @@ See [CHANGELOG.md](CHANGELOG.md) for complete version history.
---
## Key Benefits
### Progressive Disclosure Context
- **Layered memory retrieval** mirrors human memory patterns
- **Layer 1 (Index)**: See what observations exist with token costs at session start
- **Layer 2 (Details)**: Fetch full narratives on-demand via MCP search
- **Layer 3 (Perfect Recall)**: Access source code and original transcripts
- **Smart decision-making**: Token counts help Claude choose between fetching details or reading code
- **Type indicators**: Visual cues (🔴 critical, 🟤 decision, 🔵 informational) highlight observation importance
### Automatic Memory
- Context automatically injected when Claude starts
- No manual commands or configuration needed
- Works transparently in the background
### Full History Search
- Search across all sessions and observations
- FTS5 full-text search for fast queries
- Citations link back to specific observations
### Structured Observations
- AI-powered extraction of learnings
- Categorized by type (decision, bugfix, feature, etc.)
- Tagged with concepts and file references
### Multi-Prompt Sessions
- Sessions span multiple user prompts
- Context preserved across `/clear` commands
- Track entire conversation threads
---
## Configuration
Settings are managed in `~/.claude-mem/settings.json`. The file is auto-created with defaults on first run.
Settings are managed in `~/.claude-mem/settings.json` (auto-created with defaults on first run). Configure AI model, worker port, data directory, log level, and context injection settings.
**Available Settings:**
| Setting | Default | Description |
|---------|---------|-------------|
| `CLAUDE_MEM_MODEL` | `claude-sonnet-4-5` | AI model for observations |
| `CLAUDE_MEM_WORKER_PORT` | `37777` | Worker service port |
| `CLAUDE_MEM_WORKER_HOST` | `127.0.0.1` | Worker bind address (use `0.0.0.0` for remote access) |
| `CLAUDE_MEM_DATA_DIR` | `~/.claude-mem` | Data directory location |
| `CLAUDE_MEM_LOG_LEVEL` | `INFO` | Log verbosity (DEBUG, INFO, WARN, ERROR, SILENT) |
| `CLAUDE_MEM_PYTHON_VERSION` | `3.13` | Python version for chroma-mcp |
| `CLAUDE_CODE_PATH` | _(auto-detect)_ | Path to Claude executable |
| `CLAUDE_MEM_CONTEXT_OBSERVATIONS` | `50` | Number of observations to inject at SessionStart |
**Settings Management:**
```bash
# Edit settings via CLI helper
./claude-mem-settings.sh
# Or edit directly
nano ~/.claude-mem/settings.json
# View current settings
curl http://localhost:37777/api/settings
```
**Settings File Format:**
```json
{
"CLAUDE_MEM_MODEL": "claude-sonnet-4-5",
"CLAUDE_MEM_WORKER_PORT": "37777",
"CLAUDE_MEM_CONTEXT_OBSERVATIONS": "50"
}
```
See [Configuration Guide](https://docs.claude-mem.ai/configuration) for details.
See the **[Configuration Guide](https://docs.claude-mem.ai/configuration)** for all available settings and examples.
---
## Development
```bash
# Clone and build
git clone https://github.com/thedotmack/claude-mem.git
cd claude-mem
npm install
npm run build
# Run tests
npm test
# Start worker
npm run worker:start
# View logs
npm run worker:logs
```
See [Development Guide](https://docs.claude-mem.ai/development) for detailed instructions.
See the **[Development Guide](https://docs.claude-mem.ai/development)** for build instructions, testing, and contribution workflow.
---
## Troubleshooting
**Quick Diagnostic:**
If experiencing issues, describe the problem to Claude and the troubleshoot skill will automatically diagnose and provide fixes.
If you're experiencing issues, describe the problem to Claude and the troubleshoot skill will automatically activate to diagnose and provide fixes.
**Common Issues:**
- Worker not starting → `claude-mem restart`
- No context appearing → `npm run test:context`
- Database issues → `sqlite3 ~/.claude-mem/claude-mem.db "PRAGMA integrity_check;"`
- Search not working → Check FTS5 tables exist
See [Troubleshooting Guide](https://docs.claude-mem.ai/troubleshooting) for complete solutions.
### Windows Known Issues
**Console Window Visibility**: On Windows, a console window may briefly appear when the worker service starts. This is a cosmetic issue that we're working to resolve. We've prioritized stability by removing a workaround that was causing libuv crashes. The window does not affect functionality and will be addressed in a future release when the MCP SDK provides proper window hiding support.
See the **[Troubleshooting Guide](https://docs.claude-mem.ai/troubleshooting)** for common issues and solutions.
---
## Bug Reports
**Automated Bug Report Generator** - Create comprehensive bug reports with one command:
Create comprehensive bug reports with the automated generator:
```bash
# From the plugin directory
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
The bug report tool will:
- 🌎 **Auto-translate** - Write in ANY language, automatically translates to English
- 📊 **Collect diagnostics** - Gathers versions, platform info, worker status, logs, and configuration
- 📝 **Interactive prompts** - Guides you through describing the issue with multiline support
- 🤖 **AI formatting** - Uses Claude Agent SDK to generate professional GitHub issues
- 🔒 **Privacy-safe** - Auto-sanitizes paths, optional `--no-logs` flag
- 🌐 **Auto-submit** - Opens GitHub with pre-filled title and body
**Plugin Directory Paths:**
- **macOS/Linux**: `~/.claude/plugins/marketplaces/thedotmack`
- **Windows**: `%USERPROFILE%\.claude\plugins\marketplaces\thedotmack`
**Options:**
```bash
npm run bug-report --no-logs # Skip logs for privacy
npm run bug-report --verbose # Show all diagnostics
npm run bug-report --help # Show help
```
---
## Contributing
Contributions are welcome! Please:
@@ -469,6 +285,8 @@ See the [LICENSE](LICENSE) file for full details.
- Derivative works must also be licensed under AGPL-3.0
- There is NO WARRANTY for this software
**Note on Ragtime**: The `ragtime/` directory is licensed separately under the **PolyForm Noncommercial License 1.0.0**. See [ragtime/LICENSE](ragtime/LICENSE) for details.
---
## Support

146
docs/i18n/.translation-cache.json Normal file
View File

@@ -0,0 +1,146 @@
{
"sourceHash": "c0eb50d6772b5e61",
"lastUpdated": "2025-12-23T00:48:34.035Z",
"translations": {
"zh": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.09515915
},
"ja": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.09678544999999998
},
"pt-br": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.08436794999999998
},
"ko": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.10244419999999999
},
"es": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.0894832
},
"de": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.08818689999999998
},
"fr": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:39:44.891Z",
"costUsd": 0.0855869
},
"nl": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.0943619
},
"ru": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.0944719
},
"pl": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.08966189999999999
},
"cs": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.08897189999999998
},
"uk": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.09968189999999999
},
"tr": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.0969419
},
"ar": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.10445689999999998
},
"he": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:43:09.878Z",
"costUsd": 0.1489769
},
"id": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.08454690000000001
},
"sv": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.09621189999999999
},
"ro": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.10500190000000001
},
"vi": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.1035169
},
"hi": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.1171519
},
"th": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.11580689999999999
},
"bn": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:45:44.015Z",
"costUsd": 0.1376269
},
"it": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:48:34.035Z",
"costUsd": 0.0875869
},
"da": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:48:34.035Z",
"costUsd": 0.0830469
},
"no": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:48:34.035Z",
"costUsd": 0.08986190000000001
},
"hu": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:48:34.035Z",
"costUsd": 0.0911269
},
"fi": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:48:34.035Z",
"costUsd": 0.09436689999999999
},
"el": {
"hash": "c0eb50d6772b5e61",
"translatedAt": "2025-12-23T00:48:34.035Z",
"costUsd": 0.19731189999999998
}
}
}

301
docs/i18n/README.ar.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 هذه ترجمة آلية. نرحب بالتصحيحات من المجتمع!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">نظام ضغط الذاكرة المستمرة المبني لـ <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#البدء-السريع">البدء السريع</a> •
<a href="#كيف-يعمل">كيف يعمل</a> •
<a href="#أدوات-البحث-mcp">أدوات البحث</a> •
<a href="#التوثيق">التوثيق</a> •
<a href="#الإعدادات">الإعدادات</a> •
<a href="#استكشاف-الأخطاء-وإصلاحها">استكشاف الأخطاء وإصلاحها</a> •
<a href="#الترخيص">الترخيص</a>
</p>
<p align="center">
يحافظ Claude-Mem بسلاسة على السياق عبر الجلسات من خلال التقاط الملاحظات حول استخدام الأدوات تلقائيًا، وإنشاء ملخصات دلالية، وإتاحتها للجلسات المستقبلية. هذا يمكّن Claude من الحفاظ على استمرارية المعرفة حول المشاريع حتى بعد انتهاء الجلسات أو إعادة الاتصال.
</p>
---
## البدء السريع
ابدأ جلسة Claude Code جديدة في الطرفية وأدخل الأوامر التالية:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
أعد تشغيل Claude Code. سيظهر السياق من الجلسات السابقة تلقائيًا في الجلسات الجديدة.
**الميزات الرئيسية:**
- 🧠 **ذاكرة مستمرة** - يبقى السياق عبر الجلسات
- 📊 **الكشف التدريجي** - استرجاع الذاكرة بطبقات مع رؤية تكلفة الرموز
- 🔍 **بحث قائم على المهارات** - استعلم عن تاريخ مشروعك باستخدام مهارة mem-search
- 🖥️ **واجهة مستخدم ويب** - بث الذاكرة المباشر على http://localhost:37777
- 💻 **مهارة Claude Desktop** - ابحث في الذاكرة من محادثات Claude Desktop
- 🔒 **التحكم في الخصوصية** - استخدم وسوم `<private>` لاستبعاد المحتوى الحساس من التخزين
- ⚙️ **إعدادات السياق** - تحكم دقيق في السياق الذي يتم حقنه
- 🤖 **تشغيل تلقائي** - لا يتطلب تدخلاً يدويًا
- 🔗 **الاستشهادات** - رجوع إلى الملاحظات السابقة باستخدام المعرفات (الوصول عبر http://localhost:37777/api/observation/{id} أو عرض الكل في عارض الويب على http://localhost:37777)
- 🧪 **قناة تجريبية** - جرّب الميزات التجريبية مثل Endless Mode عبر تبديل الإصدار
---
## التوثيق
📚 **[عرض التوثيق الكامل](docs/)** - تصفح مستندات markdown على GitHub
### البدء
- **[دليل التثبيت](https://docs.claude-mem.ai/installation)** - البدء السريع والتثبيت المتقدم
- **[دليل الاستخدام](https://docs.claude-mem.ai/usage/getting-started)** - كيف يعمل Claude-Mem تلقائيًا
- **[أدوات البحث](https://docs.claude-mem.ai/usage/search-tools)** - استعلم عن تاريخ مشروعك باللغة الطبيعية
- **[الميزات التجريبية](https://docs.claude-mem.ai/beta-features)** - جرّب الميزات التجريبية مثل Endless Mode
### أفضل الممارسات
- **[هندسة السياق](https://docs.claude-mem.ai/context-engineering)** - مبادئ تحسين سياق وكيل الذكاء الاصطناعي
- **[الكشف التدريجي](https://docs.claude-mem.ai/progressive-disclosure)** - الفلسفة وراء استراتيجية تهيئة السياق في Claude-Mem
### البنية المعمارية
- **[نظرة عامة](https://docs.claude-mem.ai/architecture/overview)** - مكونات النظام وتدفق البيانات
- **[تطور البنية المعمارية](https://docs.claude-mem.ai/architecture-evolution)** - الرحلة من v3 إلى v5
- **[بنية الخطافات](https://docs.claude-mem.ai/hooks-architecture)** - كيف يستخدم Claude-Mem خطافات دورة الحياة
- **[مرجع الخطافات](https://docs.claude-mem.ai/architecture/hooks)** - شرح 7 سكريبتات خطافات
- **[خدمة العامل](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API وإدارة Bun
- **[قاعدة البيانات](https://docs.claude-mem.ai/architecture/database)** - مخطط SQLite وبحث FTS5
- **[بنية البحث](https://docs.claude-mem.ai/architecture/search-architecture)** - البحث المختلط مع قاعدة بيانات المتجهات Chroma
### الإعدادات والتطوير
- **[الإعدادات](https://docs.claude-mem.ai/configuration)** - متغيرات البيئة والإعدادات
- **[التطوير](https://docs.claude-mem.ai/development)** - البناء، الاختبار، سير العمل للمساهمة
- **[استكشاف الأخطاء وإصلاحها](https://docs.claude-mem.ai/troubleshooting)** - المشكلات الشائعة والحلول
---
## كيف يعمل
**المكونات الأساسية:**
1. **5 خطافات دورة الحياة** - SessionStart، UserPromptSubmit، PostToolUse، Stop، SessionEnd (6 سكريبتات خطافات)
2. **تثبيت ذكي** - فاحص التبعيات المخزنة مؤقتًا (سكريبت ما قبل الخطاف، ليس خطاف دورة حياة)
3. **خدمة العامل** - HTTP API على المنفذ 37777 مع واجهة مستخدم عارض الويب و10 نقاط نهاية للبحث، تديرها Bun
4. **قاعدة بيانات SQLite** - تخزن الجلسات، الملاحظات، الملخصات
5. **مهارة mem-search** - استعلامات اللغة الطبيعية مع الكشف التدريجي
6. **قاعدة بيانات المتجهات Chroma** - البحث المختلط الدلالي + الكلمات المفتاحية لاسترجاع السياق الذكي
انظر [نظرة عامة على البنية المعمارية](https://docs.claude-mem.ai/architecture/overview) للتفاصيل.
---
## مهارة mem-search
يوفر Claude-Mem بحثًا ذكيًا من خلال مهارة mem-search التي تُستدعى تلقائيًا عندما تسأل عن العمل السابق:
**كيف يعمل:**
- فقط اسأل بشكل طبيعي: *"ماذا فعلنا في الجلسة الأخيرة؟"* أو *"هل أصلحنا هذا الخطأ من قبل؟"*
- يستدعي Claude تلقائيًا مهارة mem-search للعثور على السياق ذي الصلة
**عمليات البحث المتاحة:**
1. **البحث في الملاحظات** - البحث النصي الكامل عبر الملاحظات
2. **البحث في الجلسات** - البحث النصي الكامل عبر ملخصات الجلسات
3. **البحث في المطالبات** - البحث في طلبات المستخدم الخام
4. **حسب المفهوم** - البحث بواسطة وسوم المفهوم (discovery، problem-solution، pattern، إلخ.)
5. **حسب الملف** - البحث عن الملاحظات التي تشير إلى ملفات محددة
6. **حسب النوع** - البحث حسب النوع (decision، bugfix، feature، refactor، discovery، change)
7. **السياق الحديث** - الحصول على سياق الجلسة الأخيرة لمشروع
8. **الجدول الزمني** - الحصول على جدول زمني موحد للسياق حول نقطة زمنية محددة
9. **الجدول الزمني حسب الاستعلام** - البحث عن الملاحظات والحصول على سياق الجدول الزمني حول أفضل تطابق
10. **مساعدة API** - الحصول على توثيق API البحث
**أمثلة على استعلامات اللغة الطبيعية:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
انظر [دليل أدوات البحث](https://docs.claude-mem.ai/usage/search-tools) لأمثلة مفصلة.
---
## الميزات التجريبية
يقدم Claude-Mem **قناة تجريبية** بميزات تجريبية مثل **Endless Mode** (بنية ذاكرة بيوميمتية للجلسات الممتدة). بدّل بين الإصدارات المستقرة والتجريبية من واجهة مستخدم عارض الويب على http://localhost:37777 ← الإعدادات.
انظر **[توثيق الميزات التجريبية](https://docs.claude-mem.ai/beta-features)** لتفاصيل حول Endless Mode وكيفية تجربته.
---
## متطلبات النظام
- **Node.js**: 18.0.0 أو أعلى
- **Claude Code**: أحدث إصدار مع دعم الإضافات
- **Bun**: بيئة تشغيل JavaScript ومدير العمليات (يُثبت تلقائيًا إذا كان مفقودًا)
- **uv**: مدير حزم Python للبحث المتجهي (يُثبت تلقائيًا إذا كان مفقودًا)
- **SQLite 3**: للتخزين المستمر (مدمج)
---
## الإعدادات
تتم إدارة الإعدادات في `~/.claude-mem/settings.json` (يتم إنشاؤه تلقائيًا بالقيم الافتراضية عند التشغيل الأول). قم بتكوين نموذج الذكاء الاصطناعي، منفذ العامل، دليل البيانات، مستوى السجل، وإعدادات حقن السياق.
انظر **[دليل الإعدادات](https://docs.claude-mem.ai/configuration)** لجميع الإعدادات المتاحة والأمثلة.
---
## التطوير
انظر **[دليل التطوير](https://docs.claude-mem.ai/development)** لتعليمات البناء، الاختبار، وسير عمل المساهمة.
---
## استكشاف الأخطاء وإصلاحها
إذا واجهت مشكلات، صِف المشكلة لـ Claude وستقوم مهارة troubleshoot تلقائيًا بتشخيصها وتوفير الإصلاحات.
انظر **[دليل استكشاف الأخطاء وإصلاحها](https://docs.claude-mem.ai/troubleshooting)** للمشكلات الشائعة والحلول.
---
## تقارير الأخطاء
أنشئ تقارير أخطاء شاملة باستخدام المولّد الآلي:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## المساهمة
المساهمات مرحب بها! يُرجى:
1. عمل Fork للمستودع
2. إنشاء فرع ميزة
3. إجراء التغييرات مع الاختبارات
4. تحديث التوثيق
5. تقديم Pull Request
انظر [دليل التطوير](https://docs.claude-mem.ai/development) لسير عمل المساهمة.
---
## الترخيص
هذا المشروع مرخص بموجب **ترخيص GNU Affero العام الإصدار 3.0** (AGPL-3.0).
حقوق النشر (C) 2025 Alex Newman (@thedotmack). جميع الحقوق محفوظة.
انظر ملف [LICENSE](LICENSE) للتفاصيل الكاملة.
**ماذا يعني هذا:**
- يمكنك استخدام وتعديل وتوزيع هذا البرنامج بحرية
- إذا قمت بتعديل ونشر على خادم شبكة، يجب أن تتيح كود المصدر الخاص بك
- الأعمال المشتقة يجب أن تكون مرخصة أيضًا تحت AGPL-3.0
- لا يوجد ضمان لهذا البرنامج
**ملاحظة حول Ragtime**: دليل `ragtime/` مرخص بشكل منفصل تحت **ترخيص PolyForm Noncommercial 1.0.0**. انظر [ragtime/LICENSE](ragtime/LICENSE) للتفاصيل.
---
## الدعم
- **التوثيق**: [docs/](docs/)
- **المشكلات**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **المستودع**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **المؤلف**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**مبني باستخدام Claude Agent SDK** | **مدعوم بواسطة Claude Code** | **صُنع باستخدام TypeScript**

302
docs/i18n/README.bn.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 এটি একটি স্বয়ংক্রিয় অনুবাদ। সম্প্রদায়ের সংশোধন স্বাগত জানাই!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center"><a href="https://claude.com/claude-code" target="_blank">Claude Code</a>-এর জন্য নির্মিত স্থায়ী মেমরি কম্প্রেশন সিস্টেম।</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#দ্রুত-শুরু">দ্রুত শুরু</a> •
<a href="#এটি-কীভাবে-কাজ-করে">এটি কীভাবে কাজ করে</a> •
<a href="#অনুসন্ধান-টুল">অনুসন্ধান টুল</a> •
<a href="#ডকুমেন্টেশন">ডকুমেন্টেশন</a> •
<a href="#কনফিগারেশন">কনফিগারেশন</a> •
<a href="#সমস্যা-সমাধান">সমস্যা সমাধান</a> •
<a href="#লাইসেন্স">লাইসেন্স</a>
</p>
<p align="center">
Claude-Mem স্বয়ংক্রিয়ভাবে টুল ব্যবহারের পর্যবেক্ষণ ক্যাপচার করে, সিমান্টিক সারসংক্ষেপ তৈরি করে এবং সেগুলি ভবিষ্যতের সেশনে উপলব্ধ করে সেশন জুড়ে প্রসঙ্গ নির্বিঘ্নে সংরক্ষণ করে। এটি Claude কে সেশন শেষ হওয়ার বা পুনঃসংযোগের পরেও প্রকল্প সম্পর্কে জ্ঞানের ধারাবাহিকতা বজায় রাখতে সক্ষম করে।
</p>
---
## দ্রুত শুরু
টার্মিনালে একটি নতুন Claude Code সেশন শুরু করুন এবং নিম্নলিখিত কমান্ডগুলি প্রবেশ করান:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Claude Code পুনরায় চালু করুন। পূর্ববর্তী সেশনের প্রসঙ্গ স্বয়ংক্রিয়ভাবে নতুন সেশনে উপস্থিত হবে।
**মূল বৈশিষ্ট্যসমূহ:**
- 🧠 **স্থায়ী মেমরি** - প্রসঙ্গ সেশন জুড়ে টিকে থাকে
- 📊 **প্রগতিশীল প্রকাশ** - টোকেন খরচ দৃশ্যমানতা সহ স্তরযুক্ত মেমরি পুনরুদ্ধার
- 🔍 **দক্ষতা-ভিত্তিক অনুসন্ধান** - mem-search skill দিয়ে আপনার প্রকল্পের ইতিহাস অনুসন্ধান করুন
- 🖥️ **ওয়েব ভিউয়ার UI** - http://localhost:37777 এ রিয়েল-টাইম মেমরি স্ট্রিম
- 💻 **Claude Desktop Skill** - Claude Desktop কথোপকথন থেকে মেমরি অনুসন্ধান করুন
- 🔒 **গোপনীয়তা নিয়ন্ত্রণ** - সংবেদনশীল বিষয়বস্তু স্টোরেজ থেকে বাদ দিতে `<private>` ট্যাগ ব্যবহার করুন
- ⚙️ **প্রসঙ্গ কনফিগারেশন** - কোন প্রসঙ্গ ইনজেক্ট করা হবে তার উপর সূক্ষ্ম নিয়ন্ত্রণ
- 🤖 **স্বয়ংক্রিয় অপারেশন** - কোন ম্যানুয়াল হস্তক্ষেপ প্রয়োজন নেই
- 🔗 **উদ্ধৃতি** - ID দিয়ে পূর্ববর্তী পর্যবেক্ষণ রেফারেন্স করুন (http://localhost:37777/api/observation/{id} এর মাধ্যমে অ্যাক্সেস করুন অথবা http://localhost:37777 এ ওয়েব ভিউয়ারে সব দেখুন)
- 🧪 **বিটা চ্যানেল** - ভার্সন পরিবর্তনের মাধ্যমে Endless Mode-এর মতো পরীক্ষামূলক বৈশিষ্ট্য চেষ্টা করুন
---
## ডকুমেন্টেশন
📚 **[সম্পূর্ণ ডকুমেন্টেশন দেখুন](docs/)** - GitHub-এ markdown ডক্স ব্রাউজ করুন
### শুরু করা
- **[ইনস্টলেশন গাইড](https://docs.claude-mem.ai/installation)** - দ্রুত শুরু এবং উন্নত ইনস্টলেশন
- **[ব্যবহার গাইড](https://docs.claude-mem.ai/usage/getting-started)** - Claude-Mem কীভাবে স্বয়ংক্রিয়ভাবে কাজ করে
- **[অনুসন্ধান টুল](https://docs.claude-mem.ai/usage/search-tools)** - প্রাকৃতিক ভাষা দিয়ে আপনার প্রকল্পের ইতিহাস অনুসন্ধান করুন
- **[বিটা বৈশিষ্ট্য](https://docs.claude-mem.ai/beta-features)** - Endless Mode-এর মতো পরীক্ষামূলক বৈশিষ্ট্য চেষ্টা করুন
### সর্বোত্তম অনুশীলন
- **[প্রসঙ্গ ইঞ্জিনিয়ারিং](https://docs.claude-mem.ai/context-engineering)** - AI এজেন্ট প্রসঙ্গ অপটিমাইজেশন নীতি
- **[প্রগতিশীল প্রকাশ](https://docs.claude-mem.ai/progressive-disclosure)** - Claude-Mem-এর প্রসঙ্গ প্রাইমিং কৌশলের পিছনে দর্শন
### আর্কিটেকচার
- **[সারসংক্ষেপ](https://docs.claude-mem.ai/architecture/overview)** - সিস্টেম উপাদান এবং ডেটা ফ্লো
- **[আর্কিটেকচার বিবর্তন](https://docs.claude-mem.ai/architecture-evolution)** - v3 থেকে v5 পর্যন্ত যাত্রা
- **[হুকস আর্কিটেকচার](https://docs.claude-mem.ai/hooks-architecture)** - Claude-Mem কীভাবে লাইফসাইকেল হুক ব্যবহার করে
- **[হুকস রেফারেন্স](https://docs.claude-mem.ai/architecture/hooks)** - ৭টি হুক স্ক্রিপ্ট ব্যাখ্যা করা হয়েছে
- **[ওয়ার্কার সার্ভিস](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API এবং Bun ম্যানেজমেন্ট
- **[ডাটাবেস](https://docs.claude-mem.ai/architecture/database)** - SQLite স্কিমা এবং FTS5 অনুসন্ধান
- **[অনুসন্ধান আর্কিটেকচার](https://docs.claude-mem.ai/architecture/search-architecture)** - Chroma ভেক্টর ডাটাবেস সহ হাইব্রিড অনুসন্ধান
### কনফিগারেশন এবং ডেভেলপমেন্ট
- **[কনফিগারেশন](https://docs.claude-mem.ai/configuration)** - পরিবেশ ভেরিয়েবল এবং সেটিংস
- **[ডেভেলপমেন্ট](https://docs.claude-mem.ai/development)** - বিল্ডিং, টেস্টিং, অবদান
- **[সমস্যা সমাধান](https://docs.claude-mem.ai/troubleshooting)** - সাধারণ সমস্যা এবং সমাধান
---
## এটি কীভাবে কাজ করে
**মূল উপাদানসমূহ:**
1. **৫টি লাইফসাইকেল হুক** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (৬টি হুক স্ক্রিপ্ট)
2. **স্মার্ট ইনস্টল** - ক্যাশড ডিপেন্ডেন্সি চেকার (প্রি-হুক স্ক্রিপ্ট, লাইফসাইকেল হুক নয়)
3. **ওয়ার্কার সার্ভিস** - ওয়েব ভিউয়ার UI এবং ১০টি অনুসন্ধান এন্ডপয়েন্ট সহ পোর্ট 37777-এ HTTP API, Bun দ্বারা পরিচালিত
4. **SQLite ডাটাবেস** - সেশন, পর্যবেক্ষণ, সারসংক্ষেপ সংরক্ষণ করে
5. **mem-search Skill** - প্রগতিশীল প্রকাশ সহ প্রাকৃতিক ভাষা প্রশ্ন
6. **Chroma ভেক্টর ডাটাবেস** - বুদ্ধিমান প্রসঙ্গ পুনরুদ্ধারের জন্য হাইব্রিড সিমান্টিক + কীওয়ার্ড অনুসন্ধান
বিস্তারিত জানতে [আর্কিটেকচার সারসংক্ষেপ](https://docs.claude-mem.ai/architecture/overview) দেখুন।
---
## অনুসন্ধান টুল
Claude-Mem, mem-search skill-এর মাধ্যমে বুদ্ধিমান অনুসন্ধান প্রদান করে যা আপনি পূর্ববর্তী কাজ সম্পর্কে জিজ্ঞাসা করলে স্বয়ংক্রিয়ভাবে চালু হয়:
**এটি কীভাবে কাজ করে:**
- শুধু স্বাভাবিকভাবে জিজ্ঞাসা করুন: *"গত সেশনে আমরা কী করেছিলাম?"* অথবা *"আমরা কি আগে এই বাগটি ঠিক করেছিলাম?"*
- Claude স্বয়ংক্রিয়ভাবে প্রাসঙ্গিক প্রসঙ্গ খুঁজে পেতে mem-search skill চালু করে
**উপলব্ধ অনুসন্ধান অপারেশনসমূহ:**
1. **অবজারভেশন অনুসন্ধান করুন** - পর্যবেক্ষণ জুড়ে পূর্ণ-পাঠ্য অনুসন্ধান
2. **সেশন অনুসন্ধান করুন** - সেশন সারসংক্ষেপ জুড়ে পূর্ণ-পাঠ্য অনুসন্ধান
3. **প্রম্পট অনুসন্ধান করুন** - কাঁচা ব্যবহারকারী অনুরোধ অনুসন্ধান করুন
4. **ধারণা অনুযায়ী** - ধারণা ট্যাগ দ্বারা খুঁজুন (discovery, problem-solution, pattern, ইত্যাদি)
5. **ফাইল অনুযায়ী** - নির্দিষ্ট ফাইল উল্লেখ করা পর্যবেক্ষণ খুঁজুন
6. **টাইপ অনুযায়ী** - টাইপ দ্বারা খুঁজুন (decision, bugfix, feature, refactor, discovery, change)
7. **সাম্প্রতিক প্রসঙ্গ** - একটি প্রকল্পের জন্য সাম্প্রতিক সেশন প্রসঙ্গ পান
8. **টাইমলাইন** - সময়ের একটি নির্দিষ্ট বিন্দুর চারপাশে প্রসঙ্গের একীভূত টাইমলাইন পান
9. **প্রশ্ন দ্বারা টাইমলাইন** - পর্যবেক্ষণ অনুসন্ধান করুন এবং সেরা মিলের চারপাশে টাইমলাইন প্রসঙ্গ পান
10. **API সহায়তা** - অনুসন্ধান API ডকুমেন্টেশন পান
**প্রাকৃতিক ভাষা প্রশ্নের উদাহরণ:**
```
"গত সেশনে আমরা কোন বাগ ঠিক করেছিলাম?"
"আমরা কীভাবে অথেন্টিকেশন প্রয়োগ করেছি?"
"worker-service.ts-এ কী পরিবর্তন করা হয়েছিল?"
"এই প্রকল্পে সাম্প্রতিক কাজ দেখান"
"ভিউয়ার UI যোগ করার সময় কী হচ্ছিল?"
```
বিস্তারিত উদাহরণের জন্য [অনুসন্ধান টুল গাইড](https://docs.claude-mem.ai/usage/search-tools) দেখুন।
---
## বিটা বৈশিষ্ট্য
Claude-Mem একটি **বিটা চ্যানেল** অফার করে যাতে **Endless Mode**-এর মতো পরীক্ষামূলক বৈশিষ্ট্য রয়েছে (বর্ধিত সেশনের জন্য বায়োমিমেটিক মেমরি আর্কিটেকচার)। http://localhost:37777 → Settings-এ ওয়েব ভিউয়ার UI থেকে স্থিতিশীল এবং বিটা সংস্করণের মধ্যে স্যুইচ করুন।
Endless Mode এবং এটি কীভাবে চেষ্টা করবেন সে সম্পর্কে বিস্তারিত জানতে **[বিটা বৈশিষ্ট্য ডকুমেন্টেশন](https://docs.claude-mem.ai/beta-features)** দেখুন।
---
## সিস্টেম প্রয়োজনীয়তা
- **Node.js**: 18.0.0 বা উচ্চতর
- **Claude Code**: প্লাগইন সাপোর্ট সহ সর্বশেষ সংস্করণ
- **Bun**: JavaScript রানটাইম এবং প্রসেস ম্যানেজার (অনুপস্থিত থাকলে স্বয়ংক্রিয়ভাবে ইনস্টল হয়)
- **uv**: ভেক্টর অনুসন্ধানের জন্য Python প্যাকেজ ম্যানেজার (অনুপস্থিত থাকলে স্বয়ংক্রিয়ভাবে ইনস্টল হয়)
- **SQLite 3**: স্থায়ী স্টোরেজের জন্য (বান্ডল করা)
---
## কনফিগারেশন
সেটিংস `~/.claude-mem/settings.json`-এ পরিচালিত হয় (প্রথম রানে ডিফল্ট সহ স্বয়ংক্রিয়ভাবে তৈরি হয়)। AI মডেল, ওয়ার্কার পোর্ট, ডেটা ডিরেক্টরি, লগ লেভেল এবং প্রসঙ্গ ইনজেকশন সেটিংস কনফিগার করুন।
সমস্ত উপলব্ধ সেটিংস এবং উদাহরণের জন্য **[কনফিগারেশন গাইড](https://docs.claude-mem.ai/configuration)** দেখুন।
---
## ডেভেলপমেন্ট
বিল্ড নির্দেশাবলী, টেস্টিং এবং অবদান ওয়ার্কফ্লোর জন্য **[ডেভেলপমেন্ট গাইড](https://docs.claude-mem.ai/development)** দেখুন।
---
## সমস্যা সমাধান
যদি সমস্যার সম্মুখীন হন, Claude-কে সমস্যাটি বর্ণনা করুন এবং troubleshoot skill স্বয়ংক্রিয়ভাবে নির্ণয় করবে এবং সমাধান প্রদান করবে।
সাধারণ সমস্যা এবং সমাধানের জন্য **[সমস্যা সমাধান গাইড](https://docs.claude-mem.ai/troubleshooting)** দেখুন।
---
## বাগ রিপোর্ট
স্বয়ংক্রিয় জেনারেটর দিয়ে বিস্তৃত বাগ রিপোর্ট তৈরি করুন:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## অবদান
অবদান স্বাগত জানাই! অনুগ্রহ করে:
1. রিপোজিটরি ফর্ক করুন
2. একটি ফিচার ব্র্যাঞ্চ তৈরি করুন
3. টেস্ট সহ আপনার পরিবর্তনগুলি করুন
4. ডকুমেন্টেশন আপডেট করুন
5. একটি Pull Request জমা দিন
অবদান ওয়ার্কফ্লোর জন্য [ডেভেলপমেন্ট গাইড](https://docs.claude-mem.ai/development) দেখুন।
---
## লাইসেন্স
এই প্রকল্পটি **GNU Affero General Public License v3.0** (AGPL-3.0) এর অধীনে লাইসেন্সপ্রাপ্ত।
Copyright (C) 2025 Alex Newman (@thedotmack). সর্বস্বত্ব সংরক্ষিত।
সম্পূর্ণ বিবরণের জন্য [LICENSE](LICENSE) ফাইল দেখুন।
**এর অর্থ কী:**
- আপনি এই সফটওয়্যারটি অবাধে ব্যবহার, পরিবর্তন এবং বিতরণ করতে পারেন
- যদি আপনি পরিবর্তন করেন এবং একটি নেটওয়ার্ক সার্ভারে ডিপ্লয় করেন, তাহলে আপনাকে আপনার সোর্স কোড উপলব্ধ করতে হবে
- ডেরিভেটিভ কাজগুলিও AGPL-3.0 এর অধীনে লাইসেন্সপ্রাপ্ত হতে হবে
- এই সফটওয়্যারের জন্য কোনও ওয়ারেন্টি নেই
**Ragtime সম্পর্কে নোট**: `ragtime/` ডিরেক্টরি আলাদাভাবে **PolyForm Noncommercial License 1.0.0** এর অধীনে লাইসেন্সপ্রাপ্ত। বিস্তারিত জানতে [ragtime/LICENSE](ragtime/LICENSE) দেখুন।
---
## সাপোর্ট
- **ডকুমেন্টেশন**: [docs/](docs/)
- **ইস্যু**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **রিপোজিটরি**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **লেখক**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Claude Agent SDK দিয়ে নির্মিত** | **Claude Code দ্বারা চালিত** | **TypeScript দিয়ে তৈরি**

304
docs/i18n/README.cs.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 Toto je automatický překlad. Komunitní opravy jsou vítány!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Systém trvalé komprese paměti vytvořený pro <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#rychlý-start">Rychlý start</a> •
<a href="#jak-to-funguje">Jak to funguje</a> •
<a href="#vyhledávací-nástroje-mcp">Vyhledávací nástroje</a> •
<a href="#dokumentace">Dokumentace</a> •
<a href="#konfigurace">Konfigurace</a> •
<a href="#řešení-problémů">Řešení problémů</a> •
<a href="#licence">Licence</a>
</p>
<p align="center">
Claude-Mem bezproblémově zachovává kontext napříč sezeními tím, že automaticky zaznamenává pozorování použití nástrojů, generuje sémantické souhrny a zpřístupňuje je budoucím sezením. To umožňuje Claude udržovat kontinuitu znalostí o projektech i po ukončení nebo opětovném připojení sezení.
</p>
---
## Rychlý start
Spusťte nové sezení Claude Code v terminálu a zadejte následující příkazy:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Restartujte Claude Code. Kontext z předchozích sezení se automaticky objeví v nových sezeních.
**Klíčové vlastnosti:**
- 🧠 **Trvalá paměť** - Kontext přetrvává napříč sezeními
- 📊 **Postupné odhalování** - Vrstvené vyhledávání paměti s viditelností nákladů na tokeny
- 🔍 **Vyhledávání založené na dovednostech** - Dotazujte se na historii projektu pomocí dovednosti mem-search
- 🖥️ **Webové uživatelské rozhraní** - Tok paměti v reálném čase na http://localhost:37777
- 💻 **Dovednost pro Claude Desktop** - Vyhledávejte v paměti z konverzací Claude Desktop
- 🔒 **Kontrola soukromí** - Použijte značky `<private>` k vyloučení citlivého obsahu z úložiště
- ⚙️ **Konfigurace kontextu** - Jemně odstupňovaná kontrola nad tím, jaký kontext se vkládá
- 🤖 **Automatický provoz** - Není vyžadován žádný manuální zásah
- 🔗 **Citace** - Odkazujte na minulá pozorování pomocí ID (přístup přes http://localhost:37777/api/observation/{id} nebo zobrazit vše ve webovém prohlížeči na http://localhost:37777)
- 🧪 **Beta kanál** - Vyzkoušejte experimentální funkce jako Endless Mode přepnutím verze
---
## Dokumentace
📚 **[Zobrazit kompletní dokumentaci](docs/)** - Procházejte dokumentaci v markdown na GitHubu
### Začínáme
- **[Průvodce instalací](https://docs.claude-mem.ai/installation)** - Rychlý start a pokročilá instalace
- **[Průvodce použitím](https://docs.claude-mem.ai/usage/getting-started)** - Jak Claude-Mem funguje automaticky
- **[Vyhledávací nástroje](https://docs.claude-mem.ai/usage/search-tools)** - Dotazujte se na historii projektu pomocí přirozeného jazyka
- **[Beta funkce](https://docs.claude-mem.ai/beta-features)** - Vyzkoušejte experimentální funkce jako Endless Mode
### Osvědčené postupy
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - Principy optimalizace kontextu AI agenta
- **[Postupné odhalování](https://docs.claude-mem.ai/progressive-disclosure)** - Filozofie strategie přípravy kontextu Claude-Mem
### Architektura
- **[Přehled](https://docs.claude-mem.ai/architecture/overview)** - Systémové komponenty a tok dat
- **[Evoluce architektury](https://docs.claude-mem.ai/architecture-evolution)** - Cesta z v3 na v5
- **[Architektura háčků](https://docs.claude-mem.ai/hooks-architecture)** - Jak Claude-Mem používá lifecycle hooks
- **[Reference háčků](https://docs.claude-mem.ai/architecture/hooks)** - Vysvětlení 7 hook skriptů
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API a správa Bun
- **[Databáze](https://docs.claude-mem.ai/architecture/database)** - SQLite schéma a FTS5 vyhledávání
- **[Architektura vyhledávání](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybridní vyhledávání s vektorovou databází Chroma
### Konfigurace a vývoj
- **[Konfigurace](https://docs.claude-mem.ai/configuration)** - Proměnné prostředí a nastavení
- **[Vývoj](https://docs.claude-mem.ai/development)** - Sestavení, testování, přispívání
- **[Řešení problémů](https://docs.claude-mem.ai/troubleshooting)** - Běžné problémy a řešení
---
## Jak to funguje
**Hlavní komponenty:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook skriptů)
2. **Chytrá instalace** - Kontrola cachovaných závislostí (pre-hook skript, ne lifecycle hook)
3. **Worker Service** - HTTP API na portu 37777 s webovým prohlížečem a 10 vyhledávacími endpointy, spravováno pomocí Bun
4. **SQLite databáze** - Ukládá sezení, pozorování, souhrny
5. **mem-search dovednost** - Dotazy v přirozeném jazyce s postupným odhalováním
6. **Chroma vektorová databáze** - Hybridní sémantické + klíčové vyhledávání pro inteligentní vyhledávání kontextu
Podrobnosti najdete v [Přehledu architektury](https://docs.claude-mem.ai/architecture/overview).
---
## Dovednost mem-search
Claude-Mem poskytuje inteligentní vyhledávání prostřednictvím dovednosti mem-search, která se automaticky vyvolá, když se ptáte na minulou práci:
**Jak to funguje:**
- Stačí se zeptat přirozeně: *"Co jsme dělali minulé sezení?"* nebo *"Opravovali jsme tuto chybu dříve?"*
- Claude automaticky vyvolá dovednost mem-search k nalezení relevantního kontextu
**Dostupné vyhledávací operace:**
1. **Search Observations** - Fulltextové vyhledávání napříč pozorováními
2. **Search Sessions** - Fulltextové vyhledávání napříč souhrny sezení
3. **Search Prompts** - Vyhledávání surových požadavků uživatelů
4. **By Concept** - Hledání podle koncepčních značek (discovery, problem-solution, pattern, atd.)
5. **By File** - Hledání pozorování odkazujících na konkrétní soubory
6. **By Type** - Hledání podle typu (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Získání nedávného kontextu sezení pro projekt
8. **Timeline** - Získání jednotné časové osy kontextu kolem konkrétního bodu v čase
9. **Timeline by Query** - Vyhledávání pozorování a získání kontextu časové osy kolem nejlepší shody
10. **API Help** - Získání dokumentace k vyhledávacímu API
**Příklady dotazů v přirozeném jazyce:**
```
"Jaké chyby jsme opravili minulé sezení?"
"Jak jsme implementovali autentizaci?"
"Jaké změny byly provedeny v worker-service.ts?"
"Ukaž mi nedávnou práci na tomto projektu"
"Co se dělo, když jsme přidávali viewer UI?"
```
Podrobné příklady najdete v [Průvodci vyhledávacími nástroji](https://docs.claude-mem.ai/usage/search-tools).
---
## Beta funkce
Claude-Mem nabízí **beta kanál** s experimentálními funkcemi jako **Endless Mode** (biomimetická architektura paměti pro prodloužená sezení). Přepínejte mezi stabilní a beta verzí z webového rozhraní na http://localhost:37777 → Settings.
Podrobnosti o Endless Mode a jak jej vyzkoušet najdete v **[Dokumentaci beta funkcí](https://docs.claude-mem.ai/beta-features)**.
---
## Systémové požadavky
- **Node.js**: 18.0.0 nebo vyšší
- **Claude Code**: Nejnovější verze s podporou pluginů
- **Bun**: JavaScript runtime a správce procesů (automaticky nainstalován, pokud chybí)
- **uv**: Python správce balíčků pro vektorové vyhledávání (automaticky nainstalován, pokud chybí)
- **SQLite 3**: Pro trvalé úložiště (součástí balíčku)
---
## Konfigurace
Nastavení jsou spravována v `~/.claude-mem/settings.json` (automaticky vytvořeno s výchozími hodnotami při prvním spuštění). Konfigurujte AI model, port workeru, datový adresář, úroveň logování a nastavení vkládání kontextu.
Všechna dostupná nastavení a příklady najdete v **[Průvodci konfigurací](https://docs.claude-mem.ai/configuration)**.
---
## Vývoj
Podrobné pokyny k sestavení, testování a pracovnímu postupu pro přispívání najdete v **[Průvodci vývojem](https://docs.claude-mem.ai/development)**.
---
## Řešení problémů
Pokud zaznamenáváte problémy, popište problém Claude a dovednost troubleshoot automaticky diagnostikuje a poskytne opravy.
Běžné problémy a řešení najdete v **[Průvodci řešením problémů](https://docs.claude-mem.ai/troubleshooting)**.
---
## Hlášení chyb
Vytvořte komplexní hlášení chyby pomocí automatického generátoru:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Přispívání
Příspěvky jsou vítány! Prosím:
1. Forkněte repositář
2. Vytvořte feature branch
3. Proveďte změny s testy
4. Aktualizujte dokumentaci
5. Odešlete Pull Request
Pracovní postup pro přispívání najdete v [Průvodci vývojem](https://docs.claude-mem.ai/development).
---
## Licence
Tento projekt je licencován pod **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Všechna práva vyhrazena.
Úplné podrobnosti najdete v souboru [LICENSE](LICENSE).
**Co to znamená:**
- Software můžete volně používat, upravovat a distribuovat
- Pokud jej upravíte a nasadíte na síťovém serveru, musíte zpřístupnit svůj zdrojový kód
- Odvozená díla musí být také licencována pod AGPL-3.0
- Pro tento software neexistuje ŽÁDNÁ ZÁRUKA
**Poznámka k Ragtime**: Adresář `ragtime/` je licencován samostatně pod **PolyForm Noncommercial License 1.0.0**. Podrobnosti najdete v [ragtime/LICENSE](ragtime/LICENSE).
---
## Podpora
- **Dokumentace**: [docs/](docs/)
- **Problémy**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repositář**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autor**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Vytvořeno pomocí Claude Agent SDK** | **Poháněno Claude Code** | **Vyrobeno s TypeScript**
---

302
docs/i18n/README.da.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Dette er en automatisk oversættelse. Fællesskabsrettelser er velkomne!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Vedvarende hukommelseskomprimeringsystem bygget til <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#hurtig-start">Hurtig Start</a> •
<a href="#sådan-virker-det">Sådan Virker Det</a> •
<a href="#søgeværktøjer-via-mcp">Søgeværktøjer</a> •
<a href="#dokumentation">Dokumentation</a> •
<a href="#konfiguration">Konfiguration</a> •
<a href="#fejlfinding">Fejlfinding</a> •
<a href="#licens">Licens</a>
</p>
<p align="center">
Claude-Mem bevarer problemfrit kontekst på tværs af sessioner ved automatisk at fange observationer af værktøjsbrug, generere semantiske resuméer og gøre dem tilgængelige for fremtidige sessioner. Dette gør det muligt for Claude at opretholde kontinuitet i viden om projekter, selv efter sessioner afsluttes eller genopretter forbindelse.
</p>
---
## Hurtig Start
Start en ny Claude Code-session i terminalen og indtast følgende kommandoer:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Genstart Claude Code. Kontekst fra tidligere sessioner vil automatisk vises i nye sessioner.
**Nøglefunktioner:**
- 🧠 **Vedvarende Hukommelse** - Kontekst overlever på tværs af sessioner
- 📊 **Progressiv Afsløring** - Lagdelt hukommelseshentning med synlighed af token-omkostninger
- 🔍 **Færdighedsbaseret Søgning** - Forespørg din projekthistorik med mem-search-færdighed
- 🖥️ **Web Viewer UI** - Realtids hukommelsesstream på http://localhost:37777
- 💻 **Claude Desktop-færdighed** - Søg i hukommelsen fra Claude Desktop-samtaler
- 🔒 **Privatkontrol** - Brug `<private>`-tags til at ekskludere følsomt indhold fra lagring
- ⚙️ **Kontekstkonfiguration** - Finjusteret kontrol over hvilken kontekst der indsprøjtes
- 🤖 **Automatisk Drift** - Ingen manuel indgriben påkrævet
- 🔗 **Citationer** - Henvisning til tidligere observationer med ID'er (tilgås via http://localhost:37777/api/observation/{id} eller se alle i web viewer på http://localhost:37777)
- 🧪 **Beta-kanal** - Prøv eksperimentelle funktioner som Endless Mode via versionsskift
---
## Dokumentation
📚 **[Se Fuld Dokumentation](docs/)** - Gennemse markdown-dokumenter på GitHub
### Kom Godt I Gang
- **[Installationsguide](https://docs.claude-mem.ai/installation)** - Hurtig start & avanceret installation
- **[Brugervejledning](https://docs.claude-mem.ai/usage/getting-started)** - Sådan fungerer Claude-Mem automatisk
- **[Søgeværktøjer](https://docs.claude-mem.ai/usage/search-tools)** - Forespørg din projekthistorik med naturligt sprog
- **[Beta-funktioner](https://docs.claude-mem.ai/beta-features)** - Prøv eksperimentelle funktioner som Endless Mode
### Bedste Praksis
- **[Kontekst-engineering](https://docs.claude-mem.ai/context-engineering)** - AI-agent kontekstoptimeringsprincipper
- **[Progressiv Afsløring](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofien bag Claude-Mems kontekst-priming-strategi
### Arkitektur
- **[Oversigt](https://docs.claude-mem.ai/architecture/overview)** - Systemkomponenter & dataflow
- **[Arkitekturudvikling](https://docs.claude-mem.ai/architecture-evolution)** - Rejsen fra v3 til v5
- **[Hooks-arkitektur](https://docs.claude-mem.ai/hooks-architecture)** - Hvordan Claude-Mem bruger livscyklus-hooks
- **[Hooks-reference](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook-scripts forklaret
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API & Bun-administration
- **[Database](https://docs.claude-mem.ai/architecture/database)** - SQLite-skema & FTS5-søgning
- **[Søgearkitektur](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybrid søgning med Chroma vektordatabase
### Konfiguration & Udvikling
- **[Konfiguration](https://docs.claude-mem.ai/configuration)** - Miljøvariabler & indstillinger
- **[Udvikling](https://docs.claude-mem.ai/development)** - Bygning, testning, bidrag
- **[Fejlfinding](https://docs.claude-mem.ai/troubleshooting)** - Almindelige problemer & løsninger
---
## Sådan Virker Det
**Kernekomponenter:**
1. **5 Livscyklus-hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook-scripts)
2. **Smart Installation** - Cached dependency checker (pre-hook script, ikke en livscyklus-hook)
3. **Worker Service** - HTTP API på port 37777 med web viewer UI og 10 søge-endpoints, administreret af Bun
4. **SQLite Database** - Gemmer sessioner, observationer, resuméer
5. **mem-search-færdighed** - Naturlige sprogforespørgsler med progressiv afsløring
6. **Chroma Vector Database** - Hybrid semantisk + søgeordssøgning for intelligent konteksthentning
Se [Arkitekturoversigt](https://docs.claude-mem.ai/architecture/overview) for detaljer.
---
## mem-search-færdighed
Claude-Mem leverer intelligent søgning gennem mem-search-færdigheden, der automatisk aktiveres, når du spørger om tidligere arbejde:
**Sådan Virker Det:**
- Spørg bare naturligt: *"Hvad lavede vi sidste session?"* eller *"Har vi løst denne fejl før?"*
- Claude aktiverer automatisk mem-search-færdigheden for at finde relevant kontekst
**Tilgængelige Søgeoperationer:**
1. **Search Observations** - Fuldtekstsøgning på tværs af observationer
2. **Search Sessions** - Fuldtekstsøgning på tværs af sessionsresumeer
3. **Search Prompts** - Søg i rå brugeranmodninger
4. **By Concept** - Find efter koncept-tags (discovery, problem-solution, pattern, osv.)
5. **By File** - Find observationer, der refererer til specifikke filer
6. **By Type** - Find efter type (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Få nylig sessionskontekst for et projekt
8. **Timeline** - Få samlet tidslinje af kontekst omkring et specifikt tidspunkt
9. **Timeline by Query** - Søg efter observationer og få tidslinjekontekst omkring bedste match
10. **API Help** - Få søge-API-dokumentation
**Eksempler på Naturlige Sprogforespørgsler:**
```
"Hvilke fejl løste vi sidste session?"
"Hvordan implementerede vi autentificering?"
"Hvilke ændringer blev lavet i worker-service.ts?"
"Vis mig det seneste arbejde på dette projekt"
"Hvad skete der, da vi tilføjede viewer UI?"
```
Se [Søgeværktøjsguide](https://docs.claude-mem.ai/usage/search-tools) for detaljerede eksempler.
---
## Beta-funktioner
Claude-Mem tilbyder en **beta-kanal** med eksperimentelle funktioner som **Endless Mode** (biomimetisk hukommelsesarkitektur til udvidede sessioner). Skift mellem stabile og beta-versioner fra web viewer UI på http://localhost:37777 → Settings.
Se **[Beta-funktionsdokumentation](https://docs.claude-mem.ai/beta-features)** for detaljer om Endless Mode og hvordan du prøver det.
---
## Systemkrav
- **Node.js**: 18.0.0 eller højere
- **Claude Code**: Seneste version med plugin-support
- **Bun**: JavaScript runtime og procesmanager (auto-installeres, hvis manglende)
- **uv**: Python package manager til vektorsøgning (auto-installeres, hvis manglende)
- **SQLite 3**: Til vedvarende lagring (bundtet)
---
## Konfiguration
Indstillinger administreres i `~/.claude-mem/settings.json` (auto-oprettet med standardindstillinger ved første kørsel). Konfigurer AI-model, worker-port, datakatalog, log-niveau og indstillinger for kontekstindsprøjtning.
Se **[Konfigurationsguide](https://docs.claude-mem.ai/configuration)** for alle tilgængelige indstillinger og eksempler.
---
## Udvikling
Se **[Udviklingsguide](https://docs.claude-mem.ai/development)** for bygningsinstruktioner, testning og bidragsworkflow.
---
## Fejlfinding
Hvis du oplever problemer, beskriv problemet til Claude, og troubleshoot-færdigheden vil automatisk diagnosticere og levere rettelser.
Se **[Fejlfindingsguide](https://docs.claude-mem.ai/troubleshooting)** for almindelige problemer og løsninger.
---
## Fejlrapporter
Opret omfattende fejlrapporter med den automatiserede generator:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Bidrag
Bidrag er velkomne! Venligst:
1. Fork repositoriet
2. Opret en feature-branch
3. Lav dine ændringer med tests
4. Opdater dokumentation
5. Indsend en Pull Request
Se [Udviklingsguide](https://docs.claude-mem.ai/development) for bidragsworkflow.
---
## Licens
Dette projekt er licenseret under **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Alle rettigheder forbeholdes.
Se [LICENSE](LICENSE)-filen for fulde detaljer.
**Hvad Dette Betyder:**
- Du kan bruge, modificere og distribuere denne software frit
- Hvis du modificerer og implementerer på en netværksserver, skal du gøre din kildekode tilgængelig
- Afledte værker skal også licenseres under AGPL-3.0
- Der er INGEN GARANTI for denne software
**Bemærkning om Ragtime**: `ragtime/`-kataloget er licenseret separat under **PolyForm Noncommercial License 1.0.0**. Se [ragtime/LICENSE](ragtime/LICENSE) for detaljer.
---
## Support
- **Dokumentation**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Forfatter**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Bygget med Claude Agent SDK** | **Drevet af Claude Code** | **Lavet med TypeScript**

302
docs/i18n/README.de.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Dies ist eine automatisierte Übersetzung. Korrekturen aus der Community sind willkommen!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Persistentes Speicherkomprimierungssystem entwickelt für <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#schnellstart">Schnellstart</a> •
<a href="#wie-es-funktioniert">Wie es funktioniert</a> •
<a href="#mcp-suchwerkzeuge">Suchwerkzeuge</a> •
<a href="#dokumentation">Dokumentation</a> •
<a href="#konfiguration">Konfiguration</a> •
<a href="#fehlerbehebung">Fehlerbehebung</a> •
<a href="#lizenz">Lizenz</a>
</p>
<p align="center">
Claude-Mem bewahrt nahtlos Kontext über Sitzungen hinweg, indem es automatisch Beobachtungen zur Tool-Nutzung erfasst, semantische Zusammenfassungen generiert und diese für zukünftige Sitzungen verfügbar macht. Dies ermöglicht es Claude, die Kontinuität des Wissens über Projekte aufrechtzuerhalten, auch nachdem Sitzungen beendet wurden oder die Verbindung wiederhergestellt wird.
</p>
---
## Schnellstart
Starten Sie eine neue Claude Code-Sitzung im Terminal und geben Sie die folgenden Befehle ein:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Starten Sie Claude Code neu. Kontext aus vorherigen Sitzungen wird automatisch in neuen Sitzungen angezeigt.
**Hauptmerkmale:**
- 🧠 **Persistenter Speicher** - Kontext bleibt über Sitzungen hinweg erhalten
- 📊 **Progressive Offenlegung** - Schichtweise Speicherabruf mit Sichtbarkeit der Token-Kosten
- 🔍 **Skill-basierte Suche** - Durchsuchen Sie Ihre Projekthistorie mit dem mem-search Skill
- 🖥️ **Web-Viewer-UI** - Echtzeit-Speicherstream unter http://localhost:37777
- 💻 **Claude Desktop Skill** - Durchsuchen Sie den Speicher aus Claude Desktop-Konversationen
- 🔒 **Datenschutzkontrolle** - Verwenden Sie `<private>`-Tags, um sensible Inhalte von der Speicherung auszuschließen
- ⚙️ **Kontextkonfiguration** - Feinkörnige Kontrolle darüber, welcher Kontext eingefügt wird
- 🤖 **Automatischer Betrieb** - Keine manuelle Intervention erforderlich
- 🔗 **Zitate** - Referenzieren Sie vergangene Beobachtungen mit IDs (Zugriff über http://localhost:37777/api/observation/{id} oder alle im Web-Viewer unter http://localhost:37777 anzeigen)
- 🧪 **Beta-Kanal** - Probieren Sie experimentelle Funktionen wie den Endless Mode durch Versionswechsel aus
---
## Dokumentation
📚 **[Vollständige Dokumentation anzeigen](docs/)** - Markdown-Dokumentation auf GitHub durchsuchen
### Erste Schritte
- **[Installationsanleitung](https://docs.claude-mem.ai/installation)** - Schnellstart & erweiterte Installation
- **[Nutzungsanleitung](https://docs.claude-mem.ai/usage/getting-started)** - Wie Claude-Mem automatisch funktioniert
- **[Suchwerkzeuge](https://docs.claude-mem.ai/usage/search-tools)** - Durchsuchen Sie Ihre Projekthistorie mit natürlicher Sprache
- **[Beta-Funktionen](https://docs.claude-mem.ai/beta-features)** - Probieren Sie experimentelle Funktionen wie den Endless Mode
### Best Practices
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - Prinzipien der Kontextoptimierung für KI-Agenten
- **[Progressive Disclosure](https://docs.claude-mem.ai/progressive-disclosure)** - Philosophie hinter Claude-Mems Kontext-Priming-Strategie
### Architektur
- **[Übersicht](https://docs.claude-mem.ai/architecture/overview)** - Systemkomponenten & Datenfluss
- **[Architekturentwicklung](https://docs.claude-mem.ai/architecture-evolution)** - Die Reise von v3 zu v5
- **[Hooks-Architektur](https://docs.claude-mem.ai/hooks-architecture)** - Wie Claude-Mem Lifecycle-Hooks verwendet
- **[Hooks-Referenz](https://docs.claude-mem.ai/architecture/hooks)** - 7 Hook-Skripte erklärt
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API & Bun-Verwaltung
- **[Datenbank](https://docs.claude-mem.ai/architecture/database)** - SQLite-Schema & FTS5-Suche
- **[Such-Architektur](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybride Suche mit Chroma-Vektordatenbank
### Konfiguration & Entwicklung
- **[Konfiguration](https://docs.claude-mem.ai/configuration)** - Umgebungsvariablen & Einstellungen
- **[Entwicklung](https://docs.claude-mem.ai/development)** - Erstellen, Testen, Beitragen
- **[Fehlerbehebung](https://docs.claude-mem.ai/troubleshooting)** - Häufige Probleme & Lösungen
---
## Wie es funktioniert
**Kernkomponenten:**
1. **5 Lifecycle-Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 Hook-Skripte)
2. **Smart Install** - Gecachter Abhängigkeitsprüfer (Pre-Hook-Skript, kein Lifecycle-Hook)
3. **Worker Service** - HTTP API auf Port 37777 mit Web-Viewer-UI und 10 Such-Endpunkten, verwaltet von Bun
4. **SQLite-Datenbank** - Speichert Sitzungen, Beobachtungen, Zusammenfassungen
5. **mem-search Skill** - Natürlichsprachliche Abfragen mit progressiver Offenlegung
6. **Chroma-Vektordatenbank** - Hybride semantische + Stichwortsuche für intelligenten Kontextabruf
Siehe [Architekturübersicht](https://docs.claude-mem.ai/architecture/overview) für Details.
---
## mem-search Skill
Claude-Mem bietet intelligente Suche durch den mem-search Skill, der sich automatisch aktiviert, wenn Sie nach früheren Arbeiten fragen:
**Wie es funktioniert:**
- Fragen Sie einfach natürlich: *"Was haben wir in der letzten Sitzung gemacht?"* oder *"Haben wir diesen Fehler schon einmal behoben?"*
- Claude aktiviert automatisch den mem-search Skill, um relevanten Kontext zu finden
**Verfügbare Suchoperationen:**
1. **Search Observations** - Volltextsuche über Beobachtungen
2. **Search Sessions** - Volltextsuche über Sitzungszusammenfassungen
3. **Search Prompts** - Durchsuchen von rohen Benutzeranfragen
4. **By Concept** - Suche nach Konzept-Tags (discovery, problem-solution, pattern, etc.)
5. **By File** - Beobachtungen finden, die bestimmte Dateien referenzieren
6. **By Type** - Suche nach Typ (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Aktuellen Sitzungskontext für ein Projekt abrufen
8. **Timeline** - Einheitliche Zeitachse des Kontexts um einen bestimmten Zeitpunkt herum abrufen
9. **Timeline by Query** - Nach Beobachtungen suchen und Zeitachsenkontext um die beste Übereinstimmung herum abrufen
10. **API Help** - Such-API-Dokumentation abrufen
**Beispiele für natürlichsprachliche Abfragen:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Siehe [Suchwerkzeuge-Anleitung](https://docs.claude-mem.ai/usage/search-tools) für detaillierte Beispiele.
---
## Beta-Funktionen
Claude-Mem bietet einen **Beta-Kanal** mit experimentellen Funktionen wie **Endless Mode** (biomimetische Speicherarchitektur für erweiterte Sitzungen). Wechseln Sie zwischen stabilen und Beta-Versionen über die Web-Viewer-UI unter http://localhost:37777 → Settings.
Siehe **[Beta-Funktionen-Dokumentation](https://docs.claude-mem.ai/beta-features)** für Details zum Endless Mode und wie Sie ihn ausprobieren können.
---
## Systemanforderungen
- **Node.js**: 18.0.0 oder höher
- **Claude Code**: Neueste Version mit Plugin-Unterstützung
- **Bun**: JavaScript-Laufzeitumgebung und Prozessmanager (wird automatisch installiert, falls fehlend)
- **uv**: Python-Paketmanager für Vektorsuche (wird automatisch installiert, falls fehlend)
- **SQLite 3**: Für persistente Speicherung (enthalten)
---
## Konfiguration
Einstellungen werden in `~/.claude-mem/settings.json` verwaltet (wird beim ersten Start automatisch mit Standardwerten erstellt). Konfigurieren Sie KI-Modell, Worker-Port, Datenverzeichnis, Log-Level und Kontext-Injektionseinstellungen.
Siehe die **[Konfigurationsanleitung](https://docs.claude-mem.ai/configuration)** für alle verfügbaren Einstellungen und Beispiele.
---
## Entwicklung
Siehe die **[Entwicklungsanleitung](https://docs.claude-mem.ai/development)** für Build-Anweisungen, Tests und Beitrags-Workflow.
---
## Fehlerbehebung
Wenn Sie Probleme haben, beschreiben Sie das Problem Claude und der troubleshoot Skill wird automatisch diagnostizieren und Lösungen bereitstellen.
Siehe die **[Fehlerbehebungsanleitung](https://docs.claude-mem.ai/troubleshooting)** für häufige Probleme und Lösungen.
---
## Fehlerberichte
Erstellen Sie umfassende Fehlerberichte mit dem automatisierten Generator:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Beiträge
Beiträge sind willkommen! Bitte:
1. Forken Sie das Repository
2. Erstellen Sie einen Feature-Branch
3. Nehmen Sie Ihre Änderungen mit Tests vor
4. Aktualisieren Sie die Dokumentation
5. Reichen Sie einen Pull Request ein
Siehe [Entwicklungsanleitung](https://docs.claude-mem.ai/development) für den Beitrags-Workflow.
---
## Lizenz
Dieses Projekt ist unter der **GNU Affero General Public License v3.0** (AGPL-3.0) lizenziert.
Copyright (C) 2025 Alex Newman (@thedotmack). Alle Rechte vorbehalten.
Siehe die [LICENSE](LICENSE)-Datei für vollständige Details.
**Was das bedeutet:**
- Sie können diese Software frei verwenden, modifizieren und verteilen
- Wenn Sie sie modifizieren und auf einem Netzwerkserver bereitstellen, müssen Sie Ihren Quellcode verfügbar machen
- Abgeleitete Werke müssen ebenfalls unter AGPL-3.0 lizenziert werden
- Es gibt KEINE GARANTIE für diese Software
**Hinweis zu Ragtime**: Das `ragtime/`-Verzeichnis ist separat unter der **PolyForm Noncommercial License 1.0.0** lizenziert. Siehe [ragtime/LICENSE](ragtime/LICENSE) für Details.
---
## Support
- **Dokumentation**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autor**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Erstellt mit Claude Agent SDK** | **Powered by Claude Code** | **Made with TypeScript**

302
docs/i18n/README.el.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Αυτή είναι μια αυτοματοποιημένη μετάφραση. Καλώς ορίζονται οι διορθώσεις από την κοινότητα!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Σύστημα συμπίεσης μόνιμης μνήμης κατασκευασμένο για το <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#γρήγορη-εκκίνηση">Γρήγορη Εκκίνηση</a> •
<a href="#πώς-λειτουργεί">Πώς Λειτουργεί</a> •
<a href="#εργαλεία-αναζήτησης-mcp">Εργαλεία Αναζήτησης</a> •
<a href="#τεκμηρίωση">Τεκμηρίωση</a> •
<a href="#διαμόρφωση">Διαμόρφωση</a> •
<a href="#αντιμετώπιση-προβλημάτων">Αντιμετώπιση Προβλημάτων</a> •
<a href="#άδεια-χρήσης">Άδεια Χρήσης</a>
</p>
<p align="center">
Το Claude-Mem διατηρεί απρόσκοπτα το πλαίσιο μεταξύ συνεδριών καταγράφοντας αυτόματα παρατηρήσεις χρήσης εργαλείων, δημιουργώντας σημασιολογικές περιλήψεις και καθιστώντας τες διαθέσιμες σε μελλοντικές συνεδρίες. Αυτό επιτρέπει στο Claude να διατηρεί τη συνέχεια της γνώσης για έργα ακόμη και μετά το τέλος ή την επανασύνδεση συνεδριών.
</p>
---
## Γρήγορη Εκκίνηση
Ξεκινήστε μια νέα συνεδρία Claude Code στο τερματικό και εισάγετε τις ακόλουθες εντολές:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Επανεκκινήστε το Claude Code. Το πλαίσιο από προηγούμενες συνεδρίες θα εμφανιστεί αυτόματα σε νέες συνεδρίες.
**Βασικά Χαρακτηριστικά:**
- 🧠 **Μόνιμη Μνήμη** - Το πλαίσιο διατηρείται μεταξύ συνεδριών
- 📊 **Προοδευτική Αποκάλυψη** - Ανάκτηση μνήμης σε επίπεδα με ορατότητα κόστους tokens
- 🔍 **Αναζήτηση Βασισμένη σε Δεξιότητες** - Ερωτήματα στο ιστορικό του έργου σας με τη δεξιότητα mem-search
- 🖥️ **Διεπαφή Web Viewer** - Ροή μνήμης σε πραγματικό χρόνο στο http://localhost:37777
- 💻 **Δεξιότητα Claude Desktop** - Αναζήτηση μνήμης από συνομιλίες Claude Desktop
- 🔒 **Έλεγχος Απορρήτου** - Χρησιμοποιήστε ετικέτες `<private>` για να εξαιρέσετε ευαίσθητο περιεχόμενο από την αποθήκευση
- ⚙️ **Διαμόρφωση Πλαισίου** - Λεπτομερής έλεγχος για το ποιο πλαίσιο εισάγεται
- 🤖 **Αυτόματη Λειτουργία** - Δεν απαιτείται χειροκίνητη παρέμβαση
- 🔗 **Αναφορές** - Αναφορά σε παλαιότερες παρατηρήσεις με IDs (πρόσβαση μέσω http://localhost:37777/api/observation/{id} ή προβολή όλων στο web viewer στο http://localhost:37777)
- 🧪 **Κανάλι Beta** - Δοκιμάστε πειραματικά χαρακτηριστικά όπως το Endless Mode μέσω εναλλαγής έκδοσης
---
## Τεκμηρίωση
📚 **[Προβολή Πλήρους Τεκμηρίωσης](docs/)** - Περιήγηση στα markdown έγγραφα στο GitHub
### Ξεκινώντας
- **[Οδηγός Εγκατάστασης](https://docs.claude-mem.ai/installation)** - Γρήγορη εκκίνηση & προηγμένη εγκατάσταση
- **[Οδηγός Χρήσης](https://docs.claude-mem.ai/usage/getting-started)** - Πώς λειτουργεί αυτόματα το Claude-Mem
- **[Εργαλεία Αναζήτησης](https://docs.claude-mem.ai/usage/search-tools)** - Ερωτήματα στο ιστορικό του έργου σας με φυσική γλώσσα
- **[Χαρακτηριστικά Beta](https://docs.claude-mem.ai/beta-features)** - Δοκιμάστε πειραματικά χαρακτηριστικά όπως το Endless Mode
### Βέλτιστες Πρακτικές
- **[Μηχανική Πλαισίου](https://docs.claude-mem.ai/context-engineering)** - Αρχές βελτιστοποίησης πλαισίου για AI agents
- **[Προοδευτική Αποκάλυψη](https://docs.claude-mem.ai/progressive-disclosure)** - Φιλοσοφία πίσω από τη στρατηγική προετοιμασίας πλαισίου του Claude-Mem
### Αρχιτεκτονική
- **[Επισκόπηση](https://docs.claude-mem.ai/architecture/overview)** - Συστατικά στοιχεία συστήματος & ροή δεδομένων
- **[Εξέλιξη Αρχιτεκτονικής](https://docs.claude-mem.ai/architecture-evolution)** - Το ταξίδι από το v3 στο v5
- **[Αρχιτεκτονική Hooks](https://docs.claude-mem.ai/hooks-architecture)** - Πώς το Claude-Mem χρησιμοποιεί lifecycle hooks
- **[Αναφορά Hooks](https://docs.claude-mem.ai/architecture/hooks)** - Επεξήγηση 7 hook scripts
- **[Υπηρεσία Worker](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API & διαχείριση Bun
- **[Βάση Δεδομένων](https://docs.claude-mem.ai/architecture/database)** - Σχήμα SQLite & αναζήτηση FTS5
- **[Αρχιτεκτονική Αναζήτησης](https://docs.claude-mem.ai/architecture/search-architecture)** - Υβριδική αναζήτηση με βάση δεδομένων διανυσμάτων Chroma
### Διαμόρφωση & Ανάπτυξη
- **[Διαμόρφωση](https://docs.claude-mem.ai/configuration)** - Μεταβλητές περιβάλλοντος & ρυθμίσεις
- **[Ανάπτυξη](https://docs.claude-mem.ai/development)** - Κατασκευή, δοκιμή, συνεισφορά
- **[Αντιμετώπιση Προβλημάτων](https://docs.claude-mem.ai/troubleshooting)** - Συνήθη προβλήματα & λύσεις
---
## Πώς Λειτουργεί
**Βασικά Συστατικά:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
2. **Έξυπνη Εγκατάσταση** - Έλεγχος εξαρτήσεων με cache (pre-hook script, όχι lifecycle hook)
3. **Υπηρεσία Worker** - HTTP API στη θύρα 37777 με διεπαφή web viewer και 10 endpoints αναζήτησης, διαχειριζόμενη από το Bun
4. **Βάση Δεδομένων SQLite** - Αποθηκεύει συνεδρίες, παρατηρήσεις, περιλήψεις
5. **Δεξιότητα mem-search** - Ερωτήματα φυσικής γλώσσας με προοδευτική αποκάλυψη
6. **Βάση Δεδομένων Διανυσμάτων Chroma** - Υβριδική σημασιολογική + αναζήτηση λέξεων-κλειδιών για έξυπνη ανάκτηση πλαισίου
Δείτε [Επισκόπηση Αρχιτεκτονικής](https://docs.claude-mem.ai/architecture/overview) για λεπτομέρειες.
---
## Δεξιότητα mem-search
Το Claude-Mem παρέχει έξυπνη αναζήτηση μέσω της δεξιότητας mem-search που ενεργοποιείται αυτόματα όταν ρωτάτε για παλαιότερη εργασία:
**Πώς Λειτουργεί:**
- Απλά ρωτήστε φυσικά: *"Τι κάναμε την προηγούμενη συνεδρία;"* ή *"Διορθώσαμε αυτό το σφάλμα νωρίτερα;"*
- Το Claude ενεργοποιεί αυτόματα τη δεξιότητα mem-search για να βρει σχετικό πλαίσιο
**Διαθέσιμες Λειτουργίες Αναζήτησης:**
1. **Search Observations** - Αναζήτηση πλήρους κειμένου σε παρατηρήσεις
2. **Search Sessions** - Αναζήτηση πλήρους κειμένου σε περιλήψεις συνεδριών
3. **Search Prompts** - Αναζήτηση ακατέργαστων αιτημάτων χρήστη
4. **By Concept** - Εύρεση βάσει ετικετών εννοιών (discovery, problem-solution, pattern, κ.λπ.)
5. **By File** - Εύρεση παρατηρήσεων που αναφέρονται σε συγκεκριμένα αρχεία
6. **By Type** - Εύρεση βάσει τύπου (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Λήψη πρόσφατου πλαισίου συνεδρίας για ένα έργο
8. **Timeline** - Λήψη ενοποιημένης χρονολογικής γραμμής πλαισίου γύρω από συγκεκριμένο χρονικό σημείο
9. **Timeline by Query** - Αναζήτηση παρατηρήσεων και λήψη πλαισίου χρονολογικής γραμμής γύρω από την καλύτερη αντιστοιχία
10. **API Help** - Λήψη τεκμηρίωσης API αναζήτησης
**Παραδείγματα Ερωτημάτων Φυσικής Γλώσσας:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Δείτε [Οδηγό Εργαλείων Αναζήτησης](https://docs.claude-mem.ai/usage/search-tools) για λεπτομερή παραδείγματα.
---
## Χαρακτηριστικά Beta
Το Claude-Mem προσφέρει ένα **κανάλι beta** με πειραματικά χαρακτηριστικά όπως το **Endless Mode** (βιομιμητική αρχιτεκτονική μνήμης για εκτεταμένες συνεδρίες). Εναλλαγή μεταξύ σταθερών και beta εκδόσεων από τη διεπαφή web viewer στο http://localhost:37777 → Settings.
Δείτε **[Τεκμηρίωση Χαρακτηριστικών Beta](https://docs.claude-mem.ai/beta-features)** για λεπτομέρειες σχετικά με το Endless Mode και πώς να το δοκιμάσετε.
---
## Απαιτήσεις Συστήματος
- **Node.js**: 18.0.0 ή νεότερο
- **Claude Code**: Τελευταία έκδοση με υποστήριξη plugin
- **Bun**: JavaScript runtime και διαχειριστής διεργασιών (εγκαθίσταται αυτόματα αν λείπει)
- **uv**: Διαχειριστής πακέτων Python για αναζήτηση διανυσμάτων (εγκαθίσταται αυτόματα αν λείπει)
- **SQLite 3**: Για μόνιμη αποθήκευση (συμπεριλαμβάνεται)
---
## Διαμόρφωση
Οι ρυθμίσεις διαχειρίζονται στο `~/.claude-mem/settings.json` (δημιουργείται αυτόματα με προεπιλογές κατά την πρώτη εκτέλεση). Διαμορφώστε το μοντέλο AI, τη θύρα worker, τον κατάλογο δεδομένων, το επίπεδο καταγραφής και τις ρυθμίσεις εισαγωγής πλαισίου.
Δείτε τον **[Οδηγό Διαμόρφωσης](https://docs.claude-mem.ai/configuration)** για όλες τις διαθέσιμες ρυθμίσεις και παραδείγματα.
---
## Ανάπτυξη
Δείτε τον **[Οδηγό Ανάπτυξης](https://docs.claude-mem.ai/development)** για οδηγίες κατασκευής, δοκιμών και ροής εργασίας συνεισφοράς.
---
## Αντιμετώπιση Προβλημάτων
Εάν αντιμετωπίζετε προβλήματα, περιγράψτε το πρόβλημα στο Claude και η δεξιότητα troubleshoot θα διαγνώσει αυτόματα και θα παράσχει λύσεις.
Δείτε τον **[Οδηγό Αντιμετώπισης Προβλημάτων](https://docs.claude-mem.ai/troubleshooting)** για συνήθη προβλήματα και λύσεις.
---
## Αναφορές Σφαλμάτων
Δημιουργήστε περιεκτικές αναφορές σφαλμάτων με την αυτοματοποιημένη γεννήτρια:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Συνεισφορά
Οι συνεισφορές είναι ευπρόσδεκτες! Παρακαλώ:
1. Κάντε Fork το repository
2. Δημιουργήστε ένα feature branch
3. Κάντε τις αλλαγές σας με δοκιμές
4. Ενημερώστε την τεκμηρίωση
5. Υποβάλετε ένα Pull Request
Δείτε τον [Οδηγό Ανάπτυξης](https://docs.claude-mem.ai/development) για τη ροή εργασίας συνεισφοράς.
---
## Άδεια Χρήσης
Αυτό το έργο διατίθεται με άδεια **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Με επιφύλαξη παντός δικαιώματος.
Δείτε το αρχείο [LICENSE](LICENSE) για πλήρεις λεπτομέρειες.
**Τι Σημαίνει Αυτό:**
- Μπορείτε να χρησιμοποιήσετε, να τροποποιήσετε και να διανείμετε ελεύθερα αυτό το λογισμικό
- Εάν τροποποιήσετε και αναπτύξετε σε διακομιστή δικτύου, πρέπει να καταστήσετε διαθέσιμο τον πηγαίο κώδικά σας
- Τα παράγωγα έργα πρέπει επίσης να διατίθενται με άδεια AGPL-3.0
- ΔΕΝ υπάρχει ΕΓΓΥΗΣΗ για αυτό το λογισμικό
**Σημείωση για το Ragtime**: Ο κατάλογος `ragtime/` διατίθεται χωριστά με άδεια **PolyForm Noncommercial License 1.0.0**. Δείτε το [ragtime/LICENSE](ragtime/LICENSE) για λεπτομέρειες.
---
## Υποστήριξη
- **Τεκμηρίωση**: [docs/](docs/)
- **Ζητήματα**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Συγγραφέας**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Κατασκευασμένο με Claude Agent SDK** | **Τροφοδοτείται από Claude Code** | **Φτιαγμένο με TypeScript**

303
docs/i18n/README.es.md Normal file
View File

@@ -0,0 +1,303 @@
🌐 Esta es una traducción automática. ¡Las correcciones de la comunidad son bienvenidas!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Sistema de compresión de memoria persistente construido para <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#inicio-rápido">Inicio Rápido</a> •
<a href="#cómo-funciona">Cómo Funciona</a> •
<a href="#herramientas-de-búsqueda-mcp">Herramientas de Búsqueda</a> •
<a href="#documentación">Documentación</a> •
<a href="#configuración">Configuración</a> •
<a href="#solución-de-problemas">Solución de Problemas</a> •
<a href="#licencia">Licencia</a>
</p>
<p align="center">
Claude-Mem preserva el contexto sin interrupciones entre sesiones al capturar automáticamente observaciones de uso de herramientas, generar resúmenes semánticos y ponerlos a disposición de sesiones futuras. Esto permite a Claude mantener la continuidad del conocimiento sobre proyectos incluso después de que las sesiones terminen o se reconecten.
</p>
---
## Inicio Rápido
Inicia una nueva sesión de Claude Code en la terminal e ingresa los siguientes comandos:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Reinicia Claude Code. El contexto de sesiones anteriores aparecerá automáticamente en nuevas sesiones.
**Características Principales:**
- 🧠 **Memoria Persistente** - El contexto sobrevive entre sesiones
- 📊 **Divulgación Progresiva** - Recuperación de memoria en capas con visibilidad del costo de tokens
- 🔍 **Búsqueda Basada en Habilidades** - Consulta el historial de tu proyecto con la habilidad mem-search
- 🖥️ **Interfaz de Visor Web** - Transmisión de memoria en tiempo real en http://localhost:37777
- 💻 **Habilidad para Claude Desktop** - Busca en la memoria desde conversaciones de Claude Desktop
- 🔒 **Control de Privacidad** - Usa etiquetas `<private>` para excluir contenido sensible del almacenamiento
- ⚙️ **Configuración de Contexto** - Control detallado sobre qué contexto se inyecta
- 🤖 **Operación Automática** - No se requiere intervención manual
- 🔗 **Citas** - Referencias a observaciones pasadas con IDs (accede vía http://localhost:37777/api/observation/{id} o visualiza todas en el visor web en http://localhost:37777)
- 🧪 **Canal Beta** - Prueba características experimentales como Endless Mode mediante cambio de versión
---
## Documentación
📚 **[Ver Documentación Completa](docs/)** - Explora documentos markdown en GitHub
### Primeros Pasos
- **[Guía de Instalación](https://docs.claude-mem.ai/installation)** - Inicio rápido e instalación avanzada
- **[Guía de Uso](https://docs.claude-mem.ai/usage/getting-started)** - Cómo funciona Claude-Mem automáticamente
- **[Herramientas de Búsqueda](https://docs.claude-mem.ai/usage/search-tools)** - Consulta el historial de tu proyecto con lenguaje natural
- **[Características Beta](https://docs.claude-mem.ai/beta-features)** - Prueba características experimentales como Endless Mode
### Mejores Prácticas
- **[Ingeniería de Contexto](https://docs.claude-mem.ai/context-engineering)** - Principios de optimización de contexto para agentes de IA
- **[Divulgación Progresiva](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofía detrás de la estrategia de preparación de contexto de Claude-Mem
### Arquitectura
- **[Descripción General](https://docs.claude-mem.ai/architecture/overview)** - Componentes del sistema y flujo de datos
- **[Evolución de la Arquitectura](https://docs.claude-mem.ai/architecture-evolution)** - El viaje de v3 a v5
- **[Arquitectura de Hooks](https://docs.claude-mem.ai/hooks-architecture)** - Cómo Claude-Mem usa hooks de ciclo de vida
- **[Referencia de Hooks](https://docs.claude-mem.ai/architecture/hooks)** - 7 scripts de hooks explicados
- **[Servicio Worker](https://docs.claude-mem.ai/architecture/worker-service)** - API HTTP y gestión de Bun
- **[Base de Datos](https://docs.claude-mem.ai/architecture/database)** - Esquema SQLite y búsqueda FTS5
- **[Arquitectura de Búsqueda](https://docs.claude-mem.ai/architecture/search-architecture)** - Búsqueda híbrida con base de datos vectorial Chroma
### Configuración y Desarrollo
- **[Configuración](https://docs.claude-mem.ai/configuration)** - Variables de entorno y ajustes
- **[Desarrollo](https://docs.claude-mem.ai/development)** - Compilación, pruebas y contribución
- **[Solución de Problemas](https://docs.claude-mem.ai/troubleshooting)** - Problemas comunes y soluciones
---
## Cómo Funciona
**Componentes Principales:**
1. **5 Hooks de Ciclo de Vida** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 scripts de hooks)
2. **Instalación Inteligente** - Verificador de dependencias en caché (script pre-hook, no un hook de ciclo de vida)
3. **Servicio Worker** - API HTTP en el puerto 37777 con interfaz de visor web y 10 endpoints de búsqueda, gestionado por Bun
4. **Base de Datos SQLite** - Almacena sesiones, observaciones, resúmenes
5. **Habilidad mem-search** - Consultas en lenguaje natural con divulgación progresiva
6. **Base de Datos Vectorial Chroma** - Búsqueda híbrida semántica + palabras clave para recuperación inteligente de contexto
Ver [Descripción General de la Arquitectura](https://docs.claude-mem.ai/architecture/overview) para más detalles.
---
## Habilidad mem-search
Claude-Mem proporciona búsqueda inteligente a través de la habilidad mem-search que se invoca automáticamente cuando preguntas sobre trabajo previo:
**Cómo Funciona:**
- Simplemente pregunta naturalmente: *"¿Qué hicimos en la última sesión?"* o *"¿Arreglamos este error antes?"*
- Claude invoca automáticamente la habilidad mem-search para encontrar contexto relevante
**Operaciones de Búsqueda Disponibles:**
1. **Search Observations** - Búsqueda de texto completo en observaciones
2. **Search Sessions** - Búsqueda de texto completo en resúmenes de sesiones
3. **Search Prompts** - Búsqueda de solicitudes de usuario sin procesar
4. **By Concept** - Buscar por etiquetas de concepto (discovery, problem-solution, pattern, etc.)
5. **By File** - Buscar observaciones que referencian archivos específicos
6. **By Type** - Buscar por tipo (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Obtener contexto de sesión reciente para un proyecto
8. **Timeline** - Obtener línea de tiempo unificada de contexto alrededor de un punto específico en el tiempo
9. **Timeline by Query** - Buscar observaciones y obtener contexto de línea de tiempo alrededor de la mejor coincidencia
10. **API Help** - Obtener documentación de la API de búsqueda
**Ejemplos de Consultas en Lenguaje Natural:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Ver [Guía de Herramientas de Búsqueda](https://docs.claude-mem.ai/usage/search-tools) para ejemplos detallados.
---
## Características Beta
Claude-Mem ofrece un **canal beta** con características experimentales como **Endless Mode** (arquitectura de memoria biomimética para sesiones extendidas). Cambia entre versiones estables y beta desde la interfaz del visor web en http://localhost:37777 → Settings.
Ver **[Documentación de Características Beta](https://docs.claude-mem.ai/beta-features)** para detalles sobre Endless Mode y cómo probarlo.
---
## Requisitos del Sistema
- **Node.js**: 18.0.0 o superior
- **Claude Code**: Última versión con soporte de plugins
- **Bun**: Runtime de JavaScript y gestor de procesos (se instala automáticamente si falta)
- **uv**: Gestor de paquetes de Python para búsqueda vectorial (se instala automáticamente si falta)
- **SQLite 3**: Para almacenamiento persistente (incluido)
---
## Configuración
Los ajustes se gestionan en `~/.claude-mem/settings.json` (se crea automáticamente con valores predeterminados en la primera ejecución). Configura el modelo de IA, puerto del worker, directorio de datos, nivel de registro y ajustes de inyección de contexto.
Ver la **[Guía de Configuración](https://docs.claude-mem.ai/configuration)** para todos los ajustes disponibles y ejemplos.
---
## Desarrollo
Ver la **[Guía de Desarrollo](https://docs.claude-mem.ai/development)** para instrucciones de compilación, pruebas y flujo de contribución.
---
## Solución de Problemas
Si experimentas problemas, describe el problema a Claude y la habilidad troubleshoot diagnosticará automáticamente y proporcionará soluciones.
Ver la **[Guía de Solución de Problemas](https://docs.claude-mem.ai/troubleshooting)** para problemas comunes y soluciones.
---
## Reportes de Errores
Crea reportes de errores completos con el generador automático:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Contribuciones
¡Las contribuciones son bienvenidas! Por favor:
1. Haz fork del repositorio
2. Crea una rama de característica
3. Realiza tus cambios con pruebas
4. Actualiza la documentación
5. Envía un Pull Request
Ver [Guía de Desarrollo](https://docs.claude-mem.ai/development) para el flujo de contribución.
---
## Licencia
Este proyecto está licenciado bajo la **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Todos los derechos reservados.
Ver el archivo [LICENSE](LICENSE) para detalles completos.
**Lo Que Esto Significa:**
- Puedes usar, modificar y distribuir este software libremente
- Si modificas y despliegas en un servidor de red, debes hacer tu código fuente disponible
- Los trabajos derivados también deben estar licenciados bajo AGPL-3.0
- NO hay GARANTÍA para este software
**Nota sobre Ragtime**: El directorio `ragtime/` está licenciado por separado bajo la **PolyForm Noncommercial License 1.0.0**. Ver [ragtime/LICENSE](ragtime/LICENSE) para detalles.
---
## Soporte
- **Documentación**: [docs/](docs/)
- **Problemas**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repositorio**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autor**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Construido con Claude Agent SDK** | **Impulsado por Claude Code** | **Hecho con TypeScript**

301
docs/i18n/README.fi.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 Tämä on automaattinen käännös. Yhteisön korjaukset ovat tervetulleita!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Pysyvä muistinpakkaamisjärjestelmä, joka on rakennettu <a href="https://claude.com/claude-code" target="_blank">Claude Code</a> -ympäristöön.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#pikaopas">Pikaopas</a> •
<a href="#miten-se-toimii">Miten se toimii</a> •
<a href="#hakutyökalut">Hakutyökalut</a> •
<a href="#dokumentaatio">Dokumentaatio</a> •
<a href="#asetukset">Asetukset</a> •
<a href="#vianmääritys">Vianmääritys</a> •
<a href="#lisenssi">Lisenssi</a>
</p>
<p align="center">
Claude-Mem säilyttää kontekstin saumattomasti istuntojen välillä tallentamalla automaattisesti työkalujen käyttöhavaintoja, luomalla semanttisia yhteenvetoja ja asettamalla ne tulevien istuntojen saataville. Tämä mahdollistaa Clauden säilyttää tiedon jatkuvuuden projekteista senkin jälkeen, kun istunnot päättyvät tai yhteys palautuu.
</p>
---
## Pikaopas
Aloita uusi Claude Code -istunto terminaalissa ja syötä seuraavat komennot:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Käynnistä Claude Code uudelleen. Aiempien istuntojen konteksti ilmestyy automaattisesti uusiin istuntoihin.
**Keskeiset ominaisuudet:**
- 🧠 **Pysyvä muisti** - Konteksti säilyy istuntojen välillä
- 📊 **Asteittainen paljastaminen** - Kerrostettu muistin haku tokenikustannusten näkyvyydellä
- 🔍 **Taitopohjainen haku** - Kysy projektihistoriaasi mem-search-taidolla
- 🖥️ **Web-katselukäyttöliittymä** - Reaaliaikainen muistivirta osoitteessa http://localhost:37777
- 💻 **Claude Desktop -taito** - Hae muistista Claude Desktop -keskusteluissa
- 🔒 **Yksityisyyden hallinta** - Käytä `<private>`-tageja arkaluonteisen sisällön poissulkemiseen tallennuksesta
- ⚙️ **Kontekstin määrittely** - Tarkka hallinta siitä, mikä konteksti injektoidaan
- 🤖 **Automaattinen toiminta** - Ei vaadi manuaalista puuttumista
- 🔗 **Viittaukset** - Viittaa aiempiin havaintoihin ID:llä (käytettävissä osoitteessa http://localhost:37777/api/observation/{id} tai näytä kaikki web-katselussa osoitteessa http://localhost:37777)
- 🧪 **Beta-kanava** - Kokeile kokeellisia ominaisuuksia kuten Endless Mode versionvaihdolla
---
## Dokumentaatio
📚 **[Näytä täydellinen dokumentaatio](docs/)** - Selaa markdown-dokumentteja GitHubissa
### Aloitus
- **[Asennusopas](https://docs.claude-mem.ai/installation)** - Pikaopas ja edistynyt asennus
- **[Käyttöopas](https://docs.claude-mem.ai/usage/getting-started)** - Miten Claude-Mem toimii automaattisesti
- **[Hakutyökalut](https://docs.claude-mem.ai/usage/search-tools)** - Kysy projektihistoriaasi luonnollisella kielellä
- **[Beta-ominaisuudet](https://docs.claude-mem.ai/beta-features)** - Kokeile kokeellisia ominaisuuksia kuten Endless Mode
### Parhaat käytännöt
- **[Kontekstisuunnittelu](https://docs.claude-mem.ai/context-engineering)** - AI-agentin kontekstin optimointiperiaatteet
- **[Asteittainen paljastaminen](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofia Claude-Mem-kontekstin valmistelustrategian takana
### Arkkitehtuuri
- **[Yleiskatsaus](https://docs.claude-mem.ai/architecture/overview)** - Järjestelmän komponentit ja datavirta
- **[Arkkitehtuurin kehitys](https://docs.claude-mem.ai/architecture-evolution)** - Matka versiosta v3 versioon v5
- **[Koukku-arkkitehtuuri](https://docs.claude-mem.ai/hooks-architecture)** - Miten Claude-Mem käyttää elinkaarikkoukkuja
- **[Koukku-viittaus](https://docs.claude-mem.ai/architecture/hooks)** - 7 koukku-skriptiä selitettynä
- **[Worker-palvelu](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API ja Bun-hallinta
- **[Tietokanta](https://docs.claude-mem.ai/architecture/database)** - SQLite-skeema ja FTS5-haku
- **[Hakuarkkitehtuuri](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybridihaku Chroma-vektoritietokannalla
### Asetukset ja kehitys
- **[Asetukset](https://docs.claude-mem.ai/configuration)** - Ympäristömuuttujat ja asetukset
- **[Kehitys](https://docs.claude-mem.ai/development)** - Rakentaminen, testaus, osallistuminen
- **[Vianmääritys](https://docs.claude-mem.ai/troubleshooting)** - Yleiset ongelmat ja ratkaisut
---
## Miten se toimii
**Keskeiset komponentit:**
1. **5 elinkaarikoukua** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 koukku-skriptiä)
2. **Älykäs asennus** - Välimuistettu riippuvuuksien tarkistaja (esikoukku-skripti, ei elinkaarikkoukku)
3. **Worker-palvelu** - HTTP API portissa 37777 web-katselukäyttöliittymällä ja 10 hakupäätepisteellä, Bun-hallinnoimana
4. **SQLite-tietokanta** - Tallentaa istunnot, havainnot, yhteenvedot
5. **mem-search-taito** - Luonnollisen kielen kyselyt asteittaisella paljastamisella
6. **Chroma-vektoritietokanta** - Hybridi semanttinen + avainsanahaku älykkääseen kontekstin hakuun
Katso [Arkkitehtuurin yleiskatsaus](https://docs.claude-mem.ai/architecture/overview) yksityiskohdista.
---
## mem-search-taito
Claude-Mem tarjoaa älykkään haun mem-search-taidon kautta, joka käynnistyy automaattisesti kun kysyt aiemmasta työstä:
**Miten se toimii:**
- Kysy vain luonnollisesti: *"Mitä teimme viime istunnossa?"* tai *"Korjasimmeko tämän bugin aiemmin?"*
- Claude käynnistää automaattisesti mem-search-taidon löytääkseen relevantin kontekstin
**Saatavilla olevat hakutoiminnot:**
1. **Hae havaintoja** - Koko tekstin haku havainnoissa
2. **Hae istuntoja** - Koko tekstin haku istuntojen yhteenvedoissa
3. **Hae prompteja** - Hae raakoista käyttäjäpyynnöistä
4. **Konseptin mukaan** - Hae konseptitageilla (discovery, problem-solution, pattern, jne.)
5. **Tiedoston mukaan** - Hae tiettyihin tiedostoihin viittaavia havaintoja
6. **Tyypin mukaan** - Hae tyypillä (decision, bugfix, feature, refactor, discovery, change)
7. **Viimeaikainen konteksti** - Hae projektin viimeaikainen istuntokonteksti
8. **Aikajana** - Hae yhtenäinen aikajana kontekstista tietyn ajankohdan ympärillä
9. **Aikajana kyselyn mukaan** - Hae havaintoja ja saa aikalinjakonteksti parhaan osuman ympärillä
10. **API-ohje** - Hae haku-API:n dokumentaatio
**Esimerkkejä luonnollisen kielen kyselyistä:**
```
"Mitkä bugit korjasimme viime istunnossa?"
"Miten toteutimme autentikoinnin?"
"Mitä muutoksia tehtiin worker-service.ts:ään?"
"Näytä viimeaikainen työ tässä projektissa"
"Mitä tapahtui kun lisäsimme katselukäyttöliittymän?"
```
Katso [Hakutyökalujen opas](https://docs.claude-mem.ai/usage/search-tools) yksityiskohtaisia esimerkkejä varten.
---
## Beta-ominaisuudet
Claude-Mem tarjoaa **beta-kanavan** kokeellisilla ominaisuuksilla kuten **Endless Mode** (biomimeettinen muistiarkkitehtuuri pidennetyille istunnoille). Vaihda vakaan ja beta-version välillä web-katselukäyttöliittymästä osoitteessa http://localhost:37777 → Settings.
Katso **[Beta-ominaisuuksien dokumentaatio](https://docs.claude-mem.ai/beta-features)** yksityiskohdista Endless Moden ja sen kokeilemisen osalta.
---
## Järjestelmävaatimukset
- **Node.js**: 18.0.0 tai uudempi
- **Claude Code**: Uusin versio plugin-tuella
- **Bun**: JavaScript-ajoympäristö ja prosessinhallinta (asennetaan automaattisesti jos puuttuu)
- **uv**: Python-paketinhallinta vektorihakuun (asennetaan automaattisesti jos puuttuu)
- **SQLite 3**: Pysyvälle tallennukselle (sisältyy)
---
## Asetukset
Asetuksia hallitaan tiedostossa `~/.claude-mem/settings.json` (luodaan automaattisesti oletusarvoilla ensimmäisellä suorituskerralla). Määritä AI-malli, worker-portti, datahakemisto, lokitaso ja kontekstin injektointiasetukset.
Katso **[Asetusopas](https://docs.claude-mem.ai/configuration)** kaikista saatavilla olevista asetuksista ja esimerkeistä.
---
## Kehitys
Katso **[Kehitysopas](https://docs.claude-mem.ai/development)** rakennusohjeista, testauksesta ja osallistumisen työnkulusta.
---
## Vianmääritys
Jos kohtaat ongelmia, kuvaile ongelma Claudelle ja troubleshoot-taito diagnosoi automaattisesti ja tarjoaa korjauksia.
Katso **[Vianmääritysopas](https://docs.claude-mem.ai/troubleshooting)** yleisistä ongelmista ja ratkaisuista.
---
## Bugiraportit
Luo kattavia bugiraportteja automaattisella generaattorilla:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Osallistuminen
Osallistuminen on tervetullutta! Ole hyvä:
1. Haarukoi repositorio
2. Luo ominaisuushaara
3. Tee muutoksesi testeineen
4. Päivitä dokumentaatio
5. Lähetä Pull Request
Katso [Kehitysopas](https://docs.claude-mem.ai/development) osallistumisen työnkulusta.
---
## Lisenssi
Tämä projekti on lisensoitu **GNU Affero General Public License v3.0** (AGPL-3.0) -lisenssillä.
Copyright (C) 2025 Alex Newman (@thedotmack). Kaikki oikeudet pidätetään.
Katso [LICENSE](LICENSE)-tiedosto täydellisistä yksityiskohdista.
**Mitä tämä tarkoittaa:**
- Voit käyttää, muokata ja jakaa tätä ohjelmistoa vapaasti
- Jos muokkaat ja otat käyttöön verkkopalvelimella, sinun on asetettava lähdekoodisi saataville
- Johdannaisten teosten on myös oltava AGPL-3.0-lisensoituja
- Tälle ohjelmistolle EI OLE TAKUUTA
**Huomautus Ragtimesta**: `ragtime/`-hakemisto on erikseen lisensoitu **PolyForm Noncommercial License 1.0.0** -lisenssillä. Katso [ragtime/LICENSE](ragtime/LICENSE) yksityiskohdista.
---
## Tuki
- **Dokumentaatio**: [docs/](docs/)
- **Ongelmat**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repositorio**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Tekijä**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Rakennettu Claude Agent SDK:lla** | **Claude Coden voimalla** | **Tehty TypeScriptillä**

304
docs/i18n/README.fr.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 Ceci est une traduction automatisée. Les corrections de la communauté sont les bienvenues !
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Système de compression de mémoire persistante conçu pour <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#démarrage-rapide">Démarrage rapide</a> •
<a href="#comment-ça-fonctionne">Comment ça fonctionne</a> •
<a href="#compétence-mem-search">Outils de recherche</a> •
<a href="#documentation">Documentation</a> •
<a href="#configuration">Configuration</a> •
<a href="#dépannage">Dépannage</a> •
<a href="#licence">Licence</a>
</p>
<p align="center">
Claude-Mem préserve de manière transparente le contexte d'une session à l'autre en capturant automatiquement les observations d'utilisation des outils, en générant des résumés sémantiques et en les rendant disponibles pour les sessions futures. Cela permet à Claude de maintenir la continuité des connaissances sur les projets même après la fin des sessions ou la reconnexion.
</p>
---
## Démarrage rapide
Démarrez une nouvelle session Claude Code dans le terminal et saisissez les commandes suivantes :
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Redémarrez Claude Code. Le contexte des sessions précédentes apparaîtra automatiquement dans les nouvelles sessions.
**Fonctionnalités clés :**
- 🧠 **Mémoire persistante** - Le contexte survit d'une session à l'autre
- 📊 **Divulgation progressive** - Récupération de mémoire en couches avec visibilité du coût en tokens
- 🔍 **Recherche basée sur les compétences** - Interrogez l'historique de votre projet avec la compétence mem-search
- 🖥️ **Interface Web de visualisation** - Flux de mémoire en temps réel à http://localhost:37777
- 💻 **Compétence Claude Desktop** - Recherchez dans la mémoire depuis les conversations Claude Desktop
- 🔒 **Contrôle de la confidentialité** - Utilisez les balises `<private>` pour exclure le contenu sensible du stockage
- ⚙️ **Configuration du contexte** - Contrôle précis sur le contexte injecté
- 🤖 **Fonctionnement automatique** - Aucune intervention manuelle requise
- 🔗 **Citations** - Référencez les observations passées avec des ID (accès via http://localhost:37777/api/observation/{id} ou visualisez tout dans l'interface web à http://localhost:37777)
- 🧪 **Canal bêta** - Essayez des fonctionnalités expérimentales comme le mode Endless via le changement de version
---
## Documentation
📚 **[Voir la documentation complète](docs/)** - Parcourez la documentation markdown sur GitHub
### Pour commencer
- **[Guide d'installation](https://docs.claude-mem.ai/installation)** - Démarrage rapide et installation avancée
- **[Guide d'utilisation](https://docs.claude-mem.ai/usage/getting-started)** - Comment Claude-Mem fonctionne automatiquement
- **[Outils de recherche](https://docs.claude-mem.ai/usage/search-tools)** - Interrogez l'historique de votre projet en langage naturel
- **[Fonctionnalités bêta](https://docs.claude-mem.ai/beta-features)** - Essayez des fonctionnalités expérimentales comme le mode Endless
### Bonnes pratiques
- **[Ingénierie du contexte](https://docs.claude-mem.ai/context-engineering)** - Principes d'optimisation du contexte pour les agents IA
- **[Divulgation progressive](https://docs.claude-mem.ai/progressive-disclosure)** - Philosophie derrière la stratégie d'amorçage du contexte de Claude-Mem
### Architecture
- **[Vue d'ensemble](https://docs.claude-mem.ai/architecture/overview)** - Composants du système et flux de données
- **[Évolution de l'architecture](https://docs.claude-mem.ai/architecture-evolution)** - Le parcours de la v3 à la v5
- **[Architecture des hooks](https://docs.claude-mem.ai/hooks-architecture)** - Comment Claude-Mem utilise les hooks de cycle de vie
- **[Référence des hooks](https://docs.claude-mem.ai/architecture/hooks)** - Explication des 7 scripts de hooks
- **[Service Worker](https://docs.claude-mem.ai/architecture/worker-service)** - API HTTP et gestion Bun
- **[Base de données](https://docs.claude-mem.ai/architecture/database)** - Schéma SQLite et recherche FTS5
- **[Architecture de recherche](https://docs.claude-mem.ai/architecture/search-architecture)** - Recherche hybride avec la base de données vectorielle Chroma
### Configuration et développement
- **[Configuration](https://docs.claude-mem.ai/configuration)** - Variables d'environnement et paramètres
- **[Développement](https://docs.claude-mem.ai/development)** - Compilation, tests, contribution
- **[Dépannage](https://docs.claude-mem.ai/troubleshooting)** - Problèmes courants et solutions
---
## Comment ça fonctionne
**Composants principaux :**
1. **5 hooks de cycle de vie** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 scripts de hooks)
2. **Installation intelligente** - Vérificateur de dépendances en cache (script pré-hook, pas un hook de cycle de vie)
3. **Service Worker** - API HTTP sur le port 37777 avec interface web de visualisation et 10 points de terminaison de recherche, géré par Bun
4. **Base de données SQLite** - Stocke les sessions, observations, résumés
5. **Compétence mem-search** - Requêtes en langage naturel avec divulgation progressive
6. **Base de données vectorielle Chroma** - Recherche hybride sémantique + mots-clés pour une récupération de contexte intelligente
Voir [Vue d'ensemble de l'architecture](https://docs.claude-mem.ai/architecture/overview) pour plus de détails.
---
## Compétence mem-search
Claude-Mem fournit une recherche intelligente via la compétence mem-search qui s'invoque automatiquement lorsque vous posez des questions sur le travail passé :
**Comment ça fonctionne :**
- Posez simplement des questions naturellement : *"Qu'avons-nous fait lors de la dernière session ?"* ou *"Avons-nous déjà corrigé ce bug ?"*
- Claude invoque automatiquement la compétence mem-search pour trouver le contexte pertinent
**Opérations de recherche disponibles :**
1. **Rechercher des observations** - Recherche plein texte dans les observations
2. **Rechercher des sessions** - Recherche plein texte dans les résumés de sessions
3. **Rechercher des invites** - Rechercher dans les demandes brutes des utilisateurs
4. **Par concept** - Trouver par étiquettes de concept (discovery, problem-solution, pattern, etc.)
5. **Par fichier** - Trouver les observations faisant référence à des fichiers spécifiques
6. **Par type** - Trouver par type (decision, bugfix, feature, refactor, discovery, change)
7. **Contexte récent** - Obtenir le contexte récent d'une session pour un projet
8. **Timeline** - Obtenir une chronologie unifiée du contexte autour d'un point spécifique dans le temps
9. **Timeline par requête** - Rechercher des observations et obtenir le contexte de la chronologie autour de la meilleure correspondance
10. **Aide API** - Obtenir la documentation de l'API de recherche
**Exemples de requêtes en langage naturel :**
```
"Quels bugs avons-nous corrigés lors de la dernière session ?"
"Comment avons-nous implémenté l'authentification ?"
"Quels changements ont été apportés à worker-service.ts ?"
"Montrez-moi le travail récent sur ce projet"
"Que se passait-il lorsque nous avons ajouté l'interface de visualisation ?"
```
Voir le [Guide des outils de recherche](https://docs.claude-mem.ai/usage/search-tools) pour des exemples détaillés.
---
## Fonctionnalités bêta
Claude-Mem propose un **canal bêta** avec des fonctionnalités expérimentales comme le **mode Endless** (architecture de mémoire biomimétique pour les sessions étendues). Basculez entre les versions stables et bêta depuis l'interface web de visualisation à http://localhost:37777 → Paramètres.
Voir la **[Documentation des fonctionnalités bêta](https://docs.claude-mem.ai/beta-features)** pour plus de détails sur le mode Endless et comment l'essayer.
---
## Configuration système requise
- **Node.js** : 18.0.0 ou supérieur
- **Claude Code** : Dernière version avec support des plugins
- **Bun** : Runtime JavaScript et gestionnaire de processus (installé automatiquement si manquant)
- **uv** : Gestionnaire de packages Python pour la recherche vectorielle (installé automatiquement si manquant)
- **SQLite 3** : Pour le stockage persistant (inclus)
---
## Configuration
Les paramètres sont gérés dans `~/.claude-mem/settings.json` (créé automatiquement avec les valeurs par défaut au premier lancement). Configurez le modèle IA, le port du worker, le répertoire de données, le niveau de journalisation et les paramètres d'injection de contexte.
Voir le **[Guide de configuration](https://docs.claude-mem.ai/configuration)** pour tous les paramètres disponibles et des exemples.
---
## Développement
Voir le **[Guide de développement](https://docs.claude-mem.ai/development)** pour les instructions de compilation, les tests et le flux de contribution.
---
## Dépannage
Si vous rencontrez des problèmes, décrivez le problème à Claude et la compétence troubleshoot diagnostiquera automatiquement et fournira des solutions.
Voir le **[Guide de dépannage](https://docs.claude-mem.ai/troubleshooting)** pour les problèmes courants et les solutions.
---
## Rapports de bugs
Créez des rapports de bugs complets avec le générateur automatisé :
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Contribuer
Les contributions sont les bienvenues ! Veuillez :
1. Forker le dépôt
2. Créer une branche de fonctionnalité
3. Effectuer vos modifications avec des tests
4. Mettre à jour la documentation
5. Soumettre une Pull Request
Voir le [Guide de développement](https://docs.claude-mem.ai/development) pour le flux de contribution.
---
## Licence
Ce projet est sous licence **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Tous droits réservés.
Voir le fichier [LICENSE](LICENSE) pour tous les détails.
**Ce que cela signifie :**
- Vous pouvez utiliser, modifier et distribuer ce logiciel librement
- Si vous modifiez et déployez sur un serveur réseau, vous devez rendre votre code source disponible
- Les œuvres dérivées doivent également être sous licence AGPL-3.0
- Il n'y a AUCUNE GARANTIE pour ce logiciel
**Note sur Ragtime** : Le répertoire `ragtime/` est sous licence séparée sous la **PolyForm Noncommercial License 1.0.0**. Voir [ragtime/LICENSE](ragtime/LICENSE) pour plus de détails.
---
## Support
- **Documentation** : [docs/](docs/)
- **Issues** : [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Dépôt** : [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Auteur** : Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Construit avec Claude Agent SDK** | **Propulsé par Claude Code** | **Fait avec TypeScript**
---

301
docs/i18n/README.he.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 זהו תרגום אוטומטי. תיקונים מהקהילה יתקבלו בברכה!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">מערכת דחיסת זיכרון מתמשך שנבנתה עבור <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#quick-start">התחלה מהירה</a> •
<a href="#how-it-works">איך זה עובד</a> •
<a href="#mcp-search-tools">כלי חיפוש</a> •
<a href="#documentation">תיעוד</a> •
<a href="#configuration">הגדרות</a> •
<a href="#troubleshooting">פתרון בעיות</a> •
<a href="#license">רישיון</a>
</p>
<p align="center">
Claude-Mem משמר הקשר בצורה חלקה בין הפעלות על ידי לכידה אוטומטית של תצפיות על שימוש בכלים, יצירת סיכומים סמנטיים, והנגשתם להפעלות עתידיות. זה מאפשר ל-Claude לשמור על המשכיות של ידע על פרויקטים גם לאחר שהפעלות מסתיימות או מתחברות מחדש.
</p>
---
## התחלה מהירה
התחל הפעלה חדשה של Claude Code בטרמינל והזן את הפקודות הבאות:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
הפעל מחדש את Claude Code. הקשר מהפעלות קודמות יופיע אוטומטית בהפעלות חדשות.
**תכונות עיקריות:**
- 🧠 **זיכרון מתמשך** - הקשר שורד בין הפעלות
- 📊 **גילוי מדורג** - אחזור זיכרון רב-שכבתי עם נראות עלות טוקנים
- 🔍 **חיפוש מבוסס-מיומנויות** - שאל את היסטוריית הפרויקט שלך עם מיומנות mem-search
- 🖥️ **ממשק צופה אינטרנט** - זרימת זיכרון בזמן אמת ב-http://localhost:37777
- 💻 **מיומנות Claude Desktop** - חפש זיכרון משיחות Claude Desktop
- 🔒 **בקרת פרטיות** - השתמש בתגיות `<private>` כדי להוציא תוכן רגיש מהאחסון
- ⚙️ **הגדרות הקשר** - בקרה מדויקת על איזה הקשר מוזרק
- 🤖 **פעולה אוטומטית** - אין צורך בהתערבות ידנית
- 🔗 **ציטוטים** - הפנה לתצפיות קודמות עם מזהים (גישה דרך http://localhost:37777/api/observation/{id} או צפה בכולם בצופה האינטרנט ב-http://localhost:37777)
- 🧪 **ערוץ בטא** - נסה תכונות ניסיוניות כמו Endless Mode דרך החלפת גרסאות
---
## תיעוד
📚 **[צפה בתיעוד המלא](docs/)** - עיין במסמכי markdown ב-GitHub
### תחילת העבודה
- **[מדריך התקנה](https://docs.claude-mem.ai/installation)** - התחלה מהירה והתקנה מתקדמת
- **[מדריך שימוש](https://docs.claude-mem.ai/usage/getting-started)** - איך Claude-Mem עובד אוטומטית
- **[כלי חיפוש](https://docs.claude-mem.ai/usage/search-tools)** - שאל את היסטוריית הפרויקט שלך בשפה טבעית
- **[תכונות בטא](https://docs.claude-mem.ai/beta-features)** - נסה תכונות ניסיוניות כמו Endless Mode
### שיטות מומלצות
- **[הנדסת הקשר](https://docs.claude-mem.ai/context-engineering)** - עקרונות אופטימיזציה של הקשר לסוכן AI
- **[גילוי מדורג](https://docs.claude-mem.ai/progressive-disclosure)** - הפילוסופיה מאחורי אסטרטגיית הכנת ההקשר של Claude-Mem
### ארכיטקטורה
- **[סקירה כללית](https://docs.claude-mem.ai/architecture/overview)** - רכיבי המערכת וזרימת הנתונים
- **[התפתחות הארכיטקטורה](https://docs.claude-mem.ai/architecture-evolution)** - המסע מגרסה 3 לגרסה 5
- **[ארכיטקטורת Hooks](https://docs.claude-mem.ai/hooks-architecture)** - איך Claude-Mem משתמש ב-lifecycle hooks
- **[מדריך Hooks](https://docs.claude-mem.ai/architecture/hooks)** - 7 סקריפטי hook מוסברים
- **[שירות Worker](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API וניהול Bun
- **[מסד נתונים](https://docs.claude-mem.ai/architecture/database)** - סכמת SQLite וחיפוש FTS5
- **[ארכיטקטורת חיפוש](https://docs.claude-mem.ai/architecture/search-architecture)** - חיפוש היברידי עם מסד נתוני וקטורים Chroma
### הגדרות ופיתוח
- **[הגדרות](https://docs.claude-mem.ai/configuration)** - משתני סביבה והגדרות
- **[פיתוח](https://docs.claude-mem.ai/development)** - בנייה, בדיקה, תרומה
- **[פתרון בעיות](https://docs.claude-mem.ai/troubleshooting)** - בעיות נפוצות ופתרונות
---
## איך זה עובד
**רכיבי ליבה:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 סקריפטי hook)
2. **התקנה חכמה** - בודק תלויות עם מטמון (סקריפט pre-hook, לא lifecycle hook)
3. **שירות Worker** - HTTP API על פורט 37777 עם ממשק צופה אינטרנט ו-10 נקודות קצה לחיפוש, מנוהל על ידי Bun
4. **מסד נתוני SQLite** - מאחסן הפעלות, תצפיות, סיכומים
5. **מיומנות mem-search** - שאילתות בשפה טבעית עם גילוי מדורג
6. **מסד נתוני וקטורים Chroma** - חיפוש היברידי סמנטי + מילות מפתח לאחזור הקשר חכם
ראה [סקירה כללית של הארכיטקטורה](https://docs.claude-mem.ai/architecture/overview) לפרטים.
---
## מיומנות mem-search
Claude-Mem מספק חיפוש חכם דרך מיומנות mem-search שמופעלת אוטומטית כשאתה שואל על עבודה קודמת:
**איך זה עובד:**
- פשוט שאל באופן טבעי: *"מה עשינו בהפעלה האחרונה?"* או *"תיקנו את הבאג הזה קודם?"*
- Claude מפעיל אוטומטית את מיומנות mem-search כדי למצוא הקשר רלוונטי
**פעולות חיפוש זמינות:**
1. **חיפוש תצפיות** - חיפוש טקסט מלא על פני תצפיות
2. **חיפוש הפעלות** - חיפוש טקסט מלא על פני סיכומי הפעלות
3. **חיפוש Prompts** - חיפוש בקשות משתמש גולמיות
4. **לפי מושג** - חיפוש לפי תגיות מושג (discovery, problem-solution, pattern, וכו')
5. **לפי קובץ** - חיפוש תצפיות המתייחסות לקבצים ספציפיים
6. **לפי סוג** - חיפוש לפי סוג (decision, bugfix, feature, refactor, discovery, change)
7. **הקשר אחרון** - קבל הקשר הפעלות אחרון לפרויקט
8. **ציר זמן** - קבל ציר זמן מאוחד של הקשר סביב נקודת זמן ספציפית
9. **ציר זמן לפי שאילתה** - חפש תצפיות וקבל הקשר ציר זמן סביב ההתאמה הטובה ביותר
10. **עזרה ל-API** - קבל תיעוד API חיפוש
**דוגמאות לשאילתות בשפה טבעית:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
ראה [מדריך כלי חיפוש](https://docs.claude-mem.ai/usage/search-tools) לדוגמאות מפורטות.
---
## תכונות בטא
Claude-Mem מציע **ערוץ בטא** עם תכונות ניסיוניות כמו **Endless Mode** (ארכיטקטורת זיכרון ביומימטית להפעלות מורחבות). החלף בין גרסאות יציבות ובטא מממשק הצופה האינטרנט ב-http://localhost:37777 → Settings.
ראה **[תיעוד תכונות בטא](https://docs.claude-mem.ai/beta-features)** לפרטים על Endless Mode ואיך לנסות אותו.
---
## דרישות מערכת
- **Node.js**: 18.0.0 ומעלה
- **Claude Code**: גרסה אחרונה עם תמיכה בתוספים
- **Bun**: סביבת ריצה ומנהל תהליכים של JavaScript (מותקן אוטומטית אם חסר)
- **uv**: מנהל חבילות Python לחיפוש וקטורי (מותקן אוטומטית אם חסר)
- **SQLite 3**: לאחסון מתמשך (מצורף)
---
## הגדרות
ההגדרות מנוהלות ב-`~/.claude-mem/settings.json` (נוצר אוטומטית עם ברירות מחדל בהפעלה הראשונה). הגדר מודל AI, פורט worker, ספריית נתונים, רמת לוג, והגדרות הזרקת הקשר.
ראה **[מדריך הגדרות](https://docs.claude-mem.ai/configuration)** לכל ההגדרות הזמינות ודוגמאות.
---
## פיתוח
ראה **[מדריך פיתוח](https://docs.claude-mem.ai/development)** להוראות בנייה, בדיקה, ותהליך תרומה.
---
## פתרון בעיות
אם אתה נתקל בבעיות, תאר את הבעיה ל-Claude ומיומנות troubleshoot תאבחן אוטומטית ותספק תיקונים.
ראה **[מדריך פתרון בעיות](https://docs.claude-mem.ai/troubleshooting)** לבעיות נפוצות ופתרונות.
---
## דיווחי באגים
צור דיווחי באגים מקיפים עם המחולל האוטומטי:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## תרומה
תרומות מתקבלות בברכה! אנא:
1. עשה Fork למאגר
2. צור ענף תכונה
3. בצע את השינויים שלך עם בדיקות
4. עדכן תיעוד
5. שלח Pull Request
ראה [מדריך פיתוח](https://docs.claude-mem.ai/development) לתהליך תרומה.
---
## רישיון
פרויקט זה מורשה תחת **GNU Affero General Public License v3.0** (AGPL-3.0).
זכויות יוצרים (C) 2025 Alex Newman (@thedotmack). כל הזכויות שמורות.
ראה את קובץ [LICENSE](LICENSE) לפרטים מלאים.
**משמעות הדבר:**
- אתה יכול לשימוש, שינוי והפצה של תוכנה זו בחופשיות
- אם אתה משנה ופורס על שרת רשת, עליך להנגיש את קוד המקור שלך
- עבודות נגזרות חייבות להיות מורשות גם כן תחת AGPL-3.0
- אין אחריות לתוכנה זו
**הערה על Ragtime**: ספריית `ragtime/` מורשית בנפרד תחת **PolyForm Noncommercial License 1.0.0**. ראה [ragtime/LICENSE](ragtime/LICENSE) לפרטים.
---
## תמיכה
- **תיעוד**: [docs/](docs/)
- **בעיות**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **מאגר**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **מחבר**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**נבנה עם Claude Agent SDK** | **מופעל על ידי Claude Code** | **נוצר עם TypeScript**

304
docs/i18n/README.hi.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 यह एक स्वचालित अनुवाद है। समुदाय से सुधार का स्वागत है!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center"><a href="https://claude.com/claude-code" target="_blank">Claude Code</a> के लिए बनाई गई स्थायी मेमोरी संपीड़न प्रणाली।</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#quick-start">त्वरित शुरुआत</a> •
<a href="#how-it-works">यह कैसे काम करता है</a> •
<a href="#mcp-search-tools">खोज उपकरण</a> •
<a href="#documentation">दस्तावेज़ीकरण</a> •
<a href="#configuration">कॉन्फ़िगरेशन</a> •
<a href="#troubleshooting">समस्या निवारण</a> •
<a href="#license">लाइसेंस</a>
</p>
<p align="center">
Claude-Mem स्वचालित रूप से टूल उपयोग अवलोकनों को कैप्चर करके, सिमेंटिक सारांश उत्पन्न करके, और उन्हें भविष्य के सत्रों के लिए उपलब्ध कराकर सत्रों में संदर्भ को निर्बाध रूप से संरक्षित करता है। यह Claude को परियोजनाओं के बारे में ज्ञान की निरंतरता बनाए रखने में सक्षम बनाता है, भले ही सत्र समाप्त हो जाएं या पुनः कनेक्ट हो जाएं।
</p>
---
## त्वरित शुरुआत
टर्मिनल में एक नया Claude Code सत्र शुरू करें और निम्नलिखित कमांड दर्ज करें:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Claude Code को पुनः आरंभ करें। पिछले सत्रों का संदर्भ स्वचालित रूप से नए सत्रों में दिखाई देगा।
**मुख्य विशेषताएं:**
- 🧠 **स्थायी मेमोरी** - संदर्भ सत्रों में बना रहता है
- 📊 **प्रगतिशील प्रकटीकरण** - टोकन लागत दृश्यता के साथ स्तरित मेमोरी पुनर्प्राप्ति
- 🔍 **स्किल-आधारित खोज** - mem-search स्किल के साथ अपने प्रोजेक्ट इतिहास को क्वेरी करें
- 🖥️ **वेब व्यूअर UI** - http://localhost:37777 पर रीयल-टाइम मेमोरी स्ट्रीम
- 💻 **Claude Desktop स्किल** - Claude Desktop वार्तालापों से मेमोरी खोजें
- 🔒 **गोपनीयता नियंत्रण** - संवेदनशील सामग्री को स्टोरेज से बाहर रखने के लिए `<private>` टैग का उपयोग करें
- ⚙️ **संदर्भ कॉन्फ़िगरेशन** - किस संदर्भ को इंजेक्ट किया जाता है, इस पर सूक्ष्म नियंत्रण
- 🤖 **स्वचालित संचालन** - मैन्युअल हस्तक्षेप की आवश्यकता नहीं
- 🔗 **उद्धरण** - IDs के साथ पिछले अवलोकनों का संदर्भ दें (http://localhost:37777/api/observation/{id} के माध्यम से एक्सेस करें या http://localhost:37777 पर वेब व्यूअर में सभी देखें)
- 🧪 **बीटा चैनल** - संस्करण स्विचिंग के माध्यम से Endless Mode जैसी प्रायोगिक सुविधाओं को आज़माएं
---
## दस्तावेज़ीकरण
📚 **[पूर्ण दस्तावेज़ीकरण देखें](docs/)** - GitHub पर markdown दस्तावेज़ ब्राउज़ करें
### शुरुआत करना
- **[इंस्टॉलेशन गाइड](https://docs.claude-mem.ai/installation)** - त्वरित शुरुआत और उन्नत इंस्टॉलेशन
- **[उपयोग गाइड](https://docs.claude-mem.ai/usage/getting-started)** - Claude-Mem स्वचालित रूप से कैसे काम करता है
- **[खोज उपकरण](https://docs.claude-mem.ai/usage/search-tools)** - प्राकृतिक भाषा के साथ अपने प्रोजेक्ट इतिहास को क्वेरी करें
- **[बीटा सुविधाएं](https://docs.claude-mem.ai/beta-features)** - Endless Mode जैसी प्रायोगिक सुविधाओं को आज़माएं
### सर्वोत्तम अभ्यास
- **[संदर्भ इंजीनियरिंग](https://docs.claude-mem.ai/context-engineering)** - AI एजेंट संदर्भ अनुकूलन सिद्धांत
- **[प्रगतिशील प्रकटीकरण](https://docs.claude-mem.ai/progressive-disclosure)** - Claude-Mem की संदर्भ प्राइमिंग रणनीति के पीछे का दर्शन
### आर्किटेक्चर
- **[अवलोकन](https://docs.claude-mem.ai/architecture/overview)** - सिस्टम घटक और डेटा प्रवाह
- **[आर्किटेक्चर विकास](https://docs.claude-mem.ai/architecture-evolution)** - v3 से v5 तक की यात्रा
- **[Hooks आर्किटेक्चर](https://docs.claude-mem.ai/hooks-architecture)** - Claude-Mem जीवनचक्र hooks का उपयोग कैसे करता है
- **[Hooks संदर्भ](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook स्क्रिप्ट समझाई गई
- **[Worker सेवा](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API और Bun प्रबंधन
- **[डेटाबेस](https://docs.claude-mem.ai/architecture/database)** - SQLite स्कीमा और FTS5 खोज
- **[खोज आर्किटेक्चर](https://docs.claude-mem.ai/architecture/search-architecture)** - Chroma वेक्टर डेटाबेस के साथ हाइब्रिड खोज
### कॉन्फ़िगरेशन और विकास
- **[कॉन्फ़िगरेशन](https://docs.claude-mem.ai/configuration)** - पर्यावरण चर और सेटिंग्स
- **[विकास](https://docs.claude-mem.ai/development)** - बिल्डिंग, परीक्षण, योगदान
- **[समस्या निवारण](https://docs.claude-mem.ai/troubleshooting)** - सामान्य समस्याएं और समाधान
---
## यह कैसे काम करता है
**मुख्य घटक:**
1. **5 जीवनचक्र Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook स्क्रिप्ट)
2. **स्मार्ट इंस्टॉल** - कैश्ड डिपेंडेंसी चेकर (pre-hook स्क्रिप्ट, जीवनचक्र hook नहीं)
3. **Worker सेवा** - वेब व्यूअर UI और 10 खोज endpoints के साथ पोर्ट 37777 पर HTTP API, Bun द्वारा प्रबंधित
4. **SQLite डेटाबेस** - सत्र, अवलोकन, सारांश संग्रहीत करता है
5. **mem-search स्किल** - प्रगतिशील प्रकटीकरण के साथ प्राकृतिक भाषा क्वेरी
6. **Chroma वेक्टर डेटाबेस** - बुद्धिमान संदर्भ पुनर्प्राप्ति के लिए हाइब्रिड सिमेंटिक + कीवर्ड खोज
विवरण के लिए [आर्किटेक्चर अवलोकन](https://docs.claude-mem.ai/architecture/overview) देखें।
---
## mem-search स्किल
Claude-Mem mem-search स्किल के माध्यम से बुद्धिमान खोज प्रदान करता है जो स्वचालित रूप से सक्रिय हो जाती है जब आप पिछले काम के बारे में पूछते हैं:
**यह कैसे काम करता है:**
- बस स्वाभाविक रूप से पूछें: *"हमने पिछले सत्र में क्या किया?"* या *"क्या हमने पहले इस बग को ठीक किया था?"*
- Claude स्वचालित रूप से प्रासंगिक संदर्भ खोजने के लिए mem-search स्किल को सक्रिय करता है
**उपलब्ध खोज संचालन:**
1. **अवलोकन खोजें** - अवलोकनों में पूर्ण-पाठ खोज
2. **सत्र खोजें** - सत्र सारांशों में पूर्ण-पाठ खोज
3. **प्रॉम्प्ट खोजें** - कच्चे उपयोगकर्ता अनुरोध खोजें
4. **अवधारणा द्वारा** - अवधारणा टैग द्वारा खोजें (discovery, problem-solution, pattern, आदि)
5. **फ़ाइल द्वारा** - विशिष्ट फ़ाइलों का संदर्भ देने वाले अवलोकन खोजें
6. **प्रकार द्वारा** - प्रकार द्वारा खोजें (decision, bugfix, feature, refactor, discovery, change)
7. **हालिया संदर्भ** - एक प्रोजेक्ट के लिए हालिया सत्र संदर्भ प्राप्त करें
8. **टाइमलाइन** - समय में एक विशिष्ट बिंदु के आसपास संदर्भ की एकीकृत टाइमलाइन प्राप्त करें
9. **क्वेरी द्वारा टाइमलाइन** - अवलोकनों को खोजें और सर्वश्रेष्ठ मिलान के आसपास टाइमलाइन संदर्भ प्राप्त करें
10. **API सहायता** - खोज API दस्तावेज़ीकरण प्राप्त करें
**प्राकृतिक भाषा क्वेरी के उदाहरण:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
विस्तृत उदाहरणों के लिए [खोज उपकरण गाइड](https://docs.claude-mem.ai/usage/search-tools) देखें।
---
## बीटा सुविधाएं
Claude-Mem **बीटा चैनल** के साथ **Endless Mode** (विस्तारित सत्रों के लिए बायोमिमेटिक मेमोरी आर्किटेक्चर) जैसी प्रायोगिक सुविधाएं प्रदान करता है। http://localhost:37777 → Settings पर वेब व्यूअर UI से स्थिर और बीटा संस्करणों के बीच स्विच करें।
Endless Mode के विवरण और इसे आज़माने के तरीके के लिए **[बीटा सुविधाएं दस्तावेज़ीकरण](https://docs.claude-mem.ai/beta-features)** देखें।
---
## सिस्टम आवश्यकताएं
- **Node.js**: 18.0.0 या उच्चतर
- **Claude Code**: प्लगइन समर्थन के साथ नवीनतम संस्करण
- **Bun**: JavaScript रनटाइम और प्रोसेस मैनेजर (यदि गायब हो तो ऑटो-इंस्टॉल)
- **uv**: वेक्टर खोज के लिए Python पैकेज मैनेजर (यदि गायब हो तो ऑटो-इंस्टॉल)
- **SQLite 3**: स्थायी स्टोरेज के लिए (बंडल किया गया)
---
## कॉन्फ़िगरेशन
सेटिंग्स `~/.claude-mem/settings.json` में प्रबंधित की जाती हैं (पहली बार चलने पर डिफ़ॉल्ट के साथ ऑटो-निर्मित)। AI मॉडल, worker पोर्ट, डेटा डायरेक्टरी, लॉग स्तर, और संदर्भ इंजेक्शन सेटिंग्स कॉन्फ़िगर करें।
सभी उपलब्ध सेटिंग्स और उदाहरणों के लिए **[कॉन्फ़िगरेशन गाइड](https://docs.claude-mem.ai/configuration)** देखें।
---
## विकास
बिल्ड निर्देश, परीक्षण, और योगदान वर्कफ़्लो के लिए **[विकास गाइड](https://docs.claude-mem.ai/development)** देखें।
---
## समस्या निवारण
यदि समस्याओं का सामना कर रहे हैं, तो Claude को समस्या का वर्णन करें और troubleshoot स्किल स्वचालित रूप से निदान करेगी और सुधार प्रदान करेगी।
सामान्य समस्याओं और समाधानों के लिए **[समस्या निवारण गाइड](https://docs.claude-mem.ai/troubleshooting)** देखें।
---
## बग रिपोर्ट
स्वचालित जेनरेटर के साथ व्यापक बग रिपोर्ट बनाएं:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## योगदान
योगदान का स्वागत है! कृपया:
1. रिपॉजिटरी को Fork करें
2. एक feature ब्रांच बनाएं
3. परीक्षणों के साथ अपने परिवर्तन करें
4. दस्तावेज़ीकरण अपडेट करें
5. एक Pull Request सबमिट करें
योगदान वर्कफ़्लो के लिए [विकास गाइड](https://docs.claude-mem.ai/development) देखें।
---
## लाइसेंस
यह प्रोजेक्ट **GNU Affero General Public License v3.0** (AGPL-3.0) के तहत लाइसेंस प्राप्त है।
Copyright (C) 2025 Alex Newman (@thedotmack)। सर्वाधिकार सुरक्षित।
पूर्ण विवरण के लिए [LICENSE](LICENSE) फ़ाइल देखें।
**इसका क्या अर्थ है:**
- आप इस सॉफ़्टवेयर को स्वतंत्र रूप से उपयोग, संशोधित और वितरित कर सकते हैं
- यदि आप नेटवर्क सर्वर पर संशोधित और तैनात करते हैं, तो आपको अपना स्रोत कोड उपलब्ध कराना होगा
- व्युत्पन्न कार्यों को भी AGPL-3.0 के तहत लाइसेंस प्राप्त होना चाहिए
- इस सॉफ़्टवेयर के लिए कोई वारंटी नहीं है
**Ragtime पर नोट**: `ragtime/` डायरेक्टरी को **PolyForm Noncommercial License 1.0.0** के तहत अलग से लाइसेंस प्राप्त है। विवरण के लिए [ragtime/LICENSE](ragtime/LICENSE) देखें।
---
## समर्थन
- **दस्तावेज़ीकरण**: [docs/](docs/)
- **समस्याएं**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **रिपॉजिटरी**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **लेखक**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Claude Agent SDK के साथ निर्मित** | **Claude Code द्वारा संचालित** | **TypeScript के साथ बनाया गया**
---

302
docs/i18n/README.hu.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Ez egy automatikus fordítás. Közösségi javítások szívesen fogadottak!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Tartós memória tömörítési rendszer a <a href="https://claude.com/claude-code" target="_blank">Claude Code</a> számára.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#gyors-kezdés">Gyors kezdés</a> •
<a href="#hogyan-működik">Hogyan működik</a> •
<a href="#keresési-eszközök">Keresési eszközök</a> •
<a href="#dokumentáció">Dokumentáció</a> •
<a href="#konfiguráció">Konfiguráció</a> •
<a href="#hibaelhárítás">Hibaelhárítás</a> •
<a href="#licenc">Licenc</a>
</p>
<p align="center">
A Claude-Mem zökkenőmentesen megőrzi a kontextust munkamenetek között azáltal, hogy automatikusan rögzíti az eszközhasználati megfigyeléseket, szemantikus összefoglalókat generál, és elérhetővé teszi azokat a jövőbeli munkamenetekben. Ez lehetővé teszi Claude számára, hogy fenntartsa a projektekkel kapcsolatos tudás folytonosságát még a munkamenetek befejezése vagy újracsatlakozása után is.
</p>
---
## Gyors kezdés
Indítson el egy új Claude Code munkamenetet a terminálban, és írja be a következő parancsokat:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Indítsa újra a Claude Code-ot. A korábbi munkamenetek kontextusa automatikusan megjelenik az új munkamenetekben.
**Főbb jellemzők:**
- 🧠 **Tartós memória** - A kontextus túléli a munkameneteket
- 📊 **Progresszív felfedés** - Többrétegű memória-visszakeresés token költség láthatósággal
- 🔍 **Skill-alapú keresés** - Lekérdezheti projekt előzményeit a mem-search skill segítségével
- 🖥️ **Webes megjelenítő felület** - Valós idejű memória stream a http://localhost:37777 címen
- 💻 **Claude Desktop Skill** - Memória keresése Claude Desktop beszélgetésekből
- 🔒 **Adatvédelmi kontroll** - Használja a `<private>` címkéket az érzékeny tartalom kizárásához
- ⚙️ **Kontextus konfiguráció** - Finomhangolt kontroll afelett, hogy milyen kontextus kerül beillesztésre
- 🤖 **Automatikus működés** - Nincs szükség manuális beavatkozásra
- 🔗 **Hivatkozások** - Hivatkozás múltbeli megfigyelésekre ID-kkal (hozzáférés: http://localhost:37777/api/observation/{id} vagy mindegyik megtekintése a webes felületen a http://localhost:37777 címen)
- 🧪 **Béta csatorna** - Kísérleti funkciók, mint az Endless Mode kipróbálása verziócserével
---
## Dokumentáció
📚 **[Teljes dokumentáció megtekintése](docs/)** - Markdown dokumentumok böngészése GitHub-on
### Első lépések
- **[Telepítési útmutató](https://docs.claude-mem.ai/installation)** - Gyors indítás és haladó telepítés
- **[Használati útmutató](https://docs.claude-mem.ai/usage/getting-started)** - Hogyan működik automatikusan a Claude-Mem
- **[Keresési eszközök](https://docs.claude-mem.ai/usage/search-tools)** - Projekt előzmények lekérdezése természetes nyelvvel
- **[Béta funkciók](https://docs.claude-mem.ai/beta-features)** - Kísérleti funkciók, mint az Endless Mode kipróbálása
### Bevált gyakorlatok
- **[Kontextus tervezés](https://docs.claude-mem.ai/context-engineering)** - AI ügynök kontextus optimalizálási elvek
- **[Progresszív felfedés](https://docs.claude-mem.ai/progressive-disclosure)** - A Claude-Mem kontextus előkészítési stratégiájának filozófiája
### Architektúra
- **[Áttekintés](https://docs.claude-mem.ai/architecture/overview)** - Rendszerkomponensek és adatfolyam
- **[Architektúra fejlődés](https://docs.claude-mem.ai/architecture-evolution)** - Az út a v3-tól a v5-ig
- **[Hooks architektúra](https://docs.claude-mem.ai/hooks-architecture)** - Hogyan használja a Claude-Mem az életciklus hookokat
- **[Hooks referencia](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook szkript magyarázata
- **[Worker szolgáltatás](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API és Bun kezelés
- **[Adatbázis](https://docs.claude-mem.ai/architecture/database)** - SQLite séma és FTS5 keresés
- **[Keresési architektúra](https://docs.claude-mem.ai/architecture/search-architecture)** - Hibrid keresés Chroma vektor adatbázissal
### Konfiguráció és fejlesztés
- **[Konfiguráció](https://docs.claude-mem.ai/configuration)** - Környezeti változók és beállítások
- **[Fejlesztés](https://docs.claude-mem.ai/development)** - Építés, tesztelés, hozzájárulás
- **[Hibaelhárítás](https://docs.claude-mem.ai/troubleshooting)** - Gyakori problémák és megoldások
---
## Hogyan működik
**Fő komponensek:**
1. **5 életciklus hook** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook szkript)
2. **Intelligens telepítés** - Gyorsítótárazott függőség ellenőrző (pre-hook szkript, nem életciklus hook)
3. **Worker szolgáltatás** - HTTP API a 37777-es porton webes megjelenítő felülettel és 10 keresési végponttal, Bun által kezelve
4. **SQLite adatbázis** - Munkamenetek, megfigyelések, összefoglalók tárolása
5. **mem-search Skill** - Természetes nyelvi lekérdezések progresszív felfedéssel
6. **Chroma vektor adatbázis** - Hibrid szemantikus + kulcsszó keresés intelligens kontextus visszakereséshez
További részletekért lásd az [Architektúra áttekintést](https://docs.claude-mem.ai/architecture/overview).
---
## mem-search Skill
A Claude-Mem intelligens keresést biztosít a mem-search skillen keresztül, amely automatikusan aktiválódik, amikor múltbeli munkáról kérdez:
**Hogyan működik:**
- Csak kérdezzen természetesen: *"Mit csináltunk az előző munkamenetben?"* vagy *"Javítottuk már ezt a hibát korábban?"*
- Claude automatikusan meghívja a mem-search skillet a releváns kontextus megtalálásához
**Elérhető keresési műveletek:**
1. **Megfigyelések keresése** - Teljes szöveges keresés a megfigyelésekben
2. **Munkamenetek keresése** - Teljes szöveges keresés munkamenet összefoglalókban
3. **Promptok keresése** - Nyers felhasználói kérések keresése
4. **Koncepció szerint** - Keresés koncepció címkék alapján (discovery, problem-solution, pattern, stb.)
5. **Fájl szerint** - Adott fájlokra hivatkozó megfigyelések keresése
6. **Típus szerint** - Keresés típus alapján (decision, bugfix, feature, refactor, discovery, change)
7. **Legutóbbi kontextus** - Legutóbbi munkamenet kontextus lekérése egy projekthez
8. **Idővonal** - Egységes idővonal kontextus lekérése egy adott időpont körül
9. **Idővonal lekérdezéssel** - Megfigyelések keresése és idővonal kontextus lekérése a legjobb találat körül
10. **API segítség** - Keresési API dokumentáció lekérése
**Példa természetes nyelvi lekérdezésekre:**
```
"Milyen hibákat javítottunk az előző munkamenetben?"
"Hogyan implementáltuk az autentikációt?"
"Milyen változtatások történtek a worker-service.ts fájlban?"
"Mutasd a legutóbbi munkát ezen a projekten"
"Mi történt, amikor hozzáadtuk a megjelenítő felületet?"
```
Részletes példákért lásd a [Keresési eszközök útmutatót](https://docs.claude-mem.ai/usage/search-tools).
---
## Béta funkciók
A Claude-Mem **béta csatornát** kínál kísérleti funkciókkal, mint az **Endless Mode** (biomimetikus memória architektúra hosszabb munkamenetekhez). Váltson a stabil és béta verziók között a webes megjelenítő felületről a http://localhost:37777 → Settings címen.
További részletekért az Endless Mode-ról és annak kipróbálásáról lásd a **[Béta funkciók dokumentációt](https://docs.claude-mem.ai/beta-features)**.
---
## Rendszerkövetelmények
- **Node.js**: 18.0.0 vagy újabb
- **Claude Code**: Legújabb verzió plugin támogatással
- **Bun**: JavaScript futtatókörnyezet és folyamatkezelő (automatikusan települ, ha hiányzik)
- **uv**: Python csomagkezelő vektor kereséshez (automatikusan települ, ha hiányzik)
- **SQLite 3**: Tartós tároláshoz (mellékelve)
---
## Konfiguráció
A beállítások a `~/.claude-mem/settings.json` fájlban kezelhetők (automatikusan létrejön alapértelmezett értékekkel az első futtatáskor). Konfigurálható az AI modell, worker port, adatkönyvtár, naplózási szint és kontextus beillesztési beállítások.
Az összes elérhető beállításért és példákért lásd a **[Konfigurációs útmutatót](https://docs.claude-mem.ai/configuration)**.
---
## Fejlesztés
Az építési utasításokért, tesztelésért és hozzájárulási munkafolyamatért lásd a **[Fejlesztési útmutatót](https://docs.claude-mem.ai/development)**.
---
## Hibaelhárítás
Problémák esetén írja le a problémát Claude-nak, és a troubleshoot skill automatikusan diagnosztizálja és javítási megoldásokat kínál.
Gyakori problémákért és megoldásokért lásd a **[Hibaelhárítási útmutatót](https://docs.claude-mem.ai/troubleshooting)**.
---
## Hibajelentések
Átfogó hibajelentések készítése az automatikus generátorral:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Hozzájárulás
A hozzájárulásokat szívesen fogadjuk! Kérjük:
1. Fork-olja a tárolót
2. Hozzon létre egy feature branchet
3. Végezze el változtatásait tesztekkel
4. Frissítse a dokumentációt
5. Nyújtson be egy Pull Requestet
A hozzájárulási munkafolyamatért lásd a [Fejlesztési útmutatót](https://docs.claude-mem.ai/development).
---
## Licenc
Ez a projekt a **GNU Affero General Public License v3.0** (AGPL-3.0) alatt licencelt.
Copyright (C) 2025 Alex Newman (@thedotmack). Minden jog fenntartva.
A teljes részletekért lásd a [LICENSE](LICENSE) fájlt.
**Mit jelent ez:**
- Szabadon használhatja, módosíthatja és terjesztheti ezt a szoftvert
- Ha módosítja és hálózati szerveren telepíti, elérhetővé kell tennie a forráskódot
- A származékos munkáknak szintén AGPL-3.0 alatt kell licencelve lenniük
- Ehhez a szoftverhez NINCS GARANCIA
**Megjegyzés a Ragtime-ról**: A `ragtime/` könyvtár külön licencelt a **PolyForm Noncommercial License 1.0.0** alatt. Részletekért lásd a [ragtime/LICENSE](ragtime/LICENSE) fájlt.
---
## Támogatás
- **Dokumentáció**: [docs/](docs/)
- **Hibák**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Tároló**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Szerző**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Claude Agent SDK-val építve** | **Claude Code által hajtva** | **TypeScript-tel készítve**

304
docs/i18n/README.id.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 Ini adalah terjemahan otomatis. Koreksi dari komunitas sangat dipersilakan!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Sistem kompresi memori persisten yang dibangun untuk <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#mulai-cepat">Mulai Cepat</a> •
<a href="#cara-kerja">Cara Kerja</a> •
<a href="#alat-pencarian-mcp">Alat Pencarian</a> •
<a href="#dokumentasi">Dokumentasi</a> •
<a href="#konfigurasi">Konfigurasi</a> •
<a href="#pemecahan-masalah">Pemecahan Masalah</a> •
<a href="#lisensi">Lisensi</a>
</p>
<p align="center">
Claude-Mem secara mulus mempertahankan konteks di seluruh sesi dengan secara otomatis menangkap observasi penggunaan alat, menghasilkan ringkasan semantik, dan membuatnya tersedia untuk sesi mendatang. Ini memungkinkan Claude untuk mempertahankan kontinuitas pengetahuan tentang proyek bahkan setelah sesi berakhir atau tersambung kembali.
</p>
---
## Mulai Cepat
Mulai sesi Claude Code baru di terminal dan masukkan perintah berikut:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Restart Claude Code. Konteks dari sesi sebelumnya akan secara otomatis muncul di sesi baru.
**Fitur Utama:**
- 🧠 **Memori Persisten** - Konteks bertahan di seluruh sesi
- 📊 **Progressive Disclosure** - Pengambilan memori berlapis dengan visibilitas biaya token
- 🔍 **Pencarian Berbasis Skill** - Query riwayat proyek Anda dengan mem-search skill
- 🖥️ **Web Viewer UI** - Stream memori real-time di http://localhost:37777
- 💻 **Claude Desktop Skill** - Cari memori dari percakapan Claude Desktop
- 🔒 **Kontrol Privasi** - Gunakan tag `<private>` untuk mengecualikan konten sensitif dari penyimpanan
- ⚙️ **Konfigurasi Konteks** - Kontrol yang detail atas konteks apa yang diinjeksikan
- 🤖 **Operasi Otomatis** - Tidak memerlukan intervensi manual
- 🔗 **Kutipan** - Referensi observasi masa lalu dengan ID (akses melalui http://localhost:37777/api/observation/{id} atau lihat semua di web viewer di http://localhost:37777)
- 🧪 **Beta Channel** - Coba fitur eksperimental seperti Endless Mode melalui peralihan versi
---
## Dokumentasi
📚 **[Lihat Dokumentasi Lengkap](docs/)** - Telusuri dokumen markdown di GitHub
### Memulai
- **[Panduan Instalasi](https://docs.claude-mem.ai/installation)** - Mulai cepat & instalasi lanjutan
- **[Panduan Penggunaan](https://docs.claude-mem.ai/usage/getting-started)** - Bagaimana Claude-Mem bekerja secara otomatis
- **[Alat Pencarian](https://docs.claude-mem.ai/usage/search-tools)** - Query riwayat proyek Anda dengan bahasa alami
- **[Fitur Beta](https://docs.claude-mem.ai/beta-features)** - Coba fitur eksperimental seperti Endless Mode
### Praktik Terbaik
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - Prinsip optimisasi konteks agen AI
- **[Progressive Disclosure](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofi di balik strategi priming konteks Claude-Mem
### Arsitektur
- **[Ringkasan](https://docs.claude-mem.ai/architecture/overview)** - Komponen sistem & aliran data
- **[Evolusi Arsitektur](https://docs.claude-mem.ai/architecture-evolution)** - Perjalanan dari v3 ke v5
- **[Arsitektur Hooks](https://docs.claude-mem.ai/hooks-architecture)** - Bagaimana Claude-Mem menggunakan lifecycle hooks
- **[Referensi Hooks](https://docs.claude-mem.ai/architecture/hooks)** - 7 skrip hook dijelaskan
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API & manajemen Bun
- **[Database](https://docs.claude-mem.ai/architecture/database)** - Skema SQLite & pencarian FTS5
- **[Arsitektur Pencarian](https://docs.claude-mem.ai/architecture/search-architecture)** - Pencarian hybrid dengan database vektor Chroma
### Konfigurasi & Pengembangan
- **[Konfigurasi](https://docs.claude-mem.ai/configuration)** - Variabel environment & pengaturan
- **[Pengembangan](https://docs.claude-mem.ai/development)** - Membangun, testing, kontribusi
- **[Pemecahan Masalah](https://docs.claude-mem.ai/troubleshooting)** - Masalah umum & solusi
---
## Cara Kerja
**Komponen Inti:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 skrip hook)
2. **Smart Install** - Pemeriksa dependensi yang di-cache (skrip pre-hook, bukan lifecycle hook)
3. **Worker Service** - HTTP API di port 37777 dengan web viewer UI dan 10 endpoint pencarian, dikelola oleh Bun
4. **SQLite Database** - Menyimpan sesi, observasi, ringkasan
5. **mem-search Skill** - Query bahasa alami dengan progressive disclosure
6. **Chroma Vector Database** - Pencarian hybrid semantik + keyword untuk pengambilan konteks yang cerdas
Lihat [Ringkasan Arsitektur](https://docs.claude-mem.ai/architecture/overview) untuk detail.
---
## mem-search Skill
Claude-Mem menyediakan pencarian cerdas melalui mem-search skill yang secara otomatis dipanggil saat Anda bertanya tentang pekerjaan masa lalu:
**Cara Kerja:**
- Tanya saja secara alami: *"Apa yang kita lakukan sesi terakhir?"* atau *"Apakah kita sudah memperbaiki bug ini sebelumnya?"*
- Claude secara otomatis memanggil mem-search skill untuk menemukan konteks yang relevan
**Operasi Pencarian yang Tersedia:**
1. **Search Observations** - Pencarian teks lengkap di seluruh observasi
2. **Search Sessions** - Pencarian teks lengkap di seluruh ringkasan sesi
3. **Search Prompts** - Cari permintaan pengguna mentah
4. **By Concept** - Temukan berdasarkan tag konsep (discovery, problem-solution, pattern, dll.)
5. **By File** - Temukan observasi yang mereferensikan file tertentu
6. **By Type** - Temukan berdasarkan tipe (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Dapatkan konteks sesi terbaru untuk sebuah proyek
8. **Timeline** - Dapatkan timeline terpadu dari konteks di sekitar titik waktu tertentu
9. **Timeline by Query** - Cari observasi dan dapatkan konteks timeline di sekitar kecocokan terbaik
10. **API Help** - Dapatkan dokumentasi API pencarian
**Contoh Query Bahasa Alami:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Lihat [Panduan Alat Pencarian](https://docs.claude-mem.ai/usage/search-tools) untuk contoh detail.
---
## Fitur Beta
Claude-Mem menawarkan **beta channel** dengan fitur eksperimental seperti **Endless Mode** (arsitektur memori biomimetik untuk sesi yang diperpanjang). Beralih antara versi stabil dan beta dari web viewer UI di http://localhost:37777 → Settings.
Lihat **[Dokumentasi Fitur Beta](https://docs.claude-mem.ai/beta-features)** untuk detail tentang Endless Mode dan cara mencobanya.
---
## Persyaratan Sistem
- **Node.js**: 18.0.0 atau lebih tinggi
- **Claude Code**: Versi terbaru dengan dukungan plugin
- **Bun**: JavaScript runtime dan process manager (otomatis diinstal jika tidak ada)
- **uv**: Python package manager untuk pencarian vektor (otomatis diinstal jika tidak ada)
- **SQLite 3**: Untuk penyimpanan persisten (terbundel)
---
## Konfigurasi
Pengaturan dikelola di `~/.claude-mem/settings.json` (otomatis dibuat dengan default saat pertama kali dijalankan). Konfigurasi model AI, port worker, direktori data, level log, dan pengaturan injeksi konteks.
Lihat **[Panduan Konfigurasi](https://docs.claude-mem.ai/configuration)** untuk semua pengaturan dan contoh yang tersedia.
---
## Pengembangan
Lihat **[Panduan Pengembangan](https://docs.claude-mem.ai/development)** untuk instruksi build, testing, dan alur kerja kontribusi.
---
## Pemecahan Masalah
Jika mengalami masalah, jelaskan masalah ke Claude dan troubleshoot skill akan secara otomatis mendiagnosis dan memberikan perbaikan.
Lihat **[Panduan Pemecahan Masalah](https://docs.claude-mem.ai/troubleshooting)** untuk masalah umum dan solusi.
---
## Laporan Bug
Buat laporan bug yang komprehensif dengan generator otomatis:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Kontribusi
Kontribusi sangat dipersilakan! Silakan:
1. Fork repositori
2. Buat branch fitur
3. Buat perubahan Anda dengan tes
4. Perbarui dokumentasi
5. Kirim Pull Request
Lihat [Panduan Pengembangan](https://docs.claude-mem.ai/development) untuk alur kerja kontribusi.
---
## Lisensi
Proyek ini dilisensikan di bawah **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). All rights reserved.
Lihat file [LICENSE](LICENSE) untuk detail lengkap.
**Apa Artinya:**
- Anda dapat menggunakan, memodifikasi, dan mendistribusikan perangkat lunak ini dengan bebas
- Jika Anda memodifikasi dan men-deploy di server jaringan, Anda harus membuat kode sumber Anda tersedia
- Karya turunan juga harus dilisensikan di bawah AGPL-3.0
- TIDAK ADA JAMINAN untuk perangkat lunak ini
**Catatan tentang Ragtime**: Direktori `ragtime/` dilisensikan secara terpisah di bawah **PolyForm Noncommercial License 1.0.0**. Lihat [ragtime/LICENSE](ragtime/LICENSE) untuk detail.
---
## Dukungan
- **Dokumentasi**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repositori**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Penulis**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Built with Claude Agent SDK** | **Powered by Claude Code** | **Made with TypeScript**
---

304
docs/i18n/README.it.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 Questa è una traduzione automatica. Le correzioni della comunità sono benvenute!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Sistema di compressione della memoria persistente creato per <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#avvio-rapido">Avvio Rapido</a> •
<a href="#come-funziona">Come Funziona</a> •
<a href="#strumenti-di-ricerca">Strumenti di Ricerca</a> •
<a href="#documentazione">Documentazione</a> •
<a href="#configurazione">Configurazione</a> •
<a href="#risoluzione-dei-problemi">Risoluzione dei Problemi</a> •
<a href="#licenza">Licenza</a>
</p>
<p align="center">
Claude-Mem preserva il contesto in modo fluido tra le sessioni catturando automaticamente le osservazioni sull'utilizzo degli strumenti, generando riepiloghi semantici e rendendoli disponibili per le sessioni future. Questo consente a Claude di mantenere la continuità della conoscenza sui progetti anche dopo la fine o la riconnessione delle sessioni.
</p>
---
## Avvio Rapido
Avvia una nuova sessione di Claude Code nel terminale e inserisci i seguenti comandi:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Riavvia Claude Code. Il contesto delle sessioni precedenti apparirà automaticamente nelle nuove sessioni.
**Caratteristiche Principali:**
- 🧠 **Memoria Persistente** - Il contesto sopravvive tra le sessioni
- 📊 **Divulgazione Progressiva** - Recupero della memoria a strati con visibilità del costo in token
- 🔍 **Ricerca Basata su Skill** - Interroga la cronologia del tuo progetto con la skill mem-search
- 🖥️ **Interfaccia Web Viewer** - Stream della memoria in tempo reale su http://localhost:37777
- 💻 **Skill per Claude Desktop** - Cerca nella memoria dalle conversazioni di Claude Desktop
- 🔒 **Controllo della Privacy** - Usa i tag `<private>` per escludere contenuti sensibili dall'archiviazione
- ⚙️ **Configurazione del Contesto** - Controllo granulare su quale contesto viene iniettato
- 🤖 **Funzionamento Automatico** - Nessun intervento manuale richiesto
- 🔗 **Citazioni** - Fai riferimento a osservazioni passate con ID (accedi tramite http://localhost:37777/api/observation/{id} o visualizza tutto nel web viewer su http://localhost:37777)
- 🧪 **Canale Beta** - Prova funzionalità sperimentali come Endless Mode tramite il cambio di versione
---
## Documentazione
📚 **[Visualizza Documentazione Completa](docs/)** - Sfoglia i documenti markdown su GitHub
### Per Iniziare
- **[Guida all'Installazione](https://docs.claude-mem.ai/installation)** - Avvio rapido e installazione avanzata
- **[Guida all'Uso](https://docs.claude-mem.ai/usage/getting-started)** - Come funziona automaticamente Claude-Mem
- **[Strumenti di Ricerca](https://docs.claude-mem.ai/usage/search-tools)** - Interroga la cronologia del progetto con linguaggio naturale
- **[Funzionalità Beta](https://docs.claude-mem.ai/beta-features)** - Prova funzionalità sperimentali come Endless Mode
### Best Practice
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - Principi di ottimizzazione del contesto per agenti AI
- **[Progressive Disclosure](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofia alla base della strategia di priming del contesto di Claude-Mem
### Architettura
- **[Panoramica](https://docs.claude-mem.ai/architecture/overview)** - Componenti del sistema e flusso dei dati
- **[Evoluzione dell'Architettura](https://docs.claude-mem.ai/architecture-evolution)** - Il percorso dalla v3 alla v5
- **[Architettura degli Hook](https://docs.claude-mem.ai/hooks-architecture)** - Come Claude-Mem utilizza gli hook del ciclo di vita
- **[Riferimento Hook](https://docs.claude-mem.ai/architecture/hooks)** - Spiegazione dei 7 script hook
- **[Servizio Worker](https://docs.claude-mem.ai/architecture/worker-service)** - API HTTP e gestione Bun
- **[Database](https://docs.claude-mem.ai/architecture/database)** - Schema SQLite e ricerca FTS5
- **[Architettura di Ricerca](https://docs.claude-mem.ai/architecture/search-architecture)** - Ricerca ibrida con database vettoriale Chroma
### Configurazione e Sviluppo
- **[Configurazione](https://docs.claude-mem.ai/configuration)** - Variabili d'ambiente e impostazioni
- **[Sviluppo](https://docs.claude-mem.ai/development)** - Build, test e flusso di contribuzione
- **[Risoluzione dei Problemi](https://docs.claude-mem.ai/troubleshooting)** - Problemi comuni e soluzioni
---
## Come Funziona
**Componenti Principali:**
1. **5 Hook del Ciclo di Vita** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 script hook)
2. **Installazione Intelligente** - Controllo delle dipendenze in cache (script pre-hook, non un hook del ciclo di vita)
3. **Servizio Worker** - API HTTP sulla porta 37777 con interfaccia web viewer e 10 endpoint di ricerca, gestita da Bun
4. **Database SQLite** - Memorizza sessioni, osservazioni, riepiloghi
5. **Skill mem-search** - Query in linguaggio naturale con divulgazione progressiva
6. **Database Vettoriale Chroma** - Ricerca ibrida semantica + keyword per recupero intelligente del contesto
Vedi [Panoramica dell'Architettura](https://docs.claude-mem.ai/architecture/overview) per i dettagli.
---
## Skill mem-search
Claude-Mem fornisce una ricerca intelligente tramite la skill mem-search che si attiva automaticamente quando chiedi del lavoro passato:
**Come Funziona:**
- Chiedi semplicemente in modo naturale: *"Cosa abbiamo fatto nell'ultima sessione?"* o *"Abbiamo già risolto questo bug prima?"*
- Claude invoca automaticamente la skill mem-search per trovare il contesto rilevante
**Operazioni di Ricerca Disponibili:**
1. **Search Observations** - Ricerca full-text nelle osservazioni
2. **Search Sessions** - Ricerca full-text nei riepiloghi delle sessioni
3. **Search Prompts** - Ricerca nelle richieste utente grezze
4. **By Concept** - Trova per tag di concetto (discovery, problem-solution, pattern, ecc.)
5. **By File** - Trova osservazioni che fanno riferimento a file specifici
6. **By Type** - Trova per tipo (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Ottieni il contesto recente della sessione per un progetto
8. **Timeline** - Ottieni la timeline unificata del contesto attorno a un punto specifico nel tempo
9. **Timeline by Query** - Cerca osservazioni e ottieni il contesto della timeline attorno alla corrispondenza migliore
10. **API Help** - Ottieni la documentazione dell'API di ricerca
**Esempi di Query in Linguaggio Naturale:**
```
"Quali bug abbiamo risolto nell'ultima sessione?"
"Come abbiamo implementato l'autenticazione?"
"Quali modifiche sono state apportate a worker-service.ts?"
"Mostrami il lavoro recente su questo progetto"
"Cosa stava succedendo quando abbiamo aggiunto l'interfaccia del viewer?"
```
Vedi [Guida agli Strumenti di Ricerca](https://docs.claude-mem.ai/usage/search-tools) per esempi dettagliati.
---
## Funzionalità Beta
Claude-Mem offre un **canale beta** con funzionalità sperimentali come **Endless Mode** (architettura di memoria biomimetica per sessioni estese). Passa dalla versione stabile a quella beta dall'interfaccia web viewer su http://localhost:37777 → Settings.
Vedi **[Documentazione delle Funzionalità Beta](https://docs.claude-mem.ai/beta-features)** per dettagli su Endless Mode e come provarlo.
---
## Requisiti di Sistema
- **Node.js**: 18.0.0 o superiore
- **Claude Code**: Ultima versione con supporto plugin
- **Bun**: Runtime JavaScript e process manager (installato automaticamente se mancante)
- **uv**: Gestore di pacchetti Python per la ricerca vettoriale (installato automaticamente se mancante)
- **SQLite 3**: Per l'archiviazione persistente (incluso)
---
## Configurazione
Le impostazioni sono gestite in `~/.claude-mem/settings.json` (creato automaticamente con valori predefiniti alla prima esecuzione). Configura il modello AI, la porta del worker, la directory dei dati, il livello di log e le impostazioni di iniezione del contesto.
Vedi la **[Guida alla Configurazione](https://docs.claude-mem.ai/configuration)** per tutte le impostazioni disponibili ed esempi.
---
## Sviluppo
Vedi la **[Guida allo Sviluppo](https://docs.claude-mem.ai/development)** per le istruzioni di build, test e flusso di contribuzione.
---
## Risoluzione dei Problemi
Se riscontri problemi, descrivi il problema a Claude e la skill troubleshoot diagnosticherà automaticamente e fornirà correzioni.
Vedi la **[Guida alla Risoluzione dei Problemi](https://docs.claude-mem.ai/troubleshooting)** per problemi comuni e soluzioni.
---
## Segnalazione Bug
Crea report di bug completi con il generatore automatizzato:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Contribuire
I contributi sono benvenuti! Per favore:
1. Fai il fork del repository
2. Crea un branch per la funzionalità
3. Apporta le tue modifiche con i test
4. Aggiorna la documentazione
5. Invia una Pull Request
Vedi [Guida allo Sviluppo](https://docs.claude-mem.ai/development) per il flusso di contribuzione.
---
## Licenza
Questo progetto è rilasciato sotto la **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Tutti i diritti riservati.
Vedi il file [LICENSE](LICENSE) per i dettagli completi.
**Cosa Significa:**
- Puoi usare, modificare e distribuire questo software liberamente
- Se modifichi e distribuisci su un server di rete, devi rendere disponibile il tuo codice sorgente
- Le opere derivate devono anche essere rilasciate sotto AGPL-3.0
- NON c'è GARANZIA per questo software
**Nota su Ragtime**: La directory `ragtime/` è rilasciata separatamente sotto la **PolyForm Noncommercial License 1.0.0**. Vedi [ragtime/LICENSE](ragtime/LICENSE) per i dettagli.
---
## Supporto
- **Documentazione**: [docs/](docs/)
- **Problemi**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autore**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Creato con Claude Agent SDK** | **Alimentato da Claude Code** | **Realizzato con TypeScript**
---

302
docs/i18n/README.ja.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 これは自動翻訳です。コミュニティによる修正を歓迎します!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center"><a href="https://claude.com/claude-code" target="_blank">Claude Code</a>向けに構築された永続的メモリ圧縮システム</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#クイックスタート">クイックスタート</a> •
<a href="#仕組み">仕組み</a> •
<a href="#mcp検索ツール">検索ツール</a> •
<a href="#ドキュメント">ドキュメント</a> •
<a href="#設定">設定</a> •
<a href="#トラブルシューティング">トラブルシューティング</a> •
<a href="#ライセンス">ライセンス</a>
</p>
<p align="center">
Claude-Memは、ツール使用の観察を自動的にキャプチャし、セマンティックサマリーを生成して将来のセッションで利用可能にすることで、セッション間のコンテキストをシームレスに保持します。これにより、Claudeはセッションが終了または再接続された後でも、プロジェクトに関する知識の連続性を維持できます。
</p>
---
## クイックスタート
ターミナルで新しいClaude Codeセッションを開始し、次のコマンドを入力します:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Claude Codeを再起動します。以前のセッションからのコンテキストが新しいセッションに自動的に表示されます。
**主な機能:**
- 🧠 **永続的メモリ** - セッション間でコンテキストが保持される
- 📊 **プログレッシブディスクロージャー** - トークンコストの可視性を持つ階層的メモリ取得
- 🔍 **スキルベース検索** - mem-searchスキルでプロジェクト履歴をクエリ
- 🖥️ **Webビューア UI** - http://localhost:37777 でリアルタイムメモリストリームを表示
- 💻 **Claude Desktopスキル** - Claude Desktopの会話からメモリを検索
- 🔒 **プライバシー制御** - `<private>`タグを使用して機密コンテンツをストレージから除外
- ⚙️ **コンテキスト設定** - どのコンテキストが注入されるかを細かく制御
- 🤖 **自動動作** - 手動介入不要
- 🔗 **引用** - IDで過去の観察を参照(http://localhost:37777/api/observation/{id} でアクセス、またはhttp://localhost:37777 のWebビューアですべて表示)
- 🧪 **ベータチャネル** - バージョン切り替えでEndless Modeなどの実験的機能を試す
---
## ドキュメント
📚 **[完全なドキュメントを見る](docs/)** - GitHubでマークダウンドキュメントを閲覧
### はじめに
- **[インストールガイド](https://docs.claude-mem.ai/installation)** - クイックスタートと高度なインストール
- **[使用ガイド](https://docs.claude-mem.ai/usage/getting-started)** - Claude-Memが自動的に動作する仕組み
- **[検索ツール](https://docs.claude-mem.ai/usage/search-tools)** - 自然言語でプロジェクト履歴をクエリ
- **[ベータ機能](https://docs.claude-mem.ai/beta-features)** - Endless Modeなどの実験的機能を試す
### ベストプラクティス
- **[コンテキストエンジニアリング](https://docs.claude-mem.ai/context-engineering)** - AIエージェントのコンテキスト最適化原則
- **[プログレッシブディスクロージャー](https://docs.claude-mem.ai/progressive-disclosure)** - Claude-Memのコンテキストプライミング戦略の背後にある哲学
### アーキテクチャ
- **[概要](https://docs.claude-mem.ai/architecture/overview)** - システムコンポーネントとデータフロー
- **[アーキテクチャの進化](https://docs.claude-mem.ai/architecture-evolution)** - v3からv5への道のり
- **[フックアーキテクチャ](https://docs.claude-mem.ai/hooks-architecture)** - Claude-Memがライフサイクルフックを使用する方法
- **[フックリファレンス](https://docs.claude-mem.ai/architecture/hooks)** - 7つのフックスクリプトの説明
- **[ワーカーサービス](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP APIとBun管理
- **[データベース](https://docs.claude-mem.ai/architecture/database)** - SQLiteスキーマとFTS5検索
- **[検索アーキテクチャ](https://docs.claude-mem.ai/architecture/search-architecture)** - Chromaベクトルデータベースを使用したハイブリッド検索
### 設定と開発
- **[設定](https://docs.claude-mem.ai/configuration)** - 環境変数と設定
- **[開発](https://docs.claude-mem.ai/development)** - ビルド、テスト、コントリビューション
- **[トラブルシューティング](https://docs.claude-mem.ai/troubleshooting)** - よくある問題と解決策
---
## 仕組み
**コアコンポーネント:**
1. **5つのライフサイクルフック** - SessionStart、UserPromptSubmit、PostToolUse、Stop、SessionEnd(6つのフックスクリプト)
2. **スマートインストール** - キャッシュされた依存関係チェッカー(プレフックスクリプト、ライフサイクルフックではない)
3. **ワーカーサービス** - ポート37777上のHTTP API、WebビューアUIと10の検索エンドポイント、Bunで管理
4. **SQLiteデータベース** - セッション、観察、サマリーを保存
5. **mem-searchスキル** - プログレッシブディスクロージャーを備えた自然言語クエリ
6. **Chromaベクトルデータベース** - インテリジェントなコンテキスト取得のためのハイブリッドセマンティック+キーワード検索
詳細は[アーキテクチャ概要](https://docs.claude-mem.ai/architecture/overview)を参照してください。
---
## mem-searchスキル
Claude-Memは、過去の作業について尋ねると自動的に呼び出されるmem-searchスキルを通じてインテリジェント検索を提供します:
**仕組み:**
- 自然に質問するだけ: *「前回のセッションで何をしましたか?」* または *「以前このバグを修正しましたか?」*
- Claudeは自動的にmem-searchスキルを呼び出して関連するコンテキストを検索します
**利用可能な検索操作:**
1. **観察の検索** - 観察全体にわたる全文検索
2. **セッションの検索** - セッションサマリー全体にわたる全文検索
3. **プロンプトの検索** - 生のユーザーリクエストを検索
4. **コンセプト別** - コンセプトタグで検索(discovery、problem-solution、patternなど)
5. **ファイル別** - 特定のファイルを参照している観察を検索
6. **タイプ別** - タイプ別に検索(decision、bugfix、feature、refactor、discovery、change)
7. **最近のコンテキスト** - プロジェクトの最近のセッションコンテキストを取得
8. **タイムライン** - 特定の時点周辺のコンテキストの統一タイムラインを取得
9. **クエリ別タイムライン** - 観察を検索し、最適な一致周辺のタイムラインコンテキストを取得
10. **APIヘルプ** - 検索APIドキュメントを取得
**自然言語クエリの例:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
詳細な例は[検索ツールガイド](https://docs.claude-mem.ai/usage/search-tools)を参照してください。
---
## ベータ機能
Claude-Memは、**Endless Mode**(拡張セッション用の生体模倣メモリアーキテクチャ)などの実験的機能を備えた**ベータチャネル**を提供します。http://localhost:37777 → SettingsのWebビューアUIから安定版とベータ版を切り替えます。
Endless Modeと試用方法の詳細については、**[ベータ機能ドキュメント](https://docs.claude-mem.ai/beta-features)**を参照してください。
---
## システム要件
- **Node.js**: 18.0.0以上
- **Claude Code**: プラグインサポートを備えた最新バージョン
- **Bun**: JavaScriptランタイムおよびプロセスマネージャー(不足している場合は自動インストール)
- **uv**: ベクトル検索用のPythonパッケージマネージャー(不足している場合は自動インストール)
- **SQLite 3**: 永続ストレージ用(バンドル済み)
---
## 設定
設定は`~/.claude-mem/settings.json`で管理されます(初回実行時にデフォルト値で自動作成)。AIモデル、ワーカーポート、データディレクトリ、ログレベル、コンテキスト注入設定を構成します。
利用可能なすべての設定と例については、**[設定ガイド](https://docs.claude-mem.ai/configuration)**を参照してください。
---
## 開発
ビルド手順、テスト、コントリビューションワークフローについては、**[開発ガイド](https://docs.claude-mem.ai/development)**を参照してください。
---
## トラブルシューティング
問題が発生した場合は、Claudeに問題を説明すると、troubleshootスキルが自動的に診断して修正を提供します。
よくある問題と解決策については、**[トラブルシューティングガイド](https://docs.claude-mem.ai/troubleshooting)**を参照してください。
---
## バグレポート
自動ジェネレーターで包括的なバグレポートを作成します:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## コントリビューション
コントリビューションを歓迎します! 以下の手順に従ってください:
1. リポジトリをフォーク
2. 機能ブランチを作成
3. テストと共に変更を加える
4. ドキュメントを更新
5. プルリクエストを提出
コントリビューションワークフローについては[開発ガイド](https://docs.claude-mem.ai/development)を参照してください。
---
## ライセンス
このプロジェクトは**GNU Affero General Public License v3.0**(AGPL-3.0)の下でライセンスされています。
Copyright (C) 2025 Alex Newman (@thedotmack). All rights reserved.
詳細は[LICENSE](LICENSE)ファイルを参照してください。
**これが意味すること:**
- このソフトウェアを自由に使用、変更、配布できます
- ネットワークサーバーで変更して展開する場合、ソースコードを利用可能にする必要があります
- 派生作品もAGPL-3.0の下でライセンスする必要があります
- このソフトウェアには保証がありません
**Ragtimeに関する注意**: `ragtime/`ディレクトリは**PolyForm Noncommercial License 1.0.0**の下で個別にライセンスされています。詳細は[ragtime/LICENSE](ragtime/LICENSE)を参照してください。
---
## サポート
- **ドキュメント**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **リポジトリ**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **作者**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Claude Agent SDKで構築** | **Claude Codeで動作** | **TypeScriptで作成**

304
docs/i18n/README.ko.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 이것은 자동 번역입니다. 커뮤니티의 수정 제안을 환영합니다!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center"><a href="https://claude.com/claude-code" target="_blank">Claude Code</a>를 위해 구축된 지속적인 메모리 압축 시스템.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#빠른-시작">빠른 시작</a> •
<a href="#작동-방식">작동 방식</a> •
<a href="#mcp-검색-도구">검색 도구</a> •
<a href="#문서">문서</a> •
<a href="#설정">설정</a> •
<a href="#문제-해결">문제 해결</a> •
<a href="#라이선스">라이선스</a>
</p>
<p align="center">
Claude-Mem은 도구 사용 관찰을 자동으로 캡처하고 의미론적 요약을 생성하여 향후 세션에서 사용할 수 있도록 함으로써 세션 간 컨텍스트를 원활하게 보존합니다. 이를 통해 Claude는 세션이 종료되거나 재연결된 후에도 프로젝트에 대한 지식의 연속성을 유지할 수 있습니다.
</p>
---
## 빠른 시작
터미널에서 새 Claude Code 세션을 시작하고 다음 명령을 입력하세요:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Claude Code를 재시작하세요. 이전 세션의 컨텍스트가 자동으로 새 세션에 나타납니다.
**주요 기능:**
- 🧠 **지속적인 메모리** - 세션 간 컨텍스트 유지
- 📊 **점진적 공개** - 토큰 비용 가시성을 갖춘 계층화된 메모리 검색
- 🔍 **스킬 기반 검색** - mem-search 스킬로 프로젝트 기록 쿼리
- 🖥️ **웹 뷰어 UI** - http://localhost:37777에서 실시간 메모리 스트림 확인
- 💻 **Claude Desktop 스킬** - Claude Desktop 대화에서 메모리 검색
- 🔒 **개인정보 제어** - `<private>` 태그를 사용하여 민감한 콘텐츠를 저장소에서 제외
- ⚙️ **컨텍스트 설정** - 주입되는 컨텍스트에 대한 세밀한 제어
- 🤖 **자동 작동** - 수동 개입 불필요
- 🔗 **인용** - ID로 과거 관찰 참조 (http://localhost:37777/api/observation/{id}를 통해 액세스하거나 http://localhost:37777의 웹 뷰어에서 모두 보기)
- 🧪 **베타 채널** - 버전 전환을 통해 Endless Mode와 같은 실험적 기능 사용
---
## 문서
📚 **[전체 문서 보기](docs/)** - GitHub에서 마크다운 문서 탐색
### 시작하기
- **[설치 가이드](https://docs.claude-mem.ai/installation)** - 빠른 시작 및 고급 설치
- **[사용 가이드](https://docs.claude-mem.ai/usage/getting-started)** - Claude-Mem이 자동으로 작동하는 방법
- **[검색 도구](https://docs.claude-mem.ai/usage/search-tools)** - 자연어로 프로젝트 기록 쿼리
- **[베타 기능](https://docs.claude-mem.ai/beta-features)** - Endless Mode와 같은 실험적 기능 시도
### 모범 사례
- **[컨텍스트 엔지니어링](https://docs.claude-mem.ai/context-engineering)** - AI 에이전트 컨텍스트 최적화 원칙
- **[점진적 공개](https://docs.claude-mem.ai/progressive-disclosure)** - Claude-Mem의 컨텍스트 프라이밍 전략의 철학
### 아키텍처
- **[개요](https://docs.claude-mem.ai/architecture/overview)** - 시스템 구성 요소 및 데이터 흐름
- **[아키텍처 진화](https://docs.claude-mem.ai/architecture-evolution)** - v3에서 v5로의 여정
- **[후크 아키텍처](https://docs.claude-mem.ai/hooks-architecture)** - Claude-Mem이 라이프사이클 후크를 사용하는 방법
- **[후크 참조](https://docs.claude-mem.ai/architecture/hooks)** - 7개 후크 스크립트 설명
- **[워커 서비스](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API 및 Bun 관리
- **[데이터베이스](https://docs.claude-mem.ai/architecture/database)** - SQLite 스키마 및 FTS5 검색
- **[검색 아키텍처](https://docs.claude-mem.ai/architecture/search-architecture)** - Chroma 벡터 데이터베이스를 활용한 하이브리드 검색
### 설정 및 개발
- **[설정](https://docs.claude-mem.ai/configuration)** - 환경 변수 및 설정
- **[개발](https://docs.claude-mem.ai/development)** - 빌드, 테스트, 기여
- **[문제 해결](https://docs.claude-mem.ai/troubleshooting)** - 일반적인 문제 및 해결 방법
---
## 작동 방식
**핵심 구성 요소:**
1. **5개 라이프사이클 후크** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6개 후크 스크립트)
2. **스마트 설치** - 캐시된 종속성 검사기 (사전 후크 스크립트, 라이프사이클 후크 아님)
3. **워커 서비스** - 웹 뷰어 UI와 10개 검색 엔드포인트를 갖춘 포트 37777의 HTTP API, Bun으로 관리
4. **SQLite 데이터베이스** - 세션, 관찰, 요약 저장
5. **mem-search 스킬** - 점진적 공개를 통한 자연어 쿼리
6. **Chroma 벡터 데이터베이스** - 지능형 컨텍스트 검색을 위한 하이브리드 의미론적 + 키워드 검색
자세한 내용은 [아키텍처 개요](https://docs.claude-mem.ai/architecture/overview)를 참조하세요.
---
## mem-search 스킬
Claude-Mem은 과거 작업에 대해 질문할 때 자동으로 호출되는 mem-search 스킬을 통해 지능형 검색을 제공합니다:
**작동 방식:**
- 자연스럽게 질문하세요: *"지난 세션에서 무엇을 했나요?"* 또는 *"이 버그를 이전에 수정했나요?"*
- Claude가 관련 컨텍스트를 찾기 위해 mem-search 스킬을 자동으로 호출합니다
**사용 가능한 검색 작업:**
1. **관찰 검색** - 관찰에 대한 전체 텍스트 검색
2. **세션 검색** - 세션 요약에 대한 전체 텍스트 검색
3. **프롬프트 검색** - 원시 사용자 요청 검색
4. **개념별** - 개념 태그로 찾기 (discovery, problem-solution, pattern 등)
5. **파일별** - 특정 파일을 참조하는 관찰 찾기
6. **유형별** - 유형별로 찾기 (decision, bugfix, feature, refactor, discovery, change)
7. **최근 컨텍스트** - 프로젝트의 최근 세션 컨텍스트 가져오기
8. **타임라인** - 특정 시점 주변의 통합된 컨텍스트 타임라인 가져오기
9. **쿼리별 타임라인** - 관찰을 검색하고 가장 일치하는 항목 주변의 타임라인 컨텍스트 가져오기
10. **API 도움말** - 검색 API 문서 가져오기
**자연어 쿼리 예제:**
```
"지난 세션에서 어떤 버그를 수정했나요?"
"인증을 어떻게 구현했나요?"
"worker-service.ts에 어떤 변경 사항이 있었나요?"
"이 프로젝트의 최근 작업을 보여주세요"
"뷰어 UI를 추가할 때 무슨 일이 있었나요?"
```
자세한 예제는 [검색 도구 가이드](https://docs.claude-mem.ai/usage/search-tools)를 참조하세요.
---
## 베타 기능
Claude-Mem은 **Endless Mode**(확장된 세션을 위한 생체모방 메모리 아키텍처)와 같은 실험적 기능을 제공하는 **베타 채널**을 제공합니다. http://localhost:37777 → Settings의 웹 뷰어 UI에서 안정 버전과 베타 버전 간 전환이 가능합니다.
Endless Mode 및 사용 방법에 대한 자세한 내용은 **[베타 기능 문서](https://docs.claude-mem.ai/beta-features)**를 참조하세요.
---
## 시스템 요구 사항
- **Node.js**: 18.0.0 이상
- **Claude Code**: 플러그인 지원이 있는 최신 버전
- **Bun**: JavaScript 런타임 및 프로세스 관리자 (누락 시 자동 설치)
- **uv**: 벡터 검색을 위한 Python 패키지 관리자 (누락 시 자동 설치)
- **SQLite 3**: 영구 저장을 위한 데이터베이스 (번들 포함)
---
## 설정
설정은 `~/.claude-mem/settings.json`에서 관리됩니다 (첫 실행 시 기본값으로 자동 생성). AI 모델, 워커 포트, 데이터 디렉토리, 로그 수준 및 컨텍스트 주입 설정을 구성할 수 있습니다.
사용 가능한 모든 설정 및 예제는 **[설정 가이드](https://docs.claude-mem.ai/configuration)**를 참조하세요.
---
## 개발
빌드 지침, 테스트 및 기여 워크플로우는 **[개발 가이드](https://docs.claude-mem.ai/development)**를 참조하세요.
---
## 문제 해결
문제가 발생하면 Claude에게 문제를 설명하면 troubleshoot 스킬이 자동으로 진단하고 수정 사항을 제공합니다.
일반적인 문제 및 해결 방법은 **[문제 해결 가이드](https://docs.claude-mem.ai/troubleshooting)**를 참조하세요.
---
## 버그 보고
자동화된 생성기로 포괄적인 버그 보고서를 작성하세요:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## 기여
기여를 환영합니다! 다음 절차를 따라주세요:
1. 저장소 포크
2. 기능 브랜치 생성
3. 테스트와 함께 변경 사항 작성
4. 문서 업데이트
5. Pull Request 제출
기여 워크플로우는 [개발 가이드](https://docs.claude-mem.ai/development)를 참조하세요.
---
## 라이선스
이 프로젝트는 **GNU Affero General Public License v3.0** (AGPL-3.0)에 따라 라이선스가 부여됩니다.
Copyright (C) 2025 Alex Newman (@thedotmack). All rights reserved.
전체 세부 정보는 [LICENSE](LICENSE) 파일을 참조하세요.
**의미:**
- 이 소프트웨어를 자유롭게 사용, 수정 및 배포할 수 있습니다
- 수정하여 네트워크 서버에 배포하는 경우 소스 코드를 공개해야 합니다
- 파생 작업물도 AGPL-3.0에 따라 라이선스가 부여되어야 합니다
- 이 소프트웨어에는 보증이 없습니다
**Ragtime에 대한 참고 사항**: `ragtime/` 디렉토리는 **PolyForm Noncommercial License 1.0.0**에 따라 별도로 라이선스가 부여됩니다. 자세한 내용은 [ragtime/LICENSE](ragtime/LICENSE)를 참조하세요.
---
## 지원
- **문서**: [docs/](docs/)
- **이슈**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **저장소**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **작성자**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Claude Agent SDK로 구축** | **Claude Code 기반** | **TypeScript로 제작**
---

301
docs/i18n/README.nl.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 Dit is een automatische vertaling. Gemeenschapscorrecties zijn welkom!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Persistent geheugencompressiesysteem gebouwd voor <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#snel-starten">Snel Starten</a> •
<a href="#hoe-het-werkt">Hoe Het Werkt</a> •
<a href="#zoektools">Zoektools</a> •
<a href="#documentatie">Documentatie</a> •
<a href="#configuratie">Configuratie</a> •
<a href="#probleemoplossing">Probleemoplossing</a> •
<a href="#licentie">Licentie</a>
</p>
<p align="center">
Claude-Mem behoudt naadloos context tussen sessies door automatisch waarnemingen van toolgebruik vast te leggen, semantische samenvattingen te genereren en deze beschikbaar te maken voor toekomstige sessies. Dit stelt Claude in staat om continuïteit van kennis over projecten te behouden, zelfs nadat sessies eindigen of opnieuw verbinden.
</p>
---
## Snel Starten
Start een nieuwe Claude Code sessie in de terminal en voer de volgende commando's in:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Herstart Claude Code. Context van eerdere sessies verschijnt automatisch in nieuwe sessies.
**Belangrijkste Functies:**
- 🧠 **Persistent Geheugen** - Context blijft behouden tussen sessies
- 📊 **Progressieve Onthulling** - Gelaagde geheugenophaling met zichtbaarheid van tokenkosten
- 🔍 **Vaardigheidgebaseerd Zoeken** - Bevraag je projectgeschiedenis met mem-search vaardigheid
- 🖥️ **Web Viewer UI** - Real-time geheugenstroom op http://localhost:37777
- 💻 **Claude Desktop Vaardigheid** - Zoek geheugen vanuit Claude Desktop gesprekken
- 🔒 **Privacycontrole** - Gebruik `<private>` tags om gevoelige content uit te sluiten van opslag
- ⚙️ **Context Configuratie** - Fijnmazige controle over welke context wordt geïnjecteerd
- 🤖 **Automatische Werking** - Geen handmatige tussenkomst vereist
- 🔗 **Citaten** - Verwijs naar eerdere waarnemingen met ID's (toegang via http://localhost:37777/api/observation/{id} of bekijk alle in de web viewer op http://localhost:37777)
- 🧪 **Bètakanaal** - Probeer experimentele functies zoals Endless Mode via versieschakeling
---
## Documentatie
📚 **[Bekijk Volledige Documentatie](docs/)** - Blader door markdown documenten op GitHub
### Aan de Slag
- **[Installatiegids](https://docs.claude-mem.ai/installation)** - Snel starten & geavanceerde installatie
- **[Gebruikersgids](https://docs.claude-mem.ai/usage/getting-started)** - Hoe Claude-Mem automatisch werkt
- **[Zoektools](https://docs.claude-mem.ai/usage/search-tools)** - Bevraag je projectgeschiedenis met natuurlijke taal
- **[Bètafuncties](https://docs.claude-mem.ai/beta-features)** - Probeer experimentele functies zoals Endless Mode
### Beste Praktijken
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - AI agent context optimalisatieprincipes
- **[Progressieve Onthulling](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofie achter Claude-Mem's context priming strategie
### Architectuur
- **[Overzicht](https://docs.claude-mem.ai/architecture/overview)** - Systeemcomponenten & gegevensstroom
- **[Architectuurevolutie](https://docs.claude-mem.ai/architecture-evolution)** - De reis van v3 naar v5
- **[Hooks Architectuur](https://docs.claude-mem.ai/hooks-architecture)** - Hoe Claude-Mem lifecycle hooks gebruikt
- **[Hooks Referentie](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook scripts uitgelegd
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API & Bun beheer
- **[Database](https://docs.claude-mem.ai/architecture/database)** - SQLite schema & FTS5 zoeken
- **[Zoekarchitectuur](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybride zoeken met Chroma vector database
### Configuratie & Ontwikkeling
- **[Configuratie](https://docs.claude-mem.ai/configuration)** - Omgevingsvariabelen & instellingen
- **[Ontwikkeling](https://docs.claude-mem.ai/development)** - Bouwen, testen, bijdragen
- **[Probleemoplossing](https://docs.claude-mem.ai/troubleshooting)** - Veelvoorkomende problemen & oplossingen
---
## Hoe Het Werkt
**Kerncomponenten:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
2. **Slimme Installatie** - Gecachte afhankelijkheidscontrole (pre-hook script, geen lifecycle hook)
3. **Worker Service** - HTTP API op poort 37777 met web viewer UI en 10 zoekeindpunten, beheerd door Bun
4. **SQLite Database** - Slaat sessies, waarnemingen, samenvattingen op
5. **mem-search Vaardigheid** - Natuurlijke taal queries met progressieve onthulling
6. **Chroma Vector Database** - Hybride semantisch + zoekwoord zoeken voor intelligente context ophaling
Zie [Architectuuroverzicht](https://docs.claude-mem.ai/architecture/overview) voor details.
---
## mem-search Vaardigheid
Claude-Mem biedt intelligent zoeken via de mem-search vaardigheid die automatisch wordt aangeroepen wanneer je vraagt over eerder werk:
**Hoe Het Werkt:**
- Vraag gewoon natuurlijk: *"Wat hebben we vorige sessie gedaan?"* of *"Hebben we deze bug eerder opgelost?"*
- Claude roept automatisch de mem-search vaardigheid aan om relevante context te vinden
**Beschikbare Zoekoperaties:**
1. **Search Observations** - Volledige tekst zoeken door waarnemingen
2. **Search Sessions** - Volledige tekst zoeken door sessiesamenvattingen
3. **Search Prompts** - Zoek ruwe gebruikersverzoeken
4. **By Concept** - Vind op concepttags (discovery, problem-solution, pattern, etc.)
5. **By File** - Vind waarnemingen die specifieke bestanden refereren
6. **By Type** - Vind op type (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Krijg recente sessiecontext voor een project
8. **Timeline** - Krijg uniforme tijdlijn van context rond een specifiek tijdstip
9. **Timeline by Query** - Zoek naar waarnemingen en krijg tijdlijncontext rond beste match
10. **API Help** - Krijg zoek API documentatie
**Voorbeeld Natuurlijke Taal Queries:**
```
"Welke bugs hebben we vorige sessie opgelost?"
"Hoe hebben we authenticatie geïmplementeerd?"
"Welke wijzigingen zijn gemaakt aan worker-service.ts?"
"Laat me recent werk aan dit project zien"
"Wat gebeurde er toen we de viewer UI toevoegden?"
```
Zie [Zoektools Gids](https://docs.claude-mem.ai/usage/search-tools) voor gedetailleerde voorbeelden.
---
## Bètafuncties
Claude-Mem biedt een **bètakanaal** met experimentele functies zoals **Endless Mode** (biomimetische geheugenarchitectuur voor uitgebreide sessies). Schakel tussen stabiele en bètaversies vanuit de web viewer UI op http://localhost:37777 → Settings.
Zie **[Bètafuncties Documentatie](https://docs.claude-mem.ai/beta-features)** voor details over Endless Mode en hoe je het kunt proberen.
---
## Systeemvereisten
- **Node.js**: 18.0.0 of hoger
- **Claude Code**: Nieuwste versie met plugin ondersteuning
- **Bun**: JavaScript runtime en procesbeheer (automatisch geïnstalleerd indien ontbreekt)
- **uv**: Python package manager voor vector zoeken (automatisch geïnstalleerd indien ontbreekt)
- **SQLite 3**: Voor persistente opslag (meegeleverd)
---
## Configuratie
Instellingen worden beheerd in `~/.claude-mem/settings.json` (automatisch aangemaakt met standaardinstellingen bij eerste run). Configureer AI model, worker poort, data directory, logniveau en context injectie-instellingen.
Zie de **[Configuratiegids](https://docs.claude-mem.ai/configuration)** voor alle beschikbare instellingen en voorbeelden.
---
## Ontwikkeling
Zie de **[Ontwikkelingsgids](https://docs.claude-mem.ai/development)** voor bouwinstructies, testen en bijdrageworkflow.
---
## Probleemoplossing
Als je problemen ervaart, beschrijf het probleem aan Claude en de troubleshoot vaardigheid zal automatisch diagnosticeren en oplossingen bieden.
Zie de **[Probleemoplossingsgids](https://docs.claude-mem.ai/troubleshooting)** voor veelvoorkomende problemen en oplossingen.
---
## Bugrapporten
Maak uitgebreide bugrapporten met de geautomatiseerde generator:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Bijdragen
Bijdragen zijn welkom! Gelieve:
1. Fork de repository
2. Maak een feature branch
3. Maak je wijzigingen met tests
4. Update documentatie
5. Dien een Pull Request in
Zie [Ontwikkelingsgids](https://docs.claude-mem.ai/development) voor bijdrageworkflow.
---
## Licentie
Dit project is gelicentieerd onder de **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Alle rechten voorbehouden.
Zie het [LICENSE](LICENSE) bestand voor volledige details.
**Wat Dit Betekent:**
- Je kunt deze software vrijelijk gebruiken, aanpassen en distribueren
- Als je aanpast en implementeert op een netwerkserver, moet je je broncode beschikbaar maken
- Afgeleide werken moeten ook gelicentieerd zijn onder AGPL-3.0
- Er is GEEN GARANTIE voor deze software
**Opmerking over Ragtime**: De `ragtime/` directory is afzonderlijk gelicentieerd onder de **PolyForm Noncommercial License 1.0.0**. Zie [ragtime/LICENSE](ragtime/LICENSE) voor details.
---
## Ondersteuning
- **Documentatie**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Auteur**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Gebouwd met Claude Agent SDK** | **Aangedreven door Claude Code** | **Gemaakt met TypeScript**

304
docs/i18n/README.no.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 Dette er en automatisk oversettelse. Bidrag fra fellesskapet er velkomne!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Vedvarende minnekomprimeringssystem bygget for <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#hurtigstart">Hurtigstart</a> •
<a href="#hvordan-det-fungerer">Hvordan Det Fungerer</a> •
<a href="#mcp-søkeverktøy">Søkeverktøy</a> •
<a href="#dokumentasjon">Dokumentasjon</a> •
<a href="#konfigurasjon">Konfigurasjon</a> •
<a href="#feilsøking">Feilsøking</a> •
<a href="#lisens">Lisens</a>
</p>
<p align="center">
Claude-Mem bevarer sømløst kontekst på tvers av økter ved automatisk å fange opp observasjoner av verktøybruk, generere semantiske sammendrag, og gjøre dem tilgjengelige for fremtidige økter. Dette gjør det mulig for Claude å opprettholde kunnskapskontinuitet om prosjekter selv etter at økter avsluttes eller gjenopprettes.
</p>
---
## Hurtigstart
Start en ny Claude Code-økt i terminalen og skriv inn følgende kommandoer:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Start Claude Code på nytt. Kontekst fra tidligere økter vil automatisk vises i nye økter.
**Nøkkelfunksjoner:**
- 🧠 **Vedvarende Minne** - Kontekst overlever på tvers av økter
- 📊 **Progressiv Avsløring** - Lagdelt minnehenting med synlighet av tokenkostnader
- 🔍 **Ferdighetsbasert Søk** - Spør om prosjekthistorikken din med mem-search-ferdigheten
- 🖥️ **Nettleser UI** - Sanntids minnestrøm på http://localhost:37777
- 💻 **Claude Desktop-ferdighet** - Søk i minne fra Claude Desktop-samtaler
- 🔒 **Personvernkontroll** - Bruk `<private>`-tagger for å ekskludere sensitivt innhold fra lagring
- ⚙️ **Kontekstkonfigurasjon** - Finjustert kontroll over hvilken kontekst som injiseres
- 🤖 **Automatisk Drift** - Ingen manuell inngripen nødvendig
- 🔗 **Kildehenvisninger** - Referer til tidligere observasjoner med ID-er (tilgang via http://localhost:37777/api/observation/{id} eller se alle i nettviseren på http://localhost:37777)
- 🧪 **Beta-kanal** - Prøv eksperimentelle funksjoner som Endless Mode via versjonsbytte
---
## Dokumentasjon
📚 **[Se Full Dokumentasjon](docs/)** - Bla gjennom markdown-dokumenter på GitHub
### Komme I Gang
- **[Installasjonsveiledning](https://docs.claude-mem.ai/installation)** - Hurtigstart og avansert installasjon
- **[Brukerveiledning](https://docs.claude-mem.ai/usage/getting-started)** - Hvordan Claude-Mem fungerer automatisk
- **[Søkeverktøy](https://docs.claude-mem.ai/usage/search-tools)** - Spør om prosjekthistorikken din med naturlig språk
- **[Beta-funksjoner](https://docs.claude-mem.ai/beta-features)** - Prøv eksperimentelle funksjoner som Endless Mode
### Beste Praksis
- **[Kontekst Engineering](https://docs.claude-mem.ai/context-engineering)** - Optimaliseringsprinsipper for AI-agentkontekst
- **[Progressiv Avsløring](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofien bak Claude-Mems strategi for kontekstpriming
### Arkitektur
- **[Oversikt](https://docs.claude-mem.ai/architecture/overview)** - Systemkomponenter og dataflyt
- **[Arkitekturutvikling](https://docs.claude-mem.ai/architecture-evolution)** - Reisen fra v3 til v5
- **[Hooks-arkitektur](https://docs.claude-mem.ai/hooks-architecture)** - Hvordan Claude-Mem bruker livssyklus-hooks
- **[Hooks-referanse](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook-skript forklart
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API og Bun-administrasjon
- **[Database](https://docs.claude-mem.ai/architecture/database)** - SQLite-skjema og FTS5-søk
- **[Søkearkitektur](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybridsøk med Chroma vektordatabase
### Konfigurasjon og Utvikling
- **[Konfigurasjon](https://docs.claude-mem.ai/configuration)** - Miljøvariabler og innstillinger
- **[Utvikling](https://docs.claude-mem.ai/development)** - Bygging, testing, bidragsflyt
- **[Feilsøking](https://docs.claude-mem.ai/troubleshooting)** - Vanlige problemer og løsninger
---
## Hvordan Det Fungerer
**Kjernekomponenter:**
1. **5 Livssyklus-Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook-skript)
2. **Smart Installasjon** - Bufret avhengighetssjekker (pre-hook-skript, ikke en livssyklus-hook)
3. **Worker Service** - HTTP API på port 37777 med nettleser UI og 10 søkeendepunkter, administrert av Bun
4. **SQLite Database** - Lagrer økter, observasjoner, sammendrag
5. **mem-search-ferdighet** - Naturligspråklige spørringer med progressiv avsløring
6. **Chroma Vektordatabase** - Hybrid semantisk + nøkkelordsøk for intelligent konteksthenting
Se [Arkitekturoversikt](https://docs.claude-mem.ai/architecture/overview) for detaljer.
---
## mem-search-ferdighet
Claude-Mem tilbyr intelligent søk gjennom mem-search-ferdigheten som automatisk aktiveres når du spør om tidligere arbeid:
**Hvordan Det Fungerer:**
- Bare spør naturlig: *"Hva gjorde vi forrige økt?"* eller *"Fikset vi denne feilen før?"*
- Claude aktiverer automatisk mem-search-ferdigheten for å finne relevant kontekst
**Tilgjengelige Søkeoperasjoner:**
1. **Search Observations** - Fulltekstsøk på tvers av observasjoner
2. **Search Sessions** - Fulltekstsøk på tvers av øktsammendrag
3. **Search Prompts** - Søk i rå brukerforespørsler
4. **By Concept** - Finn etter konsept-tagger (discovery, problem-solution, pattern, osv.)
5. **By File** - Finn observasjoner som refererer til spesifikke filer
6. **By Type** - Finn etter type (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Få nylig øktkontekst for et prosjekt
8. **Timeline** - Få samlet tidslinje av kontekst rundt et spesifikt tidspunkt
9. **Timeline by Query** - Søk etter observasjoner og få tidslinjekontekst rundt beste treff
10. **API Help** - Få søke-API-dokumentasjon
**Eksempel på Naturligspråklige Spørringer:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Se [Søkeverktøy-veiledning](https://docs.claude-mem.ai/usage/search-tools) for detaljerte eksempler.
---
## Beta-funksjoner
Claude-Mem tilbyr en **beta-kanal** med eksperimentelle funksjoner som **Endless Mode** (biomimetisk minnearkitektur for utvidede økter). Bytt mellom stabile og beta-versjoner fra nettleser-UI på http://localhost:37777 → Settings.
Se **[Beta-funksjoner Dokumentasjon](https://docs.claude-mem.ai/beta-features)** for detaljer om Endless Mode og hvordan du prøver det.
---
## Systemkrav
- **Node.js**: 18.0.0 eller høyere
- **Claude Code**: Nyeste versjon med plugin-støtte
- **Bun**: JavaScript-runtime og prosessadministrator (autoinstalleres hvis mangler)
- **uv**: Python-pakkeadministrator for vektorsøk (autoinstalleres hvis mangler)
- **SQLite 3**: For vedvarende lagring (inkludert)
---
## Konfigurasjon
Innstillinger administreres i `~/.claude-mem/settings.json` (opprettes automatisk med standardverdier ved første kjøring). Konfigurer AI-modell, worker-port, datakatalog, loggnivå og innstillinger for kontekstinjeksjon.
Se **[Konfigurasjonsveiledning](https://docs.claude-mem.ai/configuration)** for alle tilgjengelige innstillinger og eksempler.
---
## Utvikling
Se **[Utviklingsveiledning](https://docs.claude-mem.ai/development)** for byggeinstruksjoner, testing og bidragsflyt.
---
## Feilsøking
Hvis du opplever problemer, beskriv problemet til Claude og troubleshoot-ferdigheten vil automatisk diagnostisere og gi løsninger.
Se **[Feilsøkingsveiledning](https://docs.claude-mem.ai/troubleshooting)** for vanlige problemer og løsninger.
---
## Feilrapporter
Opprett omfattende feilrapporter med den automatiserte generatoren:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Bidra
Bidrag er velkomne! Vennligst:
1. Fork repositoryet
2. Opprett en feature-gren
3. Gjør endringene dine med tester
4. Oppdater dokumentasjonen
5. Send inn en Pull Request
Se [Utviklingsveiledning](https://docs.claude-mem.ai/development) for bidragsflyt.
---
## Lisens
Dette prosjektet er lisensiert under **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Alle rettigheter reservert.
Se [LICENSE](LICENSE)-filen for fullstendige detaljer.
**Hva Dette Betyr:**
- Du kan bruke, modifisere og distribuere denne programvaren fritt
- Hvis du modifiserer og distribuerer på en nettverkstjener, må du gjøre kildekoden din tilgjengelig
- Avledede verk må også være lisensiert under AGPL-3.0
- Det er INGEN GARANTI for denne programvaren
**Merknad om Ragtime**: `ragtime/`-katalogen er lisensiert separat under **PolyForm Noncommercial License 1.0.0**. Se [ragtime/LICENSE](ragtime/LICENSE) for detaljer.
---
## Støtte
- **Dokumentasjon**: [docs/](docs/)
- **Problemer**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Forfatter**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Bygget med Claude Agent SDK** | **Drevet av Claude Code** | **Laget med TypeScript**
---

301
docs/i18n/README.pl.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 To jest automatyczne tłumaczenie. Korekty społeczności są mile widziane!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">System trwałej kompresji pamięci stworzony dla <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#szybki-start">Szybki Start</a> •
<a href="#jak-to-działa">Jak To Działa</a> •
<a href="#narzędzia-wyszukiwania">Narzędzia Wyszukiwania</a> •
<a href="#dokumentacja">Dokumentacja</a> •
<a href="#konfiguracja">Konfiguracja</a> •
<a href="#rozwiązywanie-problemów">Rozwiązywanie Problemów</a> •
<a href="#licencja">Licencja</a>
</p>
<p align="center">
Claude-Mem płynnie zachowuje kontekst między sesjami, automatycznie przechwytując obserwacje użycia narzędzi, generując semantyczne podsumowania i udostępniając je przyszłym sesjom. To umożliwia Claude utrzymanie ciągłości wiedzy o projektach nawet po zakończeniu lub ponownym połączeniu sesji.
</p>
---
## Szybki Start
Uruchom nową sesję Claude Code w terminalu i wprowadź następujące polecenia:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Uruchom ponownie Claude Code. Kontekst z poprzednich sesji automatycznie pojawi się w nowych sesjach.
**Kluczowe Funkcje:**
- 🧠 **Trwała Pamięć** - Kontekst przetrwa między sesjami
- 📊 **Stopniowe Ujawnianie** - Warstwowe pobieranie pamięci z widocznością kosztów tokenów
- 🔍 **Wyszukiwanie Oparte na Umiejętnościach** - Przeszukuj historię projektu za pomocą umiejętności mem-search
- 🖥️ **Interfejs Przeglądarki Internetowej** - Strumień pamięci w czasie rzeczywistym pod adresem http://localhost:37777
- 💻 **Umiejętność Claude Desktop** - Przeszukuj pamięć z konwersacji Claude Desktop
- 🔒 **Kontrola Prywatności** - Użyj tagów `<private>`, aby wykluczyć wrażliwe treści z przechowywania
- ⚙️ **Konfiguracja Kontekstu** - Szczegółowa kontrola nad tym, jaki kontekst jest wstrzykiwany
- 🤖 **Automatyczne Działanie** - Nie wymaga ręcznej interwencji
- 🔗 **Cytowania** - Odniesienia do przeszłych obserwacji za pomocą identyfikatorów (dostęp przez http://localhost:37777/api/observation/{id} lub wyświetl wszystkie w przeglądarce internetowej pod adresem http://localhost:37777)
- 🧪 **Kanał Beta** - Wypróbuj eksperymentalne funkcje, takie jak Endless Mode, poprzez przełączanie wersji
---
## Dokumentacja
📚 **[Wyświetl Pełną Dokumentację](docs/)** - Przeglądaj dokumentację markdown na GitHub
### Pierwsze Kroki
- **[Przewodnik Instalacji](https://docs.claude-mem.ai/installation)** - Szybki start i zaawansowana instalacja
- **[Przewodnik Użytkowania](https://docs.claude-mem.ai/usage/getting-started)** - Jak Claude-Mem działa automatycznie
- **[Narzędzia Wyszukiwania](https://docs.claude-mem.ai/usage/search-tools)** - Przeszukuj historię projektu w języku naturalnym
- **[Funkcje Beta](https://docs.claude-mem.ai/beta-features)** - Wypróbuj eksperymentalne funkcje, takie jak Endless Mode
### Najlepsze Praktyki
- **[Inżynieria Kontekstu](https://docs.claude-mem.ai/context-engineering)** - Zasady optymalizacji kontekstu agenta AI
- **[Stopniowe Ujawnianie](https://docs.claude-mem.ai/progressive-disclosure)** - Filozofia strategii przygotowania kontekstu Claude-Mem
### Architektura
- **[Przegląd](https://docs.claude-mem.ai/architecture/overview)** - Komponenty systemu i przepływ danych
- **[Ewolucja Architektury](https://docs.claude-mem.ai/architecture-evolution)** - Droga od v3 do v5
- **[Architektura Hooków](https://docs.claude-mem.ai/hooks-architecture)** - Jak Claude-Mem wykorzystuje hooki cyklu życia
- **[Dokumentacja Hooków](https://docs.claude-mem.ai/architecture/hooks)** - 7 skryptów hooków wyjaśnionych
- **[Usługa Worker](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API i zarządzanie Bun
- **[Baza Danych](https://docs.claude-mem.ai/architecture/database)** - Schemat SQLite i wyszukiwanie FTS5
- **[Architektura Wyszukiwania](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybrydowe wyszukiwanie z bazą wektorów Chroma
### Konfiguracja i Rozwój
- **[Konfiguracja](https://docs.claude-mem.ai/configuration)** - Zmienne środowiskowe i ustawienia
- **[Rozwój](https://docs.claude-mem.ai/development)** - Budowanie, testowanie, współpraca
- **[Rozwiązywanie Problemów](https://docs.claude-mem.ai/troubleshooting)** - Typowe problemy i rozwiązania
---
## Jak To Działa
**Główne Komponenty:**
1. **5 Hooków Cyklu Życia** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 skryptów hooków)
2. **Inteligentna Instalacja** - Buforowany sprawdzacz zależności (skrypt pre-hook, nie hook cyklu życia)
3. **Usługa Worker** - HTTP API na porcie 37777 z interfejsem przeglądarki internetowej i 10 punktami końcowymi wyszukiwania, zarządzana przez Bun
4. **Baza Danych SQLite** - Przechowuje sesje, obserwacje, podsumowania
5. **Umiejętność mem-search** - Zapytania w języku naturalnym ze stopniowym ujawnianiem
6. **Baza Wektorów Chroma** - Hybrydowe wyszukiwanie semantyczne + słowa kluczowe dla inteligentnego pobierania kontekstu
Zobacz [Przegląd Architektury](https://docs.claude-mem.ai/architecture/overview) dla szczegółów.
---
## Umiejętność mem-search
Claude-Mem zapewnia inteligentne wyszukiwanie poprzez umiejętność mem-search, która automatycznie aktywuje się, gdy pytasz o przeszłą pracę:
**Jak To Działa:**
- Po prostu pytaj naturalnie: *"Co robiliśmy w ostatniej sesji?"* lub *"Czy naprawiliśmy ten błąd wcześniej?"*
- Claude automatycznie wywołuje umiejętność mem-search, aby znaleźć odpowiedni kontekst
**Dostępne Operacje Wyszukiwania:**
1. **Search Observations** - Wyszukiwanie pełnotekstowe w obserwacjach
2. **Search Sessions** - Wyszukiwanie pełnotekstowe w podsumowaniach sesji
3. **Search Prompts** - Wyszukiwanie surowych żądań użytkownika
4. **By Concept** - Znajdź według tagów koncepcyjnych (discovery, problem-solution, pattern, itp.)
5. **By File** - Znajdź obserwacje odnoszące się do określonych plików
6. **By Type** - Znajdź według typu (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Pobierz ostatni kontekst sesji dla projektu
8. **Timeline** - Uzyskaj ujednoliconą oś czasu kontekstu wokół określonego punktu w czasie
9. **Timeline by Query** - Wyszukaj obserwacje i uzyskaj kontekst osi czasu wokół najlepszego dopasowania
10. **API Help** - Uzyskaj dokumentację API wyszukiwania
**Przykładowe Zapytania w Języku Naturalnym:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Zobacz [Przewodnik Narzędzi Wyszukiwania](https://docs.claude-mem.ai/usage/search-tools) dla szczegółowych przykładów.
---
## Funkcje Beta
Claude-Mem oferuje **kanał beta** z eksperymentalnymi funkcjami, takimi jak **Endless Mode** (biomimetyczna architektura pamięci dla rozszerzonych sesji). Przełączaj się między stabilnymi a beta wersjami z interfejsu przeglądarki internetowej pod adresem http://localhost:37777 → Settings.
Zobacz **[Dokumentacja Funkcji Beta](https://docs.claude-mem.ai/beta-features)** dla szczegółów dotyczących Endless Mode i sposobu wypróbowania.
---
## Wymagania Systemowe
- **Node.js**: 18.0.0 lub wyższy
- **Claude Code**: Najnowsza wersja z obsługą wtyczek
- **Bun**: Środowisko uruchomieniowe JavaScript i menedżer procesów (automatycznie instalowany, jeśli brakuje)
- **uv**: Menedżer pakietów Python do wyszukiwania wektorowego (automatycznie instalowany, jeśli brakuje)
- **SQLite 3**: Do trwałego przechowywania (dołączony)
---
## Konfiguracja
Ustawienia są zarządzane w `~/.claude-mem/settings.json` (automatycznie tworzone z domyślnymi wartościami przy pierwszym uruchomieniu). Skonfiguruj model AI, port workera, katalog danych, poziom logowania i ustawienia wstrzykiwania kontekstu.
Zobacz **[Przewodnik Konfiguracji](https://docs.claude-mem.ai/configuration)** dla wszystkich dostępnych ustawień i przykładów.
---
## Rozwój
Zobacz **[Przewodnik Rozwoju](https://docs.claude-mem.ai/development)** dla instrukcji budowania, testowania i przepływu pracy współpracy.
---
## Rozwiązywanie Problemów
Jeśli napotkasz problemy, opisz problem Claude, a umiejętność troubleshoot automatycznie zdiagnozuje i dostarczy poprawki.
Zobacz **[Przewodnik Rozwiązywania Problemów](https://docs.claude-mem.ai/troubleshooting)** dla typowych problemów i rozwiązań.
---
## Zgłoszenia Błędów
Twórz kompleksowe raporty błędów za pomocą automatycznego generatora:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Współpraca
Wkład jest mile widziany! Proszę:
1. Forkuj repozytorium
2. Utwórz gałąź funkcji
3. Dokonaj zmian z testami
4. Zaktualizuj dokumentację
5. Prześlij Pull Request
Zobacz [Przewodnik Rozwoju](https://docs.claude-mem.ai/development) dla przepływu pracy współpracy.
---
## Licencja
Ten projekt jest licencjonowany na podstawie **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Wszelkie prawa zastrzeżone.
Zobacz plik [LICENSE](LICENSE) dla pełnych szczegółów.
**Co To Oznacza:**
- Możesz używać, modyfikować i dystrybuować to oprogramowanie swobodnie
- Jeśli zmodyfikujesz i wdrożysz na serwerze sieciowym, musisz udostępnić swój kod źródłowy
- Dzieła pochodne muszą być również licencjonowane na podstawie AGPL-3.0
- Nie ma GWARANCJI dla tego oprogramowania
**Uwaga o Ragtime**: Katalog `ragtime/` jest licencjonowany osobno na podstawie **PolyForm Noncommercial License 1.0.0**. Zobacz [ragtime/LICENSE](ragtime/LICENSE) dla szczegółów.
---
## Wsparcie
- **Dokumentacja**: [docs/](docs/)
- **Problemy**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repozytorium**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autor**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Zbudowano za pomocą Claude Agent SDK** | **Zasilane przez Claude Code** | **Wykonane w TypeScript**

302
docs/i18n/README.pt-br.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Esta é uma tradução automatizada. Correções da comunidade são bem-vindas!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Sistema de compressão de memória persistente construído para <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#início-rápido">Início Rápido</a> •
<a href="#como-funciona">Como Funciona</a> •
<a href="#ferramentas-de-busca-mcp">Ferramentas de Busca</a> •
<a href="#documentação">Documentação</a> •
<a href="#configuração">Configuração</a> •
<a href="#solução-de-problemas">Solução de Problemas</a> •
<a href="#licença">Licença</a>
</p>
<p align="center">
Claude-Mem preserva o contexto perfeitamente entre sessões, capturando automaticamente observações de uso de ferramentas, gerando resumos semânticos e disponibilizando-os para sessões futuras. Isso permite que Claude mantenha a continuidade do conhecimento sobre projetos mesmo após o término ou reconexão de sessões.
</p>
---
## Início Rápido
Inicie uma nova sessão do Claude Code no terminal e digite os seguintes comandos:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Reinicie o Claude Code. O contexto de sessões anteriores aparecerá automaticamente em novas sessões.
**Principais Recursos:**
- 🧠 **Memória Persistente** - O contexto sobrevive entre sessões
- 📊 **Divulgação Progressiva** - Recuperação de memória em camadas com visibilidade de custo de tokens
- 🔍 **Busca Baseada em Skill** - Consulte seu histórico de projeto com a skill mem-search
- 🖥️ **Interface Web de Visualização** - Fluxo de memória em tempo real em http://localhost:37777
- 💻 **Skill para Claude Desktop** - Busque memória em conversas do Claude Desktop
- 🔒 **Controle de Privacidade** - Use tags `<private>` para excluir conteúdo sensível do armazenamento
- ⚙️ **Configuração de Contexto** - Controle refinado sobre qual contexto é injetado
- 🤖 **Operação Automática** - Nenhuma intervenção manual necessária
- 🔗 **Citações** - Referencie observações passadas com IDs (acesse via http://localhost:37777/api/observation/{id} ou visualize todas no visualizador web em http://localhost:37777)
- 🧪 **Canal Beta** - Experimente recursos experimentais como o Endless Mode através da troca de versões
---
## Documentação
📚 **[Ver Documentação Completa](docs/)** - Navegue pelos documentos markdown no GitHub
### Começando
- **[Guia de Instalação](https://docs.claude-mem.ai/installation)** - Início rápido e instalação avançada
- **[Guia de Uso](https://docs.claude-mem.ai/usage/getting-started)** - Como Claude-Mem funciona automaticamente
- **[Ferramentas de Busca](https://docs.claude-mem.ai/usage/search-tools)** - Consulte seu histórico de projeto com linguagem natural
- **[Recursos Beta](https://docs.claude-mem.ai/beta-features)** - Experimente recursos experimentais como o Endless Mode
### Melhores Práticas
- **[Engenharia de Contexto](https://docs.claude-mem.ai/context-engineering)** - Princípios de otimização de contexto para agentes de IA
- **[Divulgação Progressiva](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofia por trás da estratégia de preparação de contexto do Claude-Mem
### Arquitetura
- **[Visão Geral](https://docs.claude-mem.ai/architecture/overview)** - Componentes do sistema e fluxo de dados
- **[Evolução da Arquitetura](https://docs.claude-mem.ai/architecture-evolution)** - A jornada da v3 à v5
- **[Arquitetura de Hooks](https://docs.claude-mem.ai/hooks-architecture)** - Como Claude-Mem usa hooks de ciclo de vida
- **[Referência de Hooks](https://docs.claude-mem.ai/architecture/hooks)** - 7 scripts de hook explicados
- **[Serviço Worker](https://docs.claude-mem.ai/architecture/worker-service)** - API HTTP e gerenciamento do Bun
- **[Banco de Dados](https://docs.claude-mem.ai/architecture/database)** - Schema SQLite e busca FTS5
- **[Arquitetura de Busca](https://docs.claude-mem.ai/architecture/search-architecture)** - Busca híbrida com banco de dados vetorial Chroma
### Configuração e Desenvolvimento
- **[Configuração](https://docs.claude-mem.ai/configuration)** - Variáveis de ambiente e configurações
- **[Desenvolvimento](https://docs.claude-mem.ai/development)** - Build, testes e contribuição
- **[Solução de Problemas](https://docs.claude-mem.ai/troubleshooting)** - Problemas comuns e soluções
---
## Como Funciona
**Componentes Principais:**
1. **5 Hooks de Ciclo de Vida** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 scripts de hook)
2. **Instalação Inteligente** - Verificador de dependências em cache (script pré-hook, não um hook de ciclo de vida)
3. **Serviço Worker** - API HTTP na porta 37777 com interface de visualização web e 10 endpoints de busca, gerenciado pelo Bun
4. **Banco de Dados SQLite** - Armazena sessões, observações, resumos
5. **Skill mem-search** - Consultas em linguagem natural com divulgação progressiva
6. **Banco de Dados Vetorial Chroma** - Busca híbrida semântica + palavra-chave para recuperação inteligente de contexto
Veja [Visão Geral da Arquitetura](https://docs.claude-mem.ai/architecture/overview) para detalhes.
---
## Skill mem-search
Claude-Mem fornece busca inteligente através da skill mem-search que se auto-invoca quando você pergunta sobre trabalhos anteriores:
**Como Funciona:**
- Apenas pergunte naturalmente: *"O que fizemos na última sessão?"* ou *"Já corrigimos esse bug antes?"*
- Claude invoca automaticamente a skill mem-search para encontrar contexto relevante
**Operações de Busca Disponíveis:**
1. **Search Observations** - Busca de texto completo em observações
2. **Search Sessions** - Busca de texto completo em resumos de sessão
3. **Search Prompts** - Busca em solicitações brutas do usuário
4. **By Concept** - Encontre por tags de conceito (discovery, problem-solution, pattern, etc.)
5. **By File** - Encontre observações que referenciam arquivos específicos
6. **By Type** - Encontre por tipo (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Obtenha contexto de sessão recente para um projeto
8. **Timeline** - Obtenha linha do tempo unificada de contexto em torno de um ponto específico no tempo
9. **Timeline by Query** - Busque observações e obtenha contexto de linha do tempo em torno da melhor correspondência
10. **API Help** - Obtenha documentação da API de busca
**Exemplos de Consultas em Linguagem Natural:**
```
"Quais bugs corrigimos na última sessão?"
"Como implementamos a autenticação?"
"Quais mudanças foram feitas em worker-service.ts?"
"Mostre-me trabalhos recentes neste projeto"
"O que estava acontecendo quando adicionamos a interface de visualização?"
```
Veja [Guia de Ferramentas de Busca](https://docs.claude-mem.ai/usage/search-tools) para exemplos detalhados.
---
## Recursos Beta
Claude-Mem oferece um **canal beta** com recursos experimentais como **Endless Mode** (arquitetura de memória biomimética para sessões estendidas). Alterne entre versões estável e beta pela interface de visualização web em http://localhost:37777 → Settings.
Veja **[Documentação de Recursos Beta](https://docs.claude-mem.ai/beta-features)** para detalhes sobre o Endless Mode e como experimentá-lo.
---
## Requisitos do Sistema
- **Node.js**: 18.0.0 ou superior
- **Claude Code**: Versão mais recente com suporte a plugins
- **Bun**: Runtime JavaScript e gerenciador de processos (instalado automaticamente se ausente)
- **uv**: Gerenciador de pacotes Python para busca vetorial (instalado automaticamente se ausente)
- **SQLite 3**: Para armazenamento persistente (incluído)
---
## Configuração
As configurações são gerenciadas em `~/.claude-mem/settings.json` (criado automaticamente com valores padrão na primeira execução). Configure modelo de IA, porta do worker, diretório de dados, nível de log e configurações de injeção de contexto.
Veja o **[Guia de Configuração](https://docs.claude-mem.ai/configuration)** para todas as configurações disponíveis e exemplos.
---
## Desenvolvimento
Veja o **[Guia de Desenvolvimento](https://docs.claude-mem.ai/development)** para instruções de build, testes e fluxo de contribuição.
---
## Solução de Problemas
Se você estiver enfrentando problemas, descreva o problema para Claude e a skill troubleshoot diagnosticará automaticamente e fornecerá correções.
Veja o **[Guia de Solução de Problemas](https://docs.claude-mem.ai/troubleshooting)** para problemas comuns e soluções.
---
## Relatos de Bug
Crie relatos de bug abrangentes com o gerador automatizado:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Contribuindo
Contribuições são bem-vindas! Por favor:
1. Faça um fork do repositório
2. Crie uma branch de feature
3. Faça suas alterações com testes
4. Atualize a documentação
5. Envie um Pull Request
Veja [Guia de Desenvolvimento](https://docs.claude-mem.ai/development) para o fluxo de contribuição.
---
## Licença
Este projeto está licenciado sob a **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Todos os direitos reservados.
Veja o arquivo [LICENSE](LICENSE) para detalhes completos.
**O Que Isso Significa:**
- Você pode usar, modificar e distribuir este software livremente
- Se você modificar e implantar em um servidor de rede, você deve disponibilizar seu código-fonte
- Trabalhos derivados também devem ser licenciados sob AGPL-3.0
- NÃO HÁ GARANTIA para este software
**Nota sobre Ragtime**: O diretório `ragtime/` é licenciado separadamente sob a **PolyForm Noncommercial License 1.0.0**. Veja [ragtime/LICENSE](ragtime/LICENSE) para detalhes.
---
## Suporte
- **Documentação**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repositório**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autor**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Construído com Claude Agent SDK** | **Desenvolvido por Claude Code** | **Feito com TypeScript**

302
docs/i18n/README.ro.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Aceasta este o traducere automată. Corecțiile din partea comunității sunt binevenite!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Sistem persistent de compresie a memoriei construit pentru <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#start-rapid">Start Rapid</a> •
<a href="#cum-funcționează">Cum Funcționează</a> •
<a href="#instrumente-de-căutare-mcp">Instrumente de Căutare</a> •
<a href="#documentație">Documentație</a> •
<a href="#configurare">Configurare</a> •
<a href="#depanare">Depanare</a> •
<a href="#licență">Licență</a>
</p>
<p align="center">
Claude-Mem păstrează contextul fără întrerupere între sesiuni prin capturarea automată a observațiilor de utilizare a instrumentelor, generarea de rezumate semantice și punerea lor la dispoziție în sesiunile viitoare. Aceasta permite lui Claude să mențină continuitatea cunoștințelor despre proiecte chiar și după încheierea sau reconectarea sesiunilor.
</p>
---
## Start Rapid
Porniți o nouă sesiune Claude Code în terminal și introduceți următoarele comenzi:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Reporniți Claude Code. Contextul din sesiunile anterioare va apărea automat în sesiunile noi.
**Caracteristici Principale:**
- 🧠 **Memorie Persistentă** - Contextul supraviețuiește între sesiuni
- 📊 **Dezvăluire Progresivă** - Recuperare stratificată a memoriei cu vizibilitatea costurilor în tokeni
- 🔍 **Căutare Bazată pe Abilități** - Interogați istoricul proiectului cu abilitatea mem-search
- 🖥️ **Interfață Web Viewer** - Flux de memorie în timp real la http://localhost:37777
- 💻 **Abilitate Claude Desktop** - Căutați în memorie din conversațiile Claude Desktop
- 🔒 **Control al Confidențialității** - Utilizați etichete `<private>` pentru a exclude conținut sensibil de la stocare
- ⚙️ **Configurare Context** - Control fin asupra contextului care este injectat
- 🤖 **Operare Automată** - Nu necesită intervenție manuală
- 🔗 **Citări** - Referință la observații anterioare cu ID-uri (accesați prin http://localhost:37777/api/observation/{id} sau vizualizați toate în web viewer la http://localhost:37777)
- 🧪 **Canal Beta** - Încercați funcții experimentale precum Endless Mode prin comutarea versiunii
---
## Documentație
📚 **[Vizualizați Documentația Completă](docs/)** - Răsfoiți documentele markdown pe GitHub
### Introducere
- **[Ghid de Instalare](https://docs.claude-mem.ai/installation)** - Start rapid și instalare avansată
- **[Ghid de Utilizare](https://docs.claude-mem.ai/usage/getting-started)** - Cum funcționează Claude-Mem automat
- **[Instrumente de Căutare](https://docs.claude-mem.ai/usage/search-tools)** - Interogați istoricul proiectului cu limbaj natural
- **[Funcții Beta](https://docs.claude-mem.ai/beta-features)** - Încercați funcții experimentale precum Endless Mode
### Practici Recomandate
- **[Inginerie Context](https://docs.claude-mem.ai/context-engineering)** - Principii de optimizare a contextului pentru agenți AI
- **[Dezvăluire Progresivă](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofia din spatele strategiei de pregătire a contextului Claude-Mem
### Arhitectură
- **[Prezentare Generală](https://docs.claude-mem.ai/architecture/overview)** - Componente de sistem și flux de date
- **[Evoluția Arhitecturii](https://docs.claude-mem.ai/architecture-evolution)** - Parcursul de la v3 la v5
- **[Arhitectura Hooks](https://docs.claude-mem.ai/hooks-architecture)** - Cum folosește Claude-Mem hook-urile de ciclu de viață
- **[Referință Hooks](https://docs.claude-mem.ai/architecture/hooks)** - 7 scripturi de hook explicate
- **[Serviciu Worker](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API și gestionare Bun
- **[Baza de Date](https://docs.claude-mem.ai/architecture/database)** - Schemă SQLite și căutare FTS5
- **[Arhitectura Căutării](https://docs.claude-mem.ai/architecture/search-architecture)** - Căutare hibridă cu baza de date vectorială Chroma
### Configurare și Dezvoltare
- **[Configurare](https://docs.claude-mem.ai/configuration)** - Variabile de mediu și setări
- **[Dezvoltare](https://docs.claude-mem.ai/development)** - Construire, testare, contribuție
- **[Depanare](https://docs.claude-mem.ai/troubleshooting)** - Probleme comune și soluții
---
## Cum Funcționează
**Componente Principale:**
1. **5 Hook-uri de Ciclu de Viață** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 scripturi de hook)
2. **Instalare Inteligentă** - Verificator de dependențe în cache (script pre-hook, nu un hook de ciclu de viață)
3. **Serviciu Worker** - HTTP API pe portul 37777 cu interfață web viewer și 10 endpoint-uri de căutare, gestionat de Bun
4. **Bază de Date SQLite** - Stochează sesiuni, observații, rezumate
5. **Abilitatea mem-search** - Interogări în limbaj natural cu dezvăluire progresivă
6. **Bază de Date Vectorială Chroma** - Căutare hibridă semantică + cuvinte cheie pentru recuperare inteligentă a contextului
Consultați [Prezentarea Generală a Arhitecturii](https://docs.claude-mem.ai/architecture/overview) pentru detalii.
---
## Abilitatea mem-search
Claude-Mem oferă căutare inteligentă prin abilitatea mem-search care se invocă automat când întrebați despre lucrul trecut:
**Cum Funcționează:**
- Întrebați natural: *"Ce am făcut în sesiunea trecută?"* sau *"Am rezolvat acest bug înainte?"*
- Claude invocă automat abilitatea mem-search pentru a găsi contextul relevant
**Operații de Căutare Disponibile:**
1. **Search Observations** - Căutare full-text în observații
2. **Search Sessions** - Căutare full-text în rezumatele sesiunilor
3. **Search Prompts** - Căutare în cererile brute ale utilizatorilor
4. **By Concept** - Găsire după etichete de concept (discovery, problem-solution, pattern, etc.)
5. **By File** - Găsire de observații care fac referire la fișiere specifice
6. **By Type** - Găsire după tip (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Obținere context recent al sesiunii pentru un proiect
8. **Timeline** - Obținere cronologie unificată a contextului în jurul unui punct specific în timp
9. **Timeline by Query** - Căutare observații și obținere context cronologic în jurul celei mai bune potriviri
10. **API Help** - Obținere documentație API de căutare
**Exemple de Interogări în Limbaj Natural:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Consultați [Ghidul Instrumentelor de Căutare](https://docs.claude-mem.ai/usage/search-tools) pentru exemple detaliate.
---
## Funcții Beta
Claude-Mem oferă un **canal beta** cu funcții experimentale precum **Endless Mode** (arhitectură de memorie biomimetică pentru sesiuni extinse). Comutați între versiunile stabile și beta din interfața web viewer la http://localhost:37777 → Settings.
Consultați **[Documentația Funcțiilor Beta](https://docs.claude-mem.ai/beta-features)** pentru detalii despre Endless Mode și cum să îl încercați.
---
## Cerințe de Sistem
- **Node.js**: 18.0.0 sau superior
- **Claude Code**: Versiunea cea mai recentă cu suport pentru plugin-uri
- **Bun**: Runtime JavaScript și manager de procese (instalat automat dacă lipsește)
- **uv**: Manager de pachete Python pentru căutare vectorială (instalat automat dacă lipsește)
- **SQLite 3**: Pentru stocare persistentă (inclus)
---
## Configurare
Setările sunt gestionate în `~/.claude-mem/settings.json` (creat automat cu valori implicite la prima rulare). Configurați modelul AI, portul worker, directorul de date, nivelul de log și setările de injectare a contextului.
Consultați **[Ghidul de Configurare](https://docs.claude-mem.ai/configuration)** pentru toate setările disponibile și exemple.
---
## Dezvoltare
Consultați **[Ghidul de Dezvoltare](https://docs.claude-mem.ai/development)** pentru instrucțiuni de construire, testare și flux de contribuție.
---
## Depanare
Dacă întâmpinați probleme, descrieți problema lui Claude și abilitatea troubleshoot va diagnostica automat și va furniza soluții.
Consultați **[Ghidul de Depanare](https://docs.claude-mem.ai/troubleshooting)** pentru probleme comune și soluții.
---
## Rapoarte de Bug-uri
Creați rapoarte comprehensive de bug-uri cu generatorul automat:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Contribuție
Contribuțiile sunt binevenite! Vă rugăm:
1. Faceți fork la repository
2. Creați o ramură de funcție
3. Faceți modificările cu teste
4. Actualizați documentația
5. Trimiteți un Pull Request
Consultați [Ghidul de Dezvoltare](https://docs.claude-mem.ai/development) pentru fluxul de contribuție.
---
## Licență
Acest proiect este licențiat sub **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Toate drepturile rezervate.
Consultați fișierul [LICENSE](LICENSE) pentru detalii complete.
**Ce Înseamnă Asta:**
- Puteți folosi, modifica și distribui acest software liber
- Dacă modificați și implementați pe un server de rețea, trebuie să faceți disponibil codul sursă
- Lucrările derivate trebuie să fie licențiate și ele sub AGPL-3.0
- NU EXISTĂ NICIO GARANȚIE pentru acest software
**Notă despre Ragtime**: Directorul `ragtime/` este licențiat separat sub **PolyForm Noncommercial License 1.0.0**. Consultați [ragtime/LICENSE](ragtime/LICENSE) pentru detalii.
---
## Suport
- **Documentație**: [docs/](docs/)
- **Probleme**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Autor**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Construit cu Claude Agent SDK** | **Alimentat de Claude Code** | **Realizat cu TypeScript**

302
docs/i18n/README.ru.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Это автоматический перевод. Приветствуются исправления от сообщества!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Система сжатия постоянной памяти, созданная для <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#быстрый-старт">Быстрый старт</a> •
<a href="#как-это-работает">Как это работает</a> •
<a href="#инструменты-поиска-mcp">Инструменты поиска</a> •
<a href="#документация">Документация</a> •
<a href="#конфигурация">Конфигурация</a> •
<a href="#устранение-неполадок">Устранение неполадок</a> •
<a href="#лицензия">Лицензия</a>
</p>
<p align="center">
Claude-Mem бесшовно сохраняет контекст между сеансами, автоматически фиксируя наблюдения за использованием инструментов, генерируя семантические сводки и делая их доступными для будущих сеансов. Это позволяет Claude поддерживать непрерывность знаний о проектах даже после завершения или переподключения сеансов.
</p>
---
## Быстрый старт
Запустите новый сеанс Claude Code в терминале и введите следующие команды:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Перезапустите Claude Code. Контекст из предыдущих сеансов будет автоматически появляться в новых сеансах.
**Ключевые возможности:**
- 🧠 **Постоянная память** - Контекст сохраняется между сеансами
- 📊 **Прогрессивное раскрытие** - Многоуровневое извлечение памяти с видимостью стоимости токенов
- 🔍 **Поиск на основе навыков** - Запросы к истории проекта с помощью навыка mem-search
- 🖥️ **Веб-интерфейс просмотра** - Поток памяти в реальном времени на http://localhost:37777
- 💻 **Навык для Claude Desktop** - Поиск в памяти из разговоров Claude Desktop
- 🔒 **Контроль конфиденциальности** - Используйте теги `<private>` для исключения конфиденциального контента из хранилища
- ⚙️ **Настройка контекста** - Детальный контроль того, какой контекст внедряется
- 🤖 **Автоматическая работа** - Не требуется ручное вмешательство
- 🔗 **Цитирование** - Ссылки на прошлые наблюдения с помощью ID (доступ через http://localhost:37777/api/observation/{id} или просмотр всех в веб-интерфейсе на http://localhost:37777)
- 🧪 **Бета-канал** - Попробуйте экспериментальные функции, такие как режим Endless, переключая версии
---
## Документация
📚 **[Просмотреть полную документацию](docs/)** - Просмотр markdown-документов на GitHub
### Начало работы
- **[Руководство по установке](https://docs.claude-mem.ai/installation)** - Быстрый старт и продвинутая установка
- **[Руководство по использованию](https://docs.claude-mem.ai/usage/getting-started)** - Как Claude-Mem работает автоматически
- **[Инструменты поиска](https://docs.claude-mem.ai/usage/search-tools)** - Запросы к истории проекта на естественном языке
- **[Бета-функции](https://docs.claude-mem.ai/beta-features)** - Попробуйте экспериментальные функции, такие как режим Endless
### Лучшие практики
- **[Инженерия контекста](https://docs.claude-mem.ai/context-engineering)** - Принципы оптимизации контекста для AI-агентов
- **[Прогрессивное раскрытие](https://docs.claude-mem.ai/progressive-disclosure)** - Философия стратегии подготовки контекста в Claude-Mem
### Архитектура
- **[Обзор](https://docs.claude-mem.ai/architecture/overview)** - Компоненты системы и поток данных
- **[Эволюция архитектуры](https://docs.claude-mem.ai/architecture-evolution)** - Путь от v3 к v5
- **[Архитектура хуков](https://docs.claude-mem.ai/hooks-architecture)** - Как Claude-Mem использует хуки жизненного цикла
- **[Справочник по хукам](https://docs.claude-mem.ai/architecture/hooks)** - Объяснение 7 скриптов хуков
- **[Сервис Worker](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API и управление Bun
- **[База данных](https://docs.claude-mem.ai/architecture/database)** - Схема SQLite и поиск FTS5
- **[Архитектура поиска](https://docs.claude-mem.ai/architecture/search-architecture)** - Гибридный поиск с векторной базой данных Chroma
### Конфигурация и разработка
- **[Конфигурация](https://docs.claude-mem.ai/configuration)** - Переменные окружения и настройки
- **[Разработка](https://docs.claude-mem.ai/development)** - Сборка, тестирование, участие в разработке
- **[Устранение неполадок](https://docs.claude-mem.ai/troubleshooting)** - Распространенные проблемы и решения
---
## Как это работает
**Основные компоненты:**
1. **5 хуков жизненного цикла** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 скриптов хуков)
2. **Умная установка** - Проверка кешированных зависимостей (скрипт предварительного хука, не является хуком жизненного цикла)
3. **Сервис Worker** - HTTP API на порту 37777 с веб-интерфейсом просмотра и 10 конечными точками поиска, управляемый Bun
4. **База данных SQLite** - Хранит сеансы, наблюдения, сводки
5. **Навык mem-search** - Запросы на естественном языке с прогрессивным раскрытием
6. **Векторная база данных Chroma** - Гибридный семантический + ключевой поиск для интеллектуального извлечения контекста
Подробности см. в [Обзоре архитектуры](https://docs.claude-mem.ai/architecture/overview).
---
## Навык mem-search
Claude-Mem предоставляет интеллектуальный поиск через навык mem-search, который автоматически вызывается, когда вы спрашиваете о прошлой работе:
**Как это работает:**
- Просто спросите естественно: *"Что мы делали в прошлом сеансе?"* или *"Мы исправляли этот баг раньше?"*
- Claude автоматически вызывает навык mem-search для поиска релевантного контекста
**Доступные операции поиска:**
1. **Поиск наблюдений** - Полнотекстовый поиск по наблюдениям
2. **Поиск сеансов** - Полнотекстовый поиск по сводкам сеансов
3. **Поиск запросов** - Поиск исходных пользовательских запросов
4. **По концепции** - Поиск по тегам концепций (discovery, problem-solution, pattern и т.д.)
5. **По файлу** - Поиск наблюдений, ссылающихся на конкретные файлы
6. **По типу** - Поиск по типу (decision, bugfix, feature, refactor, discovery, change)
7. **Недавний контекст** - Получение недавнего контекста сеанса для проекта
8. **Хронология** - Получение единой хронологии контекста вокруг определенного момента времени
9. **Хронология по запросу** - Поиск наблюдений и получение контекста хронологии вокруг наилучшего совпадения
10. **Справка по API** - Получение документации по API поиска
**Примеры запросов на естественном языке:**
```
"Какие баги мы исправили в прошлом сеансе?"
"Как мы реализовали аутентификацию?"
"Какие изменения были внесены в worker-service.ts?"
"Покажи недавнюю работу над этим проектом"
"Что происходило, когда мы добавляли интерфейс просмотра?"
```
Подробные примеры см. в [Руководстве по инструментам поиска](https://docs.claude-mem.ai/usage/search-tools).
---
## Бета-функции
Claude-Mem предлагает **бета-канал** с экспериментальными функциями, такими как **режим Endless** (биомиметическая архитектура памяти для расширенных сеансов). Переключайтесь между стабильной и бета-версиями из веб-интерфейса на http://localhost:37777 → Settings.
Подробности о режиме Endless и способах его опробовать см. в **[Документации по бета-функциям](https://docs.claude-mem.ai/beta-features)**.
---
## Системные требования
- **Node.js**: 18.0.0 или выше
- **Claude Code**: Последняя версия с поддержкой плагинов
- **Bun**: Среда выполнения JavaScript и менеджер процессов (автоматически устанавливается при отсутствии)
- **uv**: Менеджер пакетов Python для векторного поиска (автоматически устанавливается при отсутствии)
- **SQLite 3**: Для постоянного хранения (встроенный)
---
## Конфигурация
Настройки управляются в `~/.claude-mem/settings.json` (автоматически создается с настройками по умолчанию при первом запуске). Настройте AI-модель, порт worker, директорию данных, уровень логирования и параметры внедрения контекста.
Все доступные настройки и примеры см. в **[Руководстве по конфигурации](https://docs.claude-mem.ai/configuration)**.
---
## Разработка
Инструкции по сборке, тестированию и процессу участия в разработке см. в **[Руководстве по разработке](https://docs.claude-mem.ai/development)**.
---
## Устранение неполадок
При возникновении проблем опишите проблему Claude, и навык устранения неполадок автоматически выполнит диагностику и предоставит исправления.
Распространенные проблемы и решения см. в **[Руководстве по устранению неполадок](https://docs.claude-mem.ai/troubleshooting)**.
---
## Отчеты об ошибках
Создавайте подробные отчеты об ошибках с помощью автоматического генератора:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Участие в разработке
Приветствуются вклады! Пожалуйста:
1. Форкните репозиторий
2. Создайте ветку для функции
3. Внесите изменения с тестами
4. Обновите документацию
5. Отправьте Pull Request
Процесс участия см. в [Руководстве по разработке](https://docs.claude-mem.ai/development).
---
## Лицензия
Этот проект лицензирован под **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Все права защищены.
Полные сведения см. в файле [LICENSE](LICENSE).
**Что это означает:**
- Вы можете свободно использовать, модифицировать и распространять это программное обеспечение
- Если вы модифицируете и развертываете на сетевом сервере, вы должны сделать свой исходный код доступным
- Производные работы также должны быть лицензированы под AGPL-3.0
- Для этого программного обеспечения НЕТ ГАРАНТИЙ
**Примечание о Ragtime**: Директория `ragtime/` лицензирована отдельно под **PolyForm Noncommercial License 1.0.0**. Подробности см. в [ragtime/LICENSE](ragtime/LICENSE).
---
## Поддержка
- **Документация**: [docs/](docs/)
- **Проблемы**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Репозиторий**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Автор**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Создано с помощью Claude Agent SDK** | **Работает на Claude Code** | **Сделано на TypeScript**

302
docs/i18n/README.sv.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Detta är en automatiserad översättning. Bidrag från gemenskapen är välkomna!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Persistent minneskomprimeringsystem byggt för <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#snabbstart">Snabbstart</a> •
<a href="#hur-det-fungerar">Hur det fungerar</a> •
<a href="#sökverktyg-mcp">Sökverktyg</a> •
<a href="#dokumentation">Dokumentation</a> •
<a href="#konfiguration">Konfiguration</a> •
<a href="#felsökning">Felsökning</a> •
<a href="#licens">Licens</a>
</p>
<p align="center">
Claude-Mem bevarar sömlöst kontext mellan sessioner genom att automatiskt fånga observationer av verktygsanvändning, generera semantiska sammanfattningar och göra dem tillgängliga för framtida sessioner. Detta gör det möjligt för Claude att upprätthålla kontinuitet i kunskap om projekt även efter att sessioner avslutas eller återansluter.
</p>
---
## Snabbstart
Starta en ny Claude Code-session i terminalen och ange följande kommandon:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Starta om Claude Code. Kontext från tidigare sessioner kommer automatiskt att visas i nya sessioner.
**Nyckelfunktioner:**
- 🧠 **Persistent minne** - Kontext överlever mellan sessioner
- 📊 **Progressiv visning** - Skiktad minneshämtning med synlighet för tokenkostnad
- 🔍 **Färdighetsbaserad sökning** - Sök i din projekthistorik med mem-search-färdigheten
- 🖥️ **Webbvy-gränssnitt** - Realtidsminnesström på http://localhost:37777
- 💻 **Claude Desktop-färdighet** - Sök i minnet från Claude Desktop-konversationer
- 🔒 **Integritetskontroll** - Använd `<private>`-taggar för att exkludera känsligt innehåll från lagring
- ⚙️ **Kontextkonfiguration** - Detaljerad kontroll över vilken kontext som injiceras
- 🤖 **Automatisk drift** - Ingen manuell hantering krävs
- 🔗 **Citeringar** - Referera till tidigare observationer med ID:n (tillgängliga via http://localhost:37777/api/observation/{id} eller visa alla i webbvyn på http://localhost:37777)
- 🧪 **Betakanal** - Testa experimentella funktioner som Endless Mode via versionsväxling
---
## Dokumentation
📚 **[Visa fullständig dokumentation](docs/)** - Bläddra bland markdown-dokument på GitHub
### Komma igång
- **[Installationsguide](https://docs.claude-mem.ai/installation)** - Snabbstart och avancerad installation
- **[Användarguide](https://docs.claude-mem.ai/usage/getting-started)** - Hur Claude-Mem fungerar automatiskt
- **[Sökverktyg](https://docs.claude-mem.ai/usage/search-tools)** - Sök i din projekthistorik med naturligt språk
- **[Betafunktioner](https://docs.claude-mem.ai/beta-features)** - Testa experimentella funktioner som Endless Mode
### Bästa praxis
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - Optimeringsmetoder för AI-agentkontext
- **[Progressiv visning](https://docs.claude-mem.ai/progressive-disclosure)** - Filosofin bakom Claude-Mems kontextpriming-strategi
### Arkitektur
- **[Översikt](https://docs.claude-mem.ai/architecture/overview)** - Systemkomponenter och dataflöde
- **[Arkitekturutveckling](https://docs.claude-mem.ai/architecture-evolution)** - Resan från v3 till v5
- **[Hooks-arkitektur](https://docs.claude-mem.ai/hooks-architecture)** - Hur Claude-Mem använder livscykelkrokar
- **[Hooks-referens](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook-skript förklarade
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API och Bun-hantering
- **[Databas](https://docs.claude-mem.ai/architecture/database)** - SQLite-schema och FTS5-sökning
- **[Sökarkitektur](https://docs.claude-mem.ai/architecture/search-architecture)** - Hybridsökning med Chroma-vektordatabas
### Konfiguration och utveckling
- **[Konfiguration](https://docs.claude-mem.ai/configuration)** - Miljövariabler och inställningar
- **[Utveckling](https://docs.claude-mem.ai/development)** - Bygga, testa, bidra
- **[Felsökning](https://docs.claude-mem.ai/troubleshooting)** - Vanliga problem och lösningar
---
## Hur det fungerar
**Kärnkomponenter:**
1. **5 livscykelkrokar** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook-skript)
2. **Smart installation** - Cachad beroendekontrollant (pre-hook-skript, inte en livscykelkrok)
3. **Worker Service** - HTTP API på port 37777 med webbvy-gränssnitt och 10 sökändpunkter, hanterat av Bun
4. **SQLite-databas** - Lagrar sessioner, observationer, sammanfattningar
5. **mem-search-färdighet** - Naturligspråkssökningar med progressiv visning
6. **Chroma-vektordatabas** - Hybrid semantisk + nyckelordssökning för intelligent kontexthämtning
Se [Arkitekturöversikt](https://docs.claude-mem.ai/architecture/overview) för detaljer.
---
## mem-search-färdighet
Claude-Mem tillhandahåller intelligent sökning genom mem-search-färdigheten som automatiskt aktiveras när du frågar om tidigare arbete:
**Hur det fungerar:**
- Fråga bara naturligt: *"Vad gjorde vi förra sessionen?"* eller *"Fixade vi den här buggen tidigare?"*
- Claude aktiverar automatiskt mem-search-färdigheten för att hitta relevant kontext
**Tillgängliga sökoperationer:**
1. **Search Observations** - Fulltextsökning över observationer
2. **Search Sessions** - Fulltextsökning över sessionssammanfattningar
3. **Search Prompts** - Sök i råa användarförfrågningar
4. **By Concept** - Hitta efter koncepttaggar (discovery, problem-solution, pattern, etc.)
5. **By File** - Hitta observationer som refererar till specifika filer
6. **By Type** - Hitta efter typ (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Hämta senaste sessionskontext för ett projekt
8. **Timeline** - Få en enhetlig tidslinje av kontext kring en specifik tidpunkt
9. **Timeline by Query** - Sök efter observationer och få tidslinjekontext kring bästa matchning
10. **API Help** - Få API-dokumentation för sökning
**Exempel på naturligspråkssökningar:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Se [Sökverktygsguide](https://docs.claude-mem.ai/usage/search-tools) för detaljerade exempel.
---
## Betafunktioner
Claude-Mem erbjuder en **betakanal** med experimentella funktioner som **Endless Mode** (biomimetisk minnesarkitektur för utökade sessioner). Växla mellan stabila och betaversioner från webbvy-gränssnittet på http://localhost:37777 → Settings.
Se **[Dokumentation för betafunktioner](https://docs.claude-mem.ai/beta-features)** för detaljer om Endless Mode och hur du testar det.
---
## Systemkrav
- **Node.js**: 18.0.0 eller högre
- **Claude Code**: Senaste versionen med plugin-stöd
- **Bun**: JavaScript-runtime och processhanterare (installeras automatiskt om den saknas)
- **uv**: Python-pakethanterare för vektorsökning (installeras automatiskt om den saknas)
- **SQLite 3**: För persistent lagring (ingår)
---
## Konfiguration
Inställningar hanteras i `~/.claude-mem/settings.json` (skapas automatiskt med standardvärden vid första körning). Konfigurera AI-modell, worker-port, datakatalog, loggnivå och kontextinjektionsinställningar.
Se **[Konfigurationsguide](https://docs.claude-mem.ai/configuration)** för alla tillgängliga inställningar och exempel.
---
## Utveckling
Se **[Utvecklingsguide](https://docs.claude-mem.ai/development)** för bygginstruktioner, testning och bidragsarbetsflöde.
---
## Felsökning
Om du upplever problem, beskriv problemet för Claude och felsökningsfärdigheten kommer automatiskt att diagnostisera och tillhandahålla lösningar.
Se **[Felsökningsguide](https://docs.claude-mem.ai/troubleshooting)** för vanliga problem och lösningar.
---
## Buggrapporter
Skapa omfattande buggrapporter med den automatiserade generatorn:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Bidrag
Bidrag är välkomna! Vänligen:
1. Forka repositoryt
2. Skapa en feature-gren
3. Gör dina ändringar med tester
4. Uppdatera dokumentationen
5. Skicka in en Pull Request
Se [Utvecklingsguide](https://docs.claude-mem.ai/development) för bidragsarbetsflöde.
---
## Licens
Detta projekt är licensierat under **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Alla rättigheter förbehållna.
Se [LICENSE](LICENSE)-filen för fullständiga detaljer.
**Vad detta betyder:**
- Du kan använda, modifiera och distribuera denna programvara fritt
- Om du modifierar och distribuerar på en nätverksserver måste du göra din källkod tillgänglig
- Härledda verk måste också licensieras under AGPL-3.0
- Det finns INGEN GARANTI för denna programvara
**Notering om Ragtime**: Katalogen `ragtime/` är licensierad separat under **PolyForm Noncommercial License 1.0.0**. Se [ragtime/LICENSE](ragtime/LICENSE) för detaljer.
---
## Support
- **Dokumentation**: [docs/](docs/)
- **Problem**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Författare**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Byggd med Claude Agent SDK** | **Drivs av Claude Code** | **Skapad med TypeScript**

301
docs/i18n/README.th.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 นี่คือการแปลอัตโนมัติ ยินดีต้อนรับการแก้ไขจากชุมชน!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">ระบบการบีบอัดหน่วยความจำถาวรที่สร้างขึ้นสำหรับ <a href="https://claude.com/claude-code" target="_blank">Claude Code</a></h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#quick-start">เริ่มต้นอย่างรวดเร็ว</a> •
<a href="#how-it-works">วิธีการทำงาน</a> •
<a href="#mcp-search-tools">เครื่องมือค้นหา</a> •
<a href="#documentation">เอกสาร</a> •
<a href="#configuration">การกำหนดค่า</a> •
<a href="#troubleshooting">การแก้ไขปัญหา</a> •
<a href="#license">ใบอนุญาต</a>
</p>
<p align="center">
Claude-Mem รักษาบริบทข้ามเซสชันได้อย่างราบรื่นโดยการบันทึกผลการสังเกตจากการใช้เครื่องมือโดยอัตโนมัติ สร้างสรุปความหมาย และทำให้พร้อมใช้งานสำหรับเซสชันในอนาคต ทำให้ Claude สามารถรักษาความต่อเนื่องของความรู้เกี่ยวกับโปรเจกต์แม้หลังจากเซสชันสิ้นสุดหรือเชื่อมต่อใหม่
</p>
---
## เริ่มต้นอย่างรวดเร็ว
เริ่มเซสชัน Claude Code ใหม่ในเทอร์มินัลและป้อนคำสั่งต่อไปนี้:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
รีสตาร์ท Claude Code บริบทจากเซสชันก่อนหน้าจะปรากฏในเซสชันใหม่โดยอัตโนมัติ
**คุณสมบัติหลัก:**
- 🧠 **หน่วยความจำถาวร** - บริบทยังคงอยู่ข้ามเซสชัน
- 📊 **การเปิดเผยแบบก้าวหน้า** - การดึงหน่วยความจำแบบชั้นพร้อมการแสดงต้นทุนโทเค็น
- 🔍 **การค้นหาตามทักษะ** - สืบค้นประวัติโปรเจกต์ของคุณด้วยทักษะ mem-search
- 🖥️ **Web Viewer UI** - สตรีมหน่วยความจำแบบเรียลไทม์ที่ http://localhost:37777
- 💻 **Claude Desktop Skill** - ค้นหาหน่วยความจำจากการสนทนา Claude Desktop
- 🔒 **การควบคุมความเป็นส่วนตัว** - ใช้แท็ก `<private>` เพื่อยกเว้นเนื้อหาที่ละเอียดอ่อนจากการจัดเก็บ
- ⚙️ **การกำหนดค่าบริบท** - ควบคุมบริบทที่ถูกฉีดเข้ามาได้อย่างละเอียด
- 🤖 **การทำงานอัตโนมัติ** - ไม่ต้องแทรกแซงด้วยตนเอง
- 🔗 **การอ้างอิง** - อ้างอิงการสังเกตในอดีตด้วย ID (เข้าถึงผ่าน http://localhost:37777/api/observation/{id} หรือดูทั้งหมดใน web viewer ที่ http://localhost:37777)
- 🧪 **Beta Channel** - ลองคุณสมบัติทดลองเช่น Endless Mode ผ่านการสลับเวอร์ชัน
---
## เอกสาร
📚 **[ดูเอกสารฉบับเต็ม](docs/)** - เรียกดูเอกสาร markdown บน GitHub
### เริ่มต้นใช้งาน
- **[คู่มือการติดตั้ง](https://docs.claude-mem.ai/installation)** - เริ่มต้นอย่างรวดเร็วและการติดตั้งขั้นสูง
- **[คู่มือการใช้งาน](https://docs.claude-mem.ai/usage/getting-started)** - วิธีที่ Claude-Mem ทำงานโดยอัตโนมัติ
- **[เครื่องมือค้นหา](https://docs.claude-mem.ai/usage/search-tools)** - สืบค้นประวัติโปรเจกต์ของคุณด้วยภาษาธรรมชาติ
- **[คุณสมบัติ Beta](https://docs.claude-mem.ai/beta-features)** - ลองคุณสมบัติทดลองเช่น Endless Mode
### แนวปฏิบัติที่ดี
- **[Context Engineering](https://docs.claude-mem.ai/context-engineering)** - หลักการปรับบริบทสำหรับเอเจนต์ AI
- **[Progressive Disclosure](https://docs.claude-mem.ai/progressive-disclosure)** - ปรัชญาเบื้องหลังกลยุทธ์การเตรียมบริบทของ Claude-Mem
### สถาปัตยกรรม
- **[ภาพรวม](https://docs.claude-mem.ai/architecture/overview)** - ส่วนประกอบของระบบและการไหลของข้อมูล
- **[วิวัฒนาการของสถาปัตยกรรม](https://docs.claude-mem.ai/architecture-evolution)** - การเดินทางจาก v3 สู่ v5
- **[สถาปัตยกรรม Hooks](https://docs.claude-mem.ai/hooks-architecture)** - วิธีที่ Claude-Mem ใช้ lifecycle hooks
- **[การอ้างอิง Hooks](https://docs.claude-mem.ai/architecture/hooks)** - อธิบาย hook scripts ทั้ง 7 ตัว
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API และการจัดการ Bun
- **[ฐานข้อมูล](https://docs.claude-mem.ai/architecture/database)** - SQLite schema และการค้นหา FTS5
- **[สถาปัตยกรรมการค้นหา](https://docs.claude-mem.ai/architecture/search-architecture)** - การค้นหาแบบไฮบริดด้วยฐานข้อมูลเวกเตอร์ Chroma
### การกำหนดค่าและการพัฒนา
- **[การกำหนดค่า](https://docs.claude-mem.ai/configuration)** - ตัวแปรสภาพแวดล้อมและการตั้งค่า
- **[การพัฒนา](https://docs.claude-mem.ai/development)** - การสร้าง การทดสอบ การมีส่วนร่วม
- **[การแก้ไขปัญหา](https://docs.claude-mem.ai/troubleshooting)** - ปัญหาและการแก้ไขทั่วไป
---
## วิธีการทำงาน
**ส่วนประกอบหลัก:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
2. **Smart Install** - ตัวตรวจสอบการพึ่งพาที่ถูกแคช (pre-hook script, ไม่ใช่ lifecycle hook)
3. **Worker Service** - HTTP API บนพอร์ต 37777 พร้อม web viewer UI และ 10 search endpoints, จัดการโดย Bun
4. **SQLite Database** - จัดเก็บเซสชัน การสังเกต สรุป
5. **mem-search Skill** - คิวรีภาษาธรรมชาติพร้อมการเปิดเผยแบบก้าวหน้า
6. **Chroma Vector Database** - การค้นหาแบบไฮบริดทางความหมาย + คีย์เวิร์ดสำหรับการดึงบริบทอัจฉริยะ
ดู [ภาพรวมสถาปัตยกรรม](https://docs.claude-mem.ai/architecture/overview) สำหรับรายละเอียด
---
## ทักษะ mem-search
Claude-Mem ให้บริการการค้นหาอัจฉริยะผ่านทักษะ mem-search ที่เรียกใช้อัตโนมัติเมื่อคุณถามเกี่ยวกับงานที่ผ่านมา:
**วิธีการทำงาน:**
- เพียงถามตามธรรมชาติ: *"เราทำอะไรในเซสชันที่แล้ว?"* หรือ *"เราแก้บั๊กนี้ไปแล้วหรือยัง?"*
- Claude เรียกใช้ทักษะ mem-search โดยอัตโนมัติเพื่อค้นหาบริบทที่เกี่ยวข้อง
**การดำเนินการค้นหาที่มี:**
1. **Search Observations** - การค้นหาข้อความเต็มข้ามการสังเกต
2. **Search Sessions** - การค้นหาข้อความเต็มข้ามสรุปเซสชัน
3. **Search Prompts** - ค้นหาคำขอผู้ใช้แบบดิบ
4. **By Concept** - ค้นหาตามแท็กแนวคิด (discovery, problem-solution, pattern, ฯลฯ)
5. **By File** - ค้นหาการสังเกตที่อ้างอิงไฟล์เฉพาะ
6. **By Type** - ค้นหาตามประเภท (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - รับบริบทเซสชันล่าสุดสำหรับโปรเจกต์
8. **Timeline** - รับไทม์ไลน์รวมของบริบทรอบจุดเวลาเฉพาะ
9. **Timeline by Query** - ค้นหาการสังเกตและรับบริบทไทม์ไลน์รอบการจับคู่ที่ดีที่สุด
10. **API Help** - รับเอกสาร search API
**ตัวอย่างคิวรีภาษาธรรมชาติ:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
ดู [คู่มือเครื่องมือค้นหา](https://docs.claude-mem.ai/usage/search-tools) สำหรับตัวอย่างโดยละเอียด
---
## คุณสมบัติ Beta
Claude-Mem นำเสนอ **beta channel** พร้อมคุณสมบัติทดลองเช่น **Endless Mode** (สถาปัตยกรรมหน่วยความจำแบบชีวมิติสำหรับเซสชันที่ขยายออกไป) สลับระหว่างเวอร์ชันเสถียรและเบต้าจาก web viewer UI ที่ http://localhost:37777 → Settings
ดู **[เอกสารคุณสมบัติ Beta](https://docs.claude-mem.ai/beta-features)** สำหรับรายละเอียดเกี่ยวกับ Endless Mode และวิธีการลอง
---
## ความต้องการของระบบ
- **Node.js**: 18.0.0 หรือสูงกว่า
- **Claude Code**: เวอร์ชันล่าสุดพร้อมการสนับสนุนปลั๊กอิน
- **Bun**: JavaScript runtime และตัวจัดการกระบวนการ (ติดตั้งอัตโนมัติหากไม่มี)
- **uv**: ตัวจัดการแพ็คเกจ Python สำหรับการค้นหาเวกเตอร์ (ติดตั้งอัตโนมัติหากไม่มี)
- **SQLite 3**: สำหรับการจัดเก็บถาวร (รวมอยู่)
---
## การกำหนดค่า
การตั้งค่าจะถูกจัดการใน `~/.claude-mem/settings.json` (สร้างอัตโนมัติพร้อมค่าเริ่มต้นในการรันครั้งแรก) กำหนดค่าโมเดล AI พอร์ต worker ไดเรกทอรีข้อมูล ระดับ log และการตั้งค่าการฉีดบริบท
ดู **[คู่มือการกำหนดค่า](https://docs.claude-mem.ai/configuration)** สำหรับการตั้งค่าทั้งหมดที่มีและตัวอย่าง
---
## การพัฒนา
ดู **[คู่มือการพัฒนา](https://docs.claude-mem.ai/development)** สำหรับคำแนะนำการสร้าง การทดสอบ และขั้นตอนการมีส่วนร่วม
---
## การแก้ไขปัญหา
หากพบปัญหา อธิบายปัญหาให้ Claude ฟังและทักษะ troubleshoot จะวินิจฉัยและให้การแก้ไขโดยอัตโนมัติ
ดู **[คู่มือการแก้ไขปัญหา](https://docs.claude-mem.ai/troubleshooting)** สำหรับปัญหาและการแก้ไขทั่วไป
---
## รายงานบั๊ก
สร้างรายงานบั๊กที่ครอบคลุมด้วยตัวสร้างอัตโนมัติ:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## การมีส่วนร่วม
ยินดีรับการมีส่วนร่วม! กรุณา:
1. Fork repository
2. สร้าง feature branch
3. ทำการเปลี่ยนแปลงพร้อมการทดสอบ
4. อัปเดตเอกสาร
5. ส่ง Pull Request
ดู [คู่มือการพัฒนา](https://docs.claude-mem.ai/development) สำหรับขั้นตอนการมีส่วนร่วม
---
## ใบอนุญาต
โปรเจกต์นี้ได้รับอนุญาตภายใต้ **GNU Affero General Public License v3.0** (AGPL-3.0)
Copyright (C) 2025 Alex Newman (@thedotmack) สงวนลิขสิทธิ์ทั้งหมด
ดูไฟล์ [LICENSE](LICENSE) สำหรับรายละเอียดทั้งหมด
**ความหมาย:**
- คุณสามารถใช้ ดัดแปลง และแจกจ่ายซอฟต์แวร์นี้ได้อย่างอิสระ
- หากคุณดัดแปลงและปรับใช้บนเซิร์ฟเวอร์เครือข่าย คุณต้องทำให้ซอร์สโค้ดของคุณพร้อมใช้งาน
- งานที่เป็นอนุพันธ์ต้องได้รับอนุญาตภายใต้ AGPL-3.0 ด้วย
- ไม่มีการรับประกันสำหรับซอฟต์แวร์นี้
**หมายเหตุเกี่ยวกับ Ragtime**: ไดเรกทอรี `ragtime/` ได้รับอนุญาตแยกต่างหากภายใต้ **PolyForm Noncommercial License 1.0.0** ดู [ragtime/LICENSE](ragtime/LICENSE) สำหรับรายละเอียด
---
## การสนับสนุน
- **เอกสาร**: [docs/](docs/)
- **ปัญหา**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **ผู้เขียน**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**สร้างด้วย Claude Agent SDK** | **ขับเคลื่อนโดย Claude Code** | **สร้างด้วย TypeScript**

301
docs/i18n/README.tr.md Normal file
View File

@@ -0,0 +1,301 @@
🌐 Bu otomatik bir çevirisidir. Topluluk düzeltmeleri memnuniyetle karşılanır!
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center"><a href="https://claude.com/claude-code" target="_blank">Claude Code</a> için geliştirilmiş kalıcı bellek sıkıştırma sistemi.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#hızlı-başlangıç">Hızlı Başlangıç</a> •
<a href="#nasıl-çalışır">Nasıl Çalışır</a> •
<a href="#mcp-arama-araçları">Arama Araçları</a> •
<a href="#dokümantasyon">Dokümantasyon</a> •
<a href="#yapılandırma">Yapılandırma</a> •
<a href="#sorun-giderme">Sorun Giderme</a> •
<a href="#lisans">Lisans</a>
</p>
<p align="center">
Claude-Mem, araç kullanım gözlemlerini otomatik olarak yakalayarak, anlamsal özetler oluşturarak ve bunları gelecekteki oturumlarda kullanılabilir hale getirerek bağlamı oturumlar arası sorunsuzca korur. Bu, Claude'un oturumlar sona erse veya yeniden bağlansa bile projeler hakkındaki bilgi sürekliliğini korumasını sağlar.
</p>
---
## Hızlı Başlangıç
Terminal üzerinden yeni bir Claude Code oturumu başlatın ve aşağıdaki komutları girin:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Claude Code'u yeniden başlatın. Önceki oturumlardaki bağlam otomatik olarak yeni oturumlarda görünecektir.
**Temel Özellikler:**
- 🧠 **Kalıcı Bellek** - Bağlam oturumlar arası hayatta kalır
- 📊 **Aşamalı Açıklama** - Token maliyeti görünürlüğü ile katmanlı bellek erişimi
- 🔍 **Beceri Tabanlı Arama** - mem-search becerisi ile proje geçmişinizi sorgulayın
- 🖥️ **Web Görüntüleyici Arayüzü** - http://localhost:37777 adresinde gerçek zamanlı bellek akışı
- 💻 **Claude Desktop Becerisi** - Claude Desktop konuşmalarından bellek araması yapın
- 🔒 **Gizlilik Kontrolü** - Hassas içeriği depolamadan hariç tutmak için `<private>` etiketlerini kullanın
- ⚙️ **Bağlam Yapılandırması** - Hangi bağlamın enjekte edileceği üzerinde detaylı kontrol
- 🤖 **Otomatik Çalışma** - Manuel müdahale gerektirmez
- 🔗 **Alıntılar** - ID'lerle geçmiş gözlemlere referans verin (http://localhost:37777/api/observation/{id} üzerinden erişin veya http://localhost:37777 adresindeki web görüntüleyicide tümünü görüntüleyin)
- 🧪 **Beta Kanalı** - Sürüm değiştirme yoluyla Endless Mode gibi deneysel özellikleri deneyin
---
## Dokümantasyon
📚 **[Tam Dokümantasyonu Görüntüle](docs/)** - GitHub'da markdown dökümanlarına göz atın
### Başlarken
- **[Kurulum Kılavuzu](https://docs.claude-mem.ai/installation)** - Hızlı başlangıç ve gelişmiş kurulum
- **[Kullanım Kılavuzu](https://docs.claude-mem.ai/usage/getting-started)** - Claude-Mem otomatik olarak nasıl çalışır
- **[Arama Araçları](https://docs.claude-mem.ai/usage/search-tools)** - Doğal dil ile proje geçmişinizi sorgulayın
- **[Beta Özellikleri](https://docs.claude-mem.ai/beta-features)** - Endless Mode gibi deneysel özellikleri deneyin
### En İyi Uygulamalar
- **[Bağlam Mühendisliği](https://docs.claude-mem.ai/context-engineering)** - AI ajan bağlam optimizasyon ilkeleri
- **[Aşamalı Açıklama](https://docs.claude-mem.ai/progressive-disclosure)** - Claude-Mem'in bağlam hazırlama stratejisinin ardındaki felsefe
### Mimari
- **[Genel Bakış](https://docs.claude-mem.ai/architecture/overview)** - Sistem bileşenleri ve veri akışı
- **[Mimari Evrimi](https://docs.claude-mem.ai/architecture-evolution)** - v3'ten v5'e yolculuk
- **[Hooks Mimarisi](https://docs.claude-mem.ai/hooks-architecture)** - Claude-Mem yaşam döngüsü hook'larını nasıl kullanır
- **[Hooks Referansı](https://docs.claude-mem.ai/architecture/hooks)** - 7 hook betiği açıklandı
- **[Worker Servisi](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API ve Bun yönetimi
- **[Veritabanı](https://docs.claude-mem.ai/architecture/database)** - SQLite şeması ve FTS5 arama
- **[Arama Mimarisi](https://docs.claude-mem.ai/architecture/search-architecture)** - Chroma vektör veritabanı ile hibrit arama
### Yapılandırma ve Geliştirme
- **[Yapılandırma](https://docs.claude-mem.ai/configuration)** - Ortam değişkenleri ve ayarlar
- **[Geliştirme](https://docs.claude-mem.ai/development)** - Derleme, test etme, katkıda bulunma
- **[Sorun Giderme](https://docs.claude-mem.ai/troubleshooting)** - Yaygın sorunlar ve çözümler
---
## Nasıl Çalışır
**Temel Bileşenler:**
1. **5 Yaşam Döngüsü Hook'u** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook betiği)
2. **Akıllı Kurulum** - Önbelleğe alınmış bağımlılık kontrolcüsü (ön-hook betiği, yaşam döngüsü hook'u değil)
3. **Worker Servisi** - Web görüntüleyici arayüzü ve 10 arama uç noktası ile 37777 portunda HTTP API, Bun tarafından yönetilir
4. **SQLite Veritabanı** - Oturumları, gözlemleri, özetleri saklar
5. **mem-search Becerisi** - Aşamalı açıklama ile doğal dil sorguları
6. **Chroma Vektör Veritabanı** - Akıllı bağlam erişimi için hibrit anlamsal + anahtar kelime arama
Detaylar için [Mimari Genel Bakış](https://docs.claude-mem.ai/architecture/overview) bölümüne bakın.
---
## mem-search Becerisi
Claude-Mem, geçmiş çalışmalarınız hakkında sorduğunuzda otomatik olarak devreye giren mem-search becerisi aracılığıyla akıllı arama sağlar:
**Nasıl Çalışır:**
- Sadece doğal bir şekilde sorun: *"Geçen oturumda ne yaptık?"* veya *"Bu hatayı daha önce düzelttik mi?"*
- Claude, ilgili bağlamı bulmak için otomatik olarak mem-search becerisini çağırır
**Mevcut Arama İşlemleri:**
1. **Search Observations** - Gözlemler arasında tam metin arama
2. **Search Sessions** - Oturum özetleri arasında tam metin arama
3. **Search Prompts** - Ham kullanıcı isteklerinde arama
4. **By Concept** - Kavram etiketlerine göre bul (discovery, problem-solution, pattern, vb.)
5. **By File** - Belirli dosyalara referans veren gözlemleri bul
6. **By Type** - Türe göre bul (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Bir proje için yakın zamanlı oturum bağlamını al
8. **Timeline** - Belirli bir zaman noktası etrafındaki birleşik bağlam zaman çizelgesini al
9. **Timeline by Query** - Gözlemleri ara ve en iyi eşleşme etrafındaki zaman çizelgesi bağlamını al
10. **API Help** - Arama API dokümantasyonunu al
**Örnek Doğal Dil Sorguları:**
```
"Geçen oturumda hangi hataları düzelttik?"
"Kimlik doğrulamayı nasıl uyguladık?"
"worker-service.ts dosyasında hangi değişiklikler yapıldı?"
"Bu projedeki son çalışmaları göster"
"Görüntüleyici arayüzünü eklediğimizde ne oluyordu?"
```
Detaylı örnekler için [Arama Araçları Kılavuzu](https://docs.claude-mem.ai/usage/search-tools) bölümüne bakın.
---
## Beta Özellikleri
Claude-Mem, **Endless Mode** (genişletilmiş oturumlar için biyomimetik bellek mimarisi) gibi deneysel özellikler içeren bir **beta kanalı** sunar. http://localhost:37777 → Settings adresindeki web görüntüleyici arayüzünden kararlı ve beta sürümleri arasında geçiş yapın.
Endless Mode hakkında detaylar ve nasıl deneyeceğiniz için **[Beta Özellikleri Dokümantasyonu](https://docs.claude-mem.ai/beta-features)** bölümüne bakın.
---
## Sistem Gereksinimleri
- **Node.js**: 18.0.0 veya üzeri
- **Claude Code**: Plugin desteği olan en son sürüm
- **Bun**: JavaScript çalışma zamanı ve işlem yöneticisi (eksikse otomatik kurulur)
- **uv**: Vektör arama için Python paket yöneticisi (eksikse otomatik kurulur)
- **SQLite 3**: Kalıcı depolama için (dahildir)
---
## Yapılandırma
Ayarlar `~/.claude-mem/settings.json` dosyasında yönetilir (ilk çalıştırmada varsayılanlarla otomatik oluşturulur). AI modelini, worker portunu, veri dizinini, log seviyesini ve bağlam enjeksiyon ayarlarını yapılandırın.
Tüm mevcut ayarlar ve örnekler için **[Yapılandırma Kılavuzu](https://docs.claude-mem.ai/configuration)** bölümüne bakın.
---
## Geliştirme
Derleme talimatları, test etme ve katkı iş akışı için **[Geliştirme Kılavuzu](https://docs.claude-mem.ai/development)** bölümüne bakın.
---
## Sorun Giderme
Sorunlarla karşılaşırsanız, sorunu Claude'a açıklayın ve troubleshoot becerisi otomatik olarak teşhis edip düzeltmeleri sağlayacaktır.
Yaygın sorunlar ve çözümler için **[Sorun Giderme Kılavuzu](https://docs.claude-mem.ai/troubleshooting)** bölümüne bakın.
---
## Hata Raporları
Otomatik oluşturucu ile kapsamlı hata raporları oluşturun:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Katkıda Bulunma
Katkılar memnuniyetle karşılanır! Lütfen:
1. Depoyu fork edin
2. Bir özellik dalı oluşturun
3. Testlerle değişikliklerinizi yapın
4. Dokümantasyonu güncelleyin
5. Pull Request gönderin
Katkı iş akışı için [Geliştirme Kılavuzu](https://docs.claude-mem.ai/development) bölümüne bakın.
---
## Lisans
Bu proje **GNU Affero General Public License v3.0** (AGPL-3.0) altında lisanslanmıştır.
Telif Hakkı (C) 2025 Alex Newman (@thedotmack). Tüm hakları saklıdır.
Tam detaylar için [LICENSE](LICENSE) dosyasına bakın.
**Bu Ne Anlama Gelir:**
- Bu yazılımı özgürce kullanabilir, değiştirebilir ve dağıtabilirsiniz
- Değiştirip bir ağ sunucusunda dağıtırsanız, kaynak kodunuzu kullanılabilir hale getirmelisiniz
- Türev çalışmalar da AGPL-3.0 altında lisanslanmalıdır
- Bu yazılım için HİÇBİR GARANTİ yoktur
**Ragtime Hakkında Not**: `ragtime/` dizini ayrı olarak **PolyForm Noncommercial License 1.0.0** altında lisanslanmıştır. Detaylar için [ragtime/LICENSE](ragtime/LICENSE) dosyasına bakın.
---
## Destek
- **Dokümantasyon**: [docs/](docs/)
- **Sorunlar**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Depo**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Yazar**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Claude Agent SDK ile geliştirilmiştir** | **Claude Code ile desteklenmektedir** | **TypeScript ile yapılmıştır**

302
docs/i18n/README.uk.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Це автоматичний переклад. Вітаються виправлення від спільноти!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Система стиснення постійної пам'яті, створена для <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#швидкий-старт">Швидкий старт</a> •
<a href="#як-це-працює">Як це працює</a> •
<a href="#інструменти-пошуку-mcp">Інструменти пошуку</a> •
<a href="#документація">Документація</a> •
<a href="#конфігурація">Конфігурація</a> •
<a href="#усунення-несправностей">Усунення несправностей</a> •
<a href="#ліцензія">Ліцензія</a>
</p>
<p align="center">
Claude-Mem безперешкодно зберігає контекст між сесіями, автоматично фіксуючи спостереження за використанням інструментів, генеруючи семантичні резюме та роблячи їх доступними для майбутніх сесій. Це дозволяє Claude підтримувати безперервність знань про проєкти навіть після завершення або повторного підключення сесій.
</p>
---
## Швидкий старт
Розпочніть нову сесію Claude Code у терміналі та введіть наступні команди:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Перезапустіть Claude Code. Контекст з попередніх сесій автоматично з'явиться в нових сесіях.
**Ключові можливості:**
- 🧠 **Постійна пам'ять** - Контекст зберігається між сесіями
- 📊 **Прогресивне розкриття** - Багаторівневе отримання пам'яті з видимістю вартості токенів
- 🔍 **Пошук на основі навичок** - Запитуйте історію свого проєкту за допомогою навички mem-search
- 🖥️ **Веб-інтерфейс перегляду** - Потік пам'яті в реальному часі на http://localhost:37777
- 💻 **Навичка Claude Desktop** - Шукайте в пам'яті з розмов Claude Desktop
- 🔒 **Контроль конфіденційності** - Використовуйте теги `<private>` для виключення чутливого вмісту зі зберігання
- ⚙️ **Конфігурація контексту** - Детальний контроль над тим, який контекст впроваджується
- 🤖 **Автоматична робота** - Не потребує ручного втручання
- 🔗 **Цитування** - Посилайтеся на минулі спостереження за ідентифікаторами (доступ через http://localhost:37777/api/observation/{id} або перегляд усіх у веб-переглядачі на http://localhost:37777)
- 🧪 **Бета-канал** - Спробуйте експериментальні функції, як-от режим Endless Mode, через перемикання версій
---
## Документація
📚 **[Переглянути повну документацію](docs/)** - Переглядайте markdown документи на GitHub
### Початок роботи
- **[Посібник з встановлення](https://docs.claude-mem.ai/installation)** - Швидкий старт і розширене встановлення
- **[Посібник з використання](https://docs.claude-mem.ai/usage/getting-started)** - Як Claude-Mem працює автоматично
- **[Інструменти пошуку](https://docs.claude-mem.ai/usage/search-tools)** - Запитуйте історію свого проєкту природною мовою
- **[Бета-функції](https://docs.claude-mem.ai/beta-features)** - Спробуйте експериментальні функції, як-от режим Endless Mode
### Найкращі практики
- **[Інженерія контексту](https://docs.claude-mem.ai/context-engineering)** - Принципи оптимізації контексту AI-агента
- **[Прогресивне розкриття](https://docs.claude-mem.ai/progressive-disclosure)** - Філософія стратегії підготовки контексту Claude-Mem
### Архітектура
- **[Огляд](https://docs.claude-mem.ai/architecture/overview)** - Компоненти системи та потік даних
- **[Еволюція архітектури](https://docs.claude-mem.ai/architecture-evolution)** - Шлях від v3 до v5
- **[Архітектура хуків](https://docs.claude-mem.ai/hooks-architecture)** - Як Claude-Mem використовує хуки життєвого циклу
- **[Довідник хуків](https://docs.claude-mem.ai/architecture/hooks)** - Пояснення 7 скриптів хуків
- **[Сервіс воркера](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API та управління Bun
- **[База даних](https://docs.claude-mem.ai/architecture/database)** - Схема SQLite та пошук FTS5
- **[Архітектура пошуку](https://docs.claude-mem.ai/architecture/search-architecture)** - Гібридний пошук з векторною базою даних Chroma
### Конфігурація та розробка
- **[Конфігурація](https://docs.claude-mem.ai/configuration)** - Змінні середовища та налаштування
- **[Розробка](https://docs.claude-mem.ai/development)** - Збірка, тестування, внесок
- **[Усунення несправностей](https://docs.claude-mem.ai/troubleshooting)** - Поширені проблеми та рішення
---
## Як це працює
**Основні компоненти:**
1. **5 хуків життєвого циклу** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 скриптів хуків)
2. **Розумне встановлення** - Кешована перевірка залежностей (скрипт перед хуком, не хук життєвого циклу)
3. **Сервіс воркера** - HTTP API на порту 37777 з веб-інтерфейсом перегляду та 10 кінцевими точками пошуку, керується Bun
4. **База даних SQLite** - Зберігає сесії, спостереження, резюме
5. **Навичка mem-search** - Запити природною мовою з прогресивним розкриттям
6. **Векторна база даних Chroma** - Гібридний семантичний + ключовий пошук для інтелектуального отримання контексту
Дивіться [Огляд архітектури](https://docs.claude-mem.ai/architecture/overview) для деталей.
---
## Навичка mem-search
Claude-Mem надає інтелектуальний пошук через навичку mem-search, яка автоматично викликається, коли ви запитуєте про минулу роботу:
**Як це працює:**
- Просто запитайте природно: *"Що ми робили в минулій сесії?"* або *"Ми виправляли цю помилку раніше?"*
- Claude автоматично викликає навичку mem-search для пошуку релевантного контексту
**Доступні операції пошуку:**
1. **Пошук спостережень** - Повнотекстовий пошук у спостереженнях
2. **Пошук сесій** - Повнотекстовий пошук у резюме сесій
3. **Пошук запитів** - Пошук необроблених запитів користувачів
4. **За концепцією** - Знайти за тегами концепцій (discovery, problem-solution, pattern тощо)
5. **За файлом** - Знайти спостереження, що посилаються на конкретні файли
6. **За типом** - Знайти за типом (decision, bugfix, feature, refactor, discovery, change)
7. **Останній контекст** - Отримати останній контекст сесії для проєкту
8. **Часова шкала** - Отримати єдину часову шкалу контексту навколо конкретного моменту часу
9. **Часова шкала за запитом** - Шукати спостереження та отримувати контекст часової шкали навколо найкращого збігу
10. **Довідка API** - Отримати документацію API пошуку
**Приклади запитів природною мовою:**
```
"Які помилки ми виправили в минулій сесії?"
"Як ми реалізували автентифікацію?"
"Які зміни були внесені в worker-service.ts?"
"Покажи мені останню роботу над цим проєктом"
"Що відбувалося, коли ми додали інтерфейс перегляду?"
```
Дивіться [Посібник з інструментів пошуку](https://docs.claude-mem.ai/usage/search-tools) для детальних прикладів.
---
## Бета-функції
Claude-Mem пропонує **бета-канал** з експериментальними функціями, як-от **режим Endless Mode** (біоміметична архітектура пам'яті для тривалих сесій). Перемикайтеся між стабільною та бета-версіями з веб-інтерфейсу перегляду на http://localhost:37777 → Налаштування.
Дивіться **[Документацію бета-функцій](https://docs.claude-mem.ai/beta-features)** для деталей про режим Endless Mode та як його спробувати.
---
## Системні вимоги
- **Node.js**: 18.0.0 або вище
- **Claude Code**: Остання версія з підтримкою плагінів
- **Bun**: Середовище виконання JavaScript та менеджер процесів (автоматично встановлюється, якщо відсутнє)
- **uv**: Менеджер пакетів Python для векторного пошуку (автоматично встановлюється, якщо відсутній)
- **SQLite 3**: Для постійного зберігання (у комплекті)
---
## Конфігурація
Налаштування керуються в `~/.claude-mem/settings.json` (автоматично створюється зі стандартними значеннями при першому запуску). Налаштуйте модель AI, порт воркера, каталог даних, рівень журналювання та параметри впровадження контексту.
Дивіться **[Посібник з конфігурації](https://docs.claude-mem.ai/configuration)** для всіх доступних налаштувань та прикладів.
---
## Розробка
Дивіться **[Посібник з розробки](https://docs.claude-mem.ai/development)** для інструкцій зі збірки, тестування та робочого процесу внеску.
---
## Усунення несправностей
Якщо виникають проблеми, опишіть проблему Claude, і навичка troubleshoot автоматично діагностує та надасть виправлення.
Дивіться **[Посібник з усунення несправностей](https://docs.claude-mem.ai/troubleshooting)** для поширених проблем та рішень.
---
## Звіти про помилки
Створюйте вичерпні звіти про помилки за допомогою автоматизованого генератора:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Внесок
Вітаються внески! Будь ласка:
1. Створіть форк репозиторію
2. Створіть гілку функції
3. Внесіть зміни з тестами
4. Оновіть документацію
5. Надішліть Pull Request
Дивіться [Посібник з розробки](https://docs.claude-mem.ai/development) для робочого процесу внеску.
---
## Ліцензія
Цей проєкт ліцензовано під **GNU Affero General Public License v3.0** (AGPL-3.0).
Авторське право (C) 2025 Alex Newman (@thedotmack). Всі права захищені.
Дивіться файл [LICENSE](LICENSE) для повних деталей.
**Що це означає:**
- Ви можете використовувати, модифікувати та поширювати це програмне забезпечення вільно
- Якщо ви модифікуєте та розгортаєте на мережевому сервері, ви повинні зробити свій вихідний код доступним
- Похідні роботи також повинні бути ліцензовані під AGPL-3.0
- Для цього програмного забезпечення НЕМАЄ ГАРАНТІЇ
**Примітка про Ragtime**: Каталог `ragtime/` ліцензовано окремо під **PolyForm Noncommercial License 1.0.0**. Дивіться [ragtime/LICENSE](ragtime/LICENSE) для деталей.
---
## Підтримка
- **Документація**: [docs/](docs/)
- **Проблеми**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Репозиторій**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Автор**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Створено за допомогою Claude Agent SDK** | **Працює на Claude Code** | **Зроблено з TypeScript**

302
docs/i18n/README.vi.md Normal file
View File

@@ -0,0 +1,302 @@
🌐 Đây là bản dịch tự động. Chúng tôi hoan nghênh các đóng góp từ cộng đồng!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">Hệ thống nén bộ nhớ liên tục được xây dựng cho <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#bắt-đầu-nhanh">Bắt Đầu Nhanh</a> •
<a href="#cách-hoạt-động">Cách Hoạt Động</a> •
<a href="#công-cụ-tìm-kiếm-mcp">Công Cụ Tìm Kiếm</a> •
<a href="#tài-liệu">Tài Liệu</a> •
<a href="#cấu-hình">Cấu Hình</a> •
<a href="#khắc-phục-sự-cố">Khắc Phục Sự Cố</a> •
<a href="#giấy-phép">Giấy Phép</a>
</p>
<p align="center">
Claude-Mem duy trì ngữ cảnh liền mạch qua các phiên làm việc bằng cách tự động ghi lại các quan sát về việc sử dụng công cụ, tạo tóm tắt ngữ nghĩa và cung cấp chúng cho các phiên làm việc trong tương lai. Điều này giúp Claude duy trì tính liên tục của kiến thức về các dự án ngay cả sau khi phiên làm việc kết thúc hoặc kết nối lại.
</p>
---
## Bắt Đầu Nhanh
Bắt đầu một phiên Claude Code mới trong terminal và nhập các lệnh sau:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
Khởi động lại Claude Code. Ngữ cảnh từ các phiên trước sẽ tự động xuất hiện trong các phiên mới.
**Tính Năng Chính:**
- 🧠 **Bộ Nhớ Liên Tục** - Ngữ cảnh được lưu giữ qua các phiên làm việc
- 📊 **Tiết Lộ Tuần Tự** - Truy xuất bộ nhớ theo lớp với khả năng hiển thị chi phí token
- 🔍 **Tìm Kiếm Theo Kỹ Năng** - Truy vấn lịch sử dự án với kỹ năng mem-search
- 🖥️ **Giao Diện Web Viewer** - Luồng bộ nhớ thời gian thực tại http://localhost:37777
- 💻 **Kỹ Năng Claude Desktop** - Tìm kiếm bộ nhớ từ các cuộc trò chuyện Claude Desktop
- 🔒 **Kiểm Soát Quyền Riêng Tư** - Sử dụng thẻ `<private>` để loại trừ nội dung nhạy cảm khỏi lưu trữ
- ⚙️ **Cấu Hình Ngữ Cảnh** - Kiểm soát chi tiết về ngữ cảnh được chèn vào
- 🤖 **Hoạt Động Tự Động** - Không cần can thiệp thủ công
- 🔗 **Trích Dẫn** - Tham chiếu các quan sát trong quá khứ với ID (truy cập qua http://localhost:37777/api/observation/{id} hoặc xem tất cả trong web viewer tại http://localhost:37777)
- 🧪 **Kênh Beta** - Dùng thử các tính năng thử nghiệm như Endless Mode thông qua chuyển đổi phiên bản
---
## Tài Liệu
📚 **[Xem Tài Liệu Đầy Đủ](docs/)** - Duyệt tài liệu markdown trên GitHub
### Bắt Đầu
- **[Hướng Dẫn Cài Đặt](https://docs.claude-mem.ai/installation)** - Bắt đầu nhanh & cài đặt nâng cao
- **[Hướng Dẫn Sử Dụng](https://docs.claude-mem.ai/usage/getting-started)** - Cách Claude-Mem hoạt động tự động
- **[Công Cụ Tìm Kiếm](https://docs.claude-mem.ai/usage/search-tools)** - Truy vấn lịch sử dự án bằng ngôn ngữ tự nhiên
- **[Tính Năng Beta](https://docs.claude-mem.ai/beta-features)** - Dùng thử các tính năng thử nghiệm như Endless Mode
### Thực Hành Tốt Nhất
- **[Kỹ Thuật Ngữ Cảnh](https://docs.claude-mem.ai/context-engineering)** - Các nguyên tắc tối ưu hóa ngữ cảnh cho AI agent
- **[Tiết Lộ Tuần Tự](https://docs.claude-mem.ai/progressive-disclosure)** - Triết lý đằng sau chiến lược chuẩn bị ngữ cảnh của Claude-Mem
### Kiến Trúc
- **[Tổng Quan](https://docs.claude-mem.ai/architecture/overview)** - Các thành phần hệ thống & luồng dữ liệu
- **[Phát Triển Kiến Trúc](https://docs.claude-mem.ai/architecture-evolution)** - Hành trình từ v3 đến v5
- **[Kiến Trúc Hooks](https://docs.claude-mem.ai/hooks-architecture)** - Cách Claude-Mem sử dụng lifecycle hooks
- **[Tham Chiếu Hooks](https://docs.claude-mem.ai/architecture/hooks)** - Giải thích 7 hook scripts
- **[Worker Service](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API & quản lý Bun
- **[Cơ Sở Dữ Liệu](https://docs.claude-mem.ai/architecture/database)** - Schema SQLite & tìm kiếm FTS5
- **[Kiến Trúc Tìm Kiếm](https://docs.claude-mem.ai/architecture/search-architecture)** - Tìm kiếm kết hợp với cơ sở dữ liệu vector Chroma
### Cấu Hình & Phát Triển
- **[Cấu Hình](https://docs.claude-mem.ai/configuration)** - Biến môi trường & cài đặt
- **[Phát Triển](https://docs.claude-mem.ai/development)** - Xây dựng, kiểm thử, đóng góp
- **[Khắc Phục Sự Cố](https://docs.claude-mem.ai/troubleshooting)** - Các vấn đề thường gặp & giải pháp
---
## Cách Hoạt Động
**Các Thành Phần Cốt Lõi:**
1. **5 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
2. **Smart Install** - Công cụ kiểm tra phụ thuộc được cache (pre-hook script, không phải lifecycle hook)
3. **Worker Service** - HTTP API trên cổng 37777 với giao diện web viewer và 10 điểm cuối tìm kiếm, được quản lý bởi Bun
4. **SQLite Database** - Lưu trữ các phiên, quan sát, tóm tắt
5. **mem-search Skill** - Truy vấn ngôn ngữ tự nhiên với tiết lộ tuần tự
6. **Chroma Vector Database** - Tìm kiếm kết hợp ngữ nghĩa + từ khóa để truy xuất ngữ cảnh thông minh
Xem [Tổng Quan Kiến Trúc](https://docs.claude-mem.ai/architecture/overview) để biết chi tiết.
---
## mem-search Skill
Claude-Mem cung cấp tìm kiếm thông minh thông qua kỹ năng mem-search tự động kích hoạt khi bạn hỏi về công việc trước đây:
**Cách Hoạt Động:**
- Chỉ cần hỏi một cách tự nhiên: *"Chúng ta đã làm gì trong phiên trước?"* hoặc *"Chúng ta đã sửa lỗi này trước đây chưa?"*
- Claude tự động gọi kỹ năng mem-search để tìm ngữ cảnh liên quan
**Các Thao Tác Tìm Kiếm Có Sẵn:**
1. **Search Observations** - Tìm kiếm toàn văn trên các quan sát
2. **Search Sessions** - Tìm kiếm toàn văn trên các tóm tắt phiên
3. **Search Prompts** - Tìm kiếm các yêu cầu người dùng thô
4. **By Concept** - Tìm theo thẻ khái niệm (discovery, problem-solution, pattern, v.v.)
5. **By File** - Tìm các quan sát tham chiếu đến các tệp cụ thể
6. **By Type** - Tìm theo loại (decision, bugfix, feature, refactor, discovery, change)
7. **Recent Context** - Lấy ngữ cảnh phiên gần đây cho một dự án
8. **Timeline** - Lấy dòng thời gian thống nhất của ngữ cảnh xung quanh một thời điểm cụ thể
9. **Timeline by Query** - Tìm kiếm các quan sát và lấy ngữ cảnh dòng thời gian xung quanh kết quả khớp tốt nhất
10. **API Help** - Lấy tài liệu API tìm kiếm
**Ví Dụ Truy Vấn Ngôn Ngữ Tự Nhiên:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
Xem [Hướng Dẫn Công Cụ Tìm Kiếm](https://docs.claude-mem.ai/usage/search-tools) để biết các ví dụ chi tiết.
---
## Tính Năng Beta
Claude-Mem cung cấp **kênh beta** với các tính năng thử nghiệm như **Endless Mode** (kiến trúc bộ nhớ sinh học mô phỏng cho các phiên mở rộng). Chuyển đổi giữa các phiên bản ổn định và beta từ giao diện web viewer tại http://localhost:37777 → Settings.
Xem **[Tài Liệu Tính Năng Beta](https://docs.claude-mem.ai/beta-features)** để biết chi tiết về Endless Mode và cách dùng thử.
---
## Yêu Cầu Hệ Thống
- **Node.js**: 18.0.0 hoặc cao hơn
- **Claude Code**: Phiên bản mới nhất với hỗ trợ plugin
- **Bun**: JavaScript runtime và trình quản lý tiến trình (tự động cài đặt nếu thiếu)
- **uv**: Trình quản lý gói Python cho tìm kiếm vector (tự động cài đặt nếu thiếu)
- **SQLite 3**: Cho lưu trữ liên tục (đi kèm)
---
## Cấu Hình
Cài đặt được quản lý trong `~/.claude-mem/settings.json` (tự động tạo với giá trị mặc định khi chạy lần đầu). Cấu hình mô hình AI, cổng worker, thư mục dữ liệu, mức độ log và cài đặt chèn ngữ cảnh.
Xem **[Hướng Dẫn Cấu Hình](https://docs.claude-mem.ai/configuration)** để biết tất cả các cài đặt và ví dụ có sẵn.
---
## Phát Triển
Xem **[Hướng Dẫn Phát Triển](https://docs.claude-mem.ai/development)** để biết hướng dẫn xây dựng, kiểm thử và quy trình đóng góp.
---
## Khắc Phục Sự Cố
Nếu gặp sự cố, hãy mô tả vấn đề cho Claude và kỹ năng troubleshoot sẽ tự động chẩn đoán và cung cấp các bản sửa lỗi.
Xem **[Hướng Dẫn Khắc Phục Sự Cố](https://docs.claude-mem.ai/troubleshooting)** để biết các vấn đề thường gặp và giải pháp.
---
## Báo Cáo Lỗi
Tạo báo cáo lỗi toàn diện với trình tạo tự động:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## Đóng Góp
Chúng tôi hoan nghênh các đóng góp! Vui lòng:
1. Fork repository
2. Tạo nhánh tính năng
3. Thực hiện thay đổi của bạn kèm kiểm thử
4. Cập nhật tài liệu
5. Gửi Pull Request
Xem [Hướng Dẫn Phát Triển](https://docs.claude-mem.ai/development) để biết quy trình đóng góp.
---
## Giấy Phép
Dự án này được cấp phép theo **GNU Affero General Public License v3.0** (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Bảo lưu mọi quyền.
Xem tệp [LICENSE](LICENSE) để biết chi tiết đầy đủ.
**Điều Này Có Nghĩa Là:**
- Bạn có thể sử dụng, sửa đổi và phân phối phần mềm này tự do
- Nếu bạn sửa đổi và triển khai trên máy chủ mạng, bạn phải cung cấp mã nguồn của mình
- Các tác phẩm phái sinh cũng phải được cấp phép theo AGPL-3.0
- KHÔNG CÓ BẢO HÀNH cho phần mềm này
**Lưu Ý Về Ragtime**: Thư mục `ragtime/` được cấp phép riêng theo **PolyForm Noncommercial License 1.0.0**. Xem [ragtime/LICENSE](ragtime/LICENSE) để biết chi tiết.
---
## Hỗ Trợ
- **Tài Liệu**: [docs/](docs/)
- **Vấn Đề**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **Repository**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **Tác Giả**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**Được Xây Dựng với Claude Agent SDK** | **Được Hỗ Trợ bởi Claude Code** | **Được Tạo với TypeScript**

304
docs/i18n/README.zh.md Normal file
View File

@@ -0,0 +1,304 @@
🌐 这是自动翻译。欢迎社区修正!
---
<h1 align="center">
<br>
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-dark-mode.webp">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/claude-mem-logo-for-light-mode.webp" alt="Claude-Mem" width="400">
</picture>
</a>
<br>
</h1>
<p align="center">
<a href="README.zh.md">🇨🇳 中文</a> •
<a href="README.ja.md">🇯🇵 日本語</a> •
<a href="README.pt-br.md">🇧🇷 Português</a> •
<a href="README.ko.md">🇰🇷 한국어</a> •
<a href="README.es.md">🇪🇸 Español</a> •
<a href="README.de.md">🇩🇪 Deutsch</a> •
<a href="README.fr.md">🇫🇷 Français</a>
<a href="README.he.md">🇮🇱 עברית</a> •
<a href="README.ar.md">🇸🇦 العربية</a> •
<a href="README.ru.md">🇷🇺 Русский</a> •
<a href="README.pl.md">🇵🇱 Polski</a> •
<a href="README.cs.md">🇨🇿 Čeština</a> •
<a href="README.nl.md">🇳🇱 Nederlands</a> •
<a href="README.tr.md">🇹🇷 Türkçe</a> •
<a href="README.uk.md">🇺🇦 Українська</a> •
<a href="README.vi.md">🇻🇳 Tiếng Việt</a> •
<a href="README.id.md">🇮🇩 Indonesia</a> •
<a href="README.th.md">🇹🇭 ไทย</a> •
<a href="README.hi.md">🇮🇳 हिन्दी</a> •
<a href="README.bn.md">🇧🇩 বাংলা</a> •
<a href="README.ro.md">🇷🇴 Română</a> •
<a href="README.sv.md">🇸🇪 Svenska</a> •
<a href="README.it.md">🇮🇹 Italiano</a> •
<a href="README.el.md">🇬🇷 Ελληνικά</a> •
<a href="README.hu.md">🇭🇺 Magyar</a> •
<a href="README.fi.md">🇫🇮 Suomi</a> •
<a href="README.da.md">🇩🇰 Dansk</a> •
<a href="README.no.md">🇳🇴 Norsk</a>
</p>
<h4 align="center">为 <a href="https://claude.com/claude-code" target="_blank">Claude Code</a> 构建的持久化内存压缩系统。</h4>
<p align="center">
<a href="LICENSE">
<img src="https://img.shields.io/badge/License-AGPL%203.0-blue.svg" alt="License">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/version-6.5.0-green.svg" alt="Version">
</a>
<a href="package.json">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
</a>
<a href="https://github.com/thedotmack/awesome-claude-code">
<img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code">
</a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/15496" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg">
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/trendshift-badge.svg" alt="thedotmack/claude-mem | Trendshift" width="250" height="55"/>
</picture>
</a>
</p>
<br>
<p align="center">
<a href="https://github.com/thedotmack/claude-mem">
<picture>
<img src="https://raw.githubusercontent.com/thedotmack/claude-mem/main/docs/public/cm-preview.gif" alt="Claude-Mem Preview" width="800">
</picture>
</a>
</p>
<p align="center">
<a href="#快速开始">快速开始</a> •
<a href="#工作原理">工作原理</a> •
<a href="#mcp-搜索工具">搜索工具</a> •
<a href="#文档">文档</a> •
<a href="#配置">配置</a> •
<a href="#故障排除">故障排除</a> •
<a href="#许可证">许可证</a>
</p>
<p align="center">
Claude-Mem 通过自动捕获工具使用观察、生成语义摘要并使其可用于未来会话,无缝保留跨会话的上下文。这使 Claude 能够在会话结束或重新连接后仍保持对项目的知识连续性。
</p>
---
## 快速开始
在终端中启动新的 Claude Code 会话并输入以下命令:
```
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
```
重启 Claude Code。来自先前会话的上下文将自动出现在新会话中。
**核心特性:**
- 🧠 **持久化内存** - 上下文跨会话保留
- 📊 **渐进式披露** - 分层内存检索,具有令牌成本可见性
- 🔍 **基于技能的搜索** - 使用 mem-search 技能查询项目历史
- 🖥️ **Web 查看器界面** - 在 http://localhost:37777 实时查看内存流
- 💻 **Claude Desktop 技能** - 从 Claude Desktop 对话中搜索内存
- 🔒 **隐私控制** - 使用 `<private>` 标签排除敏感内容的存储
- ⚙️ **上下文配置** - 精细控制注入的上下文内容
- 🤖 **自动操作** - 无需手动干预
- 🔗 **引用** - 使用 ID 引用过去的观察(通过 http://localhost:37777/api/observation/{id} 访问,或在 http://localhost:37777 的 Web 查看器中查看全部)
- 🧪 **测试版渠道** - 通过版本切换尝试实验性功能,如无尽模式
---
## 文档
📚 **[查看完整文档](docs/)** - 在 GitHub 上浏览 Markdown 文档
### 入门指南
- **[安装指南](https://docs.claude-mem.ai/installation)** - 快速开始与高级安装
- **[使用指南](https://docs.claude-mem.ai/usage/getting-started)** - Claude-Mem 如何自动工作
- **[搜索工具](https://docs.claude-mem.ai/usage/search-tools)** - 使用自然语言查询项目历史
- **[测试版功能](https://docs.claude-mem.ai/beta-features)** - 尝试实验性功能,如无尽模式
### 最佳实践
- **[上下文工程](https://docs.claude-mem.ai/context-engineering)** - AI 代理上下文优化原则
- **[渐进式披露](https://docs.claude-mem.ai/progressive-disclosure)** - Claude-Mem 上下文启动策略背后的哲学
### 架构
- **[概述](https://docs.claude-mem.ai/architecture/overview)** - 系统组件与数据流
- **[架构演进](https://docs.claude-mem.ai/architecture-evolution)** - 从 v3 到 v5 的旅程
- **[钩子架构](https://docs.claude-mem.ai/hooks-architecture)** - Claude-Mem 如何使用生命周期钩子
- **[钩子参考](https://docs.claude-mem.ai/architecture/hooks)** - 7 个钩子脚本详解
- **[Worker 服务](https://docs.claude-mem.ai/architecture/worker-service)** - HTTP API 与 Bun 管理
- **[数据库](https://docs.claude-mem.ai/architecture/database)** - SQLite 模式与 FTS5 搜索
- **[搜索架构](https://docs.claude-mem.ai/architecture/search-architecture)** - 使用 Chroma 向量数据库的混合搜索
### 配置与开发
- **[配置](https://docs.claude-mem.ai/configuration)** - 环境变量与设置
- **[开发](https://docs.claude-mem.ai/development)** - 构建、测试、贡献
- **[故障排除](https://docs.claude-mem.ai/troubleshooting)** - 常见问题与解决方案
---
## 工作原理
**核心组件:**
1. **5 个生命周期钩子** - SessionStart、UserPromptSubmit、PostToolUse、Stop、SessionEnd(6 个钩子脚本)
2. **智能安装** - 缓存依赖检查器(预钩子脚本,不是生命周期钩子)
3. **Worker 服务** - 在端口 37777 上的 HTTP API,带有 Web 查看器界面和 10 个搜索端点,由 Bun 管理
4. **SQLite 数据库** - 存储会话、观察、摘要
5. **mem-search 技能** - 具有渐进式披露的自然语言查询
6. **Chroma 向量数据库** - 混合语义 + 关键词搜索,实现智能上下文检索
详见[架构概述](https://docs.claude-mem.ai/architecture/overview)。
---
## mem-search 技能
Claude-Mem 通过 mem-search 技能提供智能搜索,当您询问过去的工作时会自动调用:
**工作方式:**
- 只需自然提问:*"上次会话我们做了什么?"* 或 *"我们之前修复过这个 bug 吗?"*
- Claude 自动调用 mem-search 技能查找相关上下文
**可用搜索操作:**
1. **搜索观察** - 跨观察的全文搜索
2. **搜索会话** - 跨会话摘要的全文搜索
3. **搜索提示** - 搜索原始用户请求
4. **按概念搜索** - 按概念标签查找(发现、问题-解决方案、模式等)
5. **按文件搜索** - 查找引用特定文件的观察
6. **按类型搜索** - 按类型查找(决策、bug修复、功能、重构、发现、更改)
7. **最近上下文** - 获取项目的最近会话上下文
8. **时间线** - 获取特定时间点周围的统一上下文时间线
9. **按查询的时间线** - 搜索观察并获取最佳匹配周围的时间线上下文
10. **API 帮助** - 获取搜索 API 文档
**自然语言查询示例:**
```
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
```
详见[搜索工具指南](https://docs.claude-mem.ai/usage/search-tools)的详细示例。
---
## 测试版功能
Claude-Mem 提供**测试版渠道**,包含实验性功能,如**无尽模式**(用于扩展会话的仿生记忆架构)。从 Web 查看器界面 http://localhost:37777 → 设置 切换稳定版和测试版。
详见**[测试版功能文档](https://docs.claude-mem.ai/beta-features)**了解无尽模式的详细信息和试用方法。
---
## 系统要求
- **Node.js**: 18.0.0 或更高版本
- **Claude Code**: 支持插件的最新版本
- **Bun**: JavaScript 运行时和进程管理器(如缺失会自动安装)
- **uv**: 用于向量搜索的 Python 包管理器(如缺失会自动安装)
- **SQLite 3**: 用于持久化存储(已内置)
---
## 配置
设置在 `~/.claude-mem/settings.json` 中管理(首次运行时自动创建默认设置)。可配置 AI 模型、worker 端口、数据目录、日志级别和上下文注入设置。
详见**[配置指南](https://docs.claude-mem.ai/configuration)**了解所有可用设置和示例。
---
## 开发
详见**[开发指南](https://docs.claude-mem.ai/development)**了解构建说明、测试和贡献工作流程。
---
## 故障排除
如果遇到问题,向 Claude 描述问题,troubleshoot 技能将自动诊断并提供修复方案。
详见**[故障排除指南](https://docs.claude-mem.ai/troubleshooting)**了解常见问题和解决方案。
---
## Bug 报告
使用自动生成器创建全面的 bug 报告:
```bash
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
```
## 贡献
欢迎贡献!请:
1. Fork 仓库
2. 创建功能分支
3. 进行更改并添加测试
4. 更新文档
5. 提交 Pull Request
详见[开发指南](https://docs.claude-mem.ai/development)了解贡献工作流程。
---
## 许可证
本项目采用 **GNU Affero General Public License v3.0** (AGPL-3.0) 许可。
Copyright (C) 2025 Alex Newman (@thedotmack)。保留所有权利。
详见 [LICENSE](LICENSE) 文件了解完整详情。
**这意味着什么:**
- 您可以自由使用、修改和分发本软件
- 如果您修改并部署到网络服务器上,必须公开您的源代码
- 衍生作品也必须采用 AGPL-3.0 许可
- 本软件不提供任何保证
**关于 Ragtime 的说明**: `ragtime/` 目录单独采用 **PolyForm Noncommercial License 1.0.0** 许可。详见 [ragtime/LICENSE](ragtime/LICENSE)。
---
## 支持
- **文档**: [docs/](docs/)
- **问题反馈**: [GitHub Issues](https://github.com/thedotmack/claude-mem/issues)
- **仓库**: [github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
- **作者**: Alex Newman ([@thedotmack](https://github.com/thedotmack))
---
**使用 Claude Agent SDK 构建** | **由 Claude Code 驱动** | **使用 TypeScript 制作**
---

27
docs/public/configuration.mdx
View File

@@ -14,6 +14,7 @@ Settings are managed in `~/.claude-mem/settings.json`. The file is auto-created
| Setting | Default | Description |
|-------------------------------|---------------------------------|---------------------------------------|
| `CLAUDE_MEM_MODEL` | `sonnet` | AI model for processing observations |
| `CLAUDE_MEM_MODE` | `code` | Active mode profile (e.g., `code--es`, `email-investigation`) |
| `CLAUDE_MEM_CONTEXT_OBSERVATIONS` | `50` | Number of observations to inject |
| `CLAUDE_MEM_WORKER_PORT` | `37777` | Worker service port |
| `CLAUDE_MEM_SKIP_TOOLS` | `ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion` | Comma-separated tools to exclude from observations |
@@ -57,6 +58,32 @@ Edit `~/.claude-mem/settings.json`:
}
```
## Mode Configuration
Configure the active workflow mode and language.
### Settings
| Setting | Default | Description |
|---------|---------|-------------|
| `CLAUDE_MEM_MODE` | `code` | Defines behavior and language. See [Modes & Languages](modes). |
### Examples
**Spanish Code Mode:**
```json
{
"CLAUDE_MEM_MODE": "code--es"
}
```
**Email Investigation Mode:**
```json
{
"CLAUDE_MEM_MODE": "email-investigation"
}
```
## Files and Directories
### Data Directory Structure

1
docs/public/docs.json
View File

@@ -57,6 +57,7 @@
"icon": "gear",
"pages": [
"configuration",
"modes",
"development",
"troubleshooting",
"platform-integration"

2
docs/public/introduction.mdx
View File

@@ -23,6 +23,8 @@ Restart Claude Code. Context from previous sessions will automatically appear in
## Key Features
- 🧠 **Persistent Memory** - Context survives across sessions
- 🌐 **Multilingual Modes** - Supports 10+ languages (Spanish, Chinese, French, etc.)
- 🎭 **Mode System** - Switch between workflows (Code, Email Investigation)
- 🔍 **mem-search Skill** - Query your project history with natural language (~2,250 token savings)
- 🌐 **Web Viewer UI** - Real-time memory stream visualization at http://localhost:37777
- 🔒 **Privacy Control** - Use `<private>` tags to exclude sensitive content from storage

77
docs/public/modes.mdx Normal file
View File

@@ -0,0 +1,77 @@
---
title: "Modes & Languages"
description: "Configure Claude-Mem behavior and language with the Mode System"
---
# Modes & Languages
Claude-Mem uses a flexible **Mode System** to adapt its behavior, observation types, and output language. This allows you to switch between different workflows (like coding vs. email investigation) or languages without reinstalling the plugin.
## What is a Mode?
A "mode" is a configuration profile that defines:
1. **Observer Role**: How Claude should analyze your work (e.g., "Software Engineer" vs. "Forensic Analyst").
2. **Observation Types**: Valid categories for memory (e.g., "Bug Fix", "Feature" vs. "Person", "Organization").
3. **Concepts**: Semantic tags for indexing (e.g., "Pattern", "Trade-off").
4. **Language**: The language used for generating observations and summaries.
## Configuration
Set the active mode using the `CLAUDE_MEM_MODE` setting in `~/.claude-mem/settings.json`:
```json
{
"CLAUDE_MEM_MODE": "code--es"
}
```
Or via environment variable:
```bash
export CLAUDE_MEM_MODE="code--fr"
```
## Available Modes
### Code Mode (Default)
The standard mode for software development. Captures bug fixes, features, refactors, and architectural decisions.
**ID:** `code`
### Multilingual Code Modes
Inherits all behavior from Code Mode but instructs Claude to generate **all** memory artifacts (titles, narratives, facts, summaries) in the target language.
| Language | Mode ID | Description |
|----------|---------|-------------|
| **Chinese** | `code--zh` | 中文 |
| **Spanish** | `code--es` | Español |
| **French** | `code--fr` | Français |
| **German** | `code--de` | Deutsch |
| **Japanese** | `code--ja` | 日本語 |
| **Korean** | `code--ko` | 한국어 |
| **Portuguese** | `code--pt` | Português |
| **Russian** | `code--ru` | Русский |
| **Thai** | `code--th` | ภาษาไทย |
| **Vietnamese** | `code--vi` | Tiếng Việt |
### Email Investigation Mode
A specialized mode for analyzing email dumps (e.g., FOIA releases, corporate archives). Focuses on identifying entities, relationships, timeline events, and key topics.
**ID:** `email-investigation`
**Observation Types:**
- `entity`: Person, organization, or email address
- `relationship`: Connection between entities
- `timeline-event`: Time-stamped event in communication sequence
- `evidence`: Supporting documentation or proof
- `anomaly`: Suspicious pattern or irregularity
- `conclusion`: Investigative finding or determination
## Mode Inheritance
The system supports inheritance using the `--` separator. For example, `code--es` means:
1. Load `code` (Parent) configuration.
2. Load `code--es` (Child) configuration.
3. Merge Child into Parent (Child overrides).
This allows for lightweight "remix" modes that only change specific aspects (like the language prompt) while keeping the core definitions intact.

20
package.json
View File

@@ -33,28 +33,22 @@
"scripts": {
"build": "node scripts/build-hooks.js",
"build-and-sync": "npm run build && npm run sync-marketplace && sleep 1 && cd ~/.claude/plugins/marketplaces/thedotmack && npm run worker:restart",
"test": "vitest",
"test:parser": "npx tsx src/sdk/parser.test.ts",
"test:context": "echo '{\"session_id\":\"test-'$(date +%s)'\",\"cwd\":\"'$(pwd)'\",\"source\":\"startup\"}' | node plugin/scripts/context-hook.js 2>/dev/null",
"test:context:verbose": "echo '{\"session_id\":\"test-'$(date +%s)'\",\"cwd\":\"'$(pwd)'\",\"source\":\"startup\"}' | node plugin/scripts/context-hook.js",
"sync-marketplace": "node scripts/sync-marketplace.cjs",
"sync-marketplace:force": "node scripts/sync-marketplace.cjs --force",
"build:binaries": "node scripts/build-worker-binary.js",
"worker:start": "bun plugin/scripts/worker-cli.js start",
"worker:stop": "bun plugin/scripts/worker-cli.js stop",
"worker:restart": "bun plugin/scripts/worker-cli.js restart",
"worker:status": "bun plugin/scripts/worker-cli.js status",
"worker:start": "claude-mem start",
"worker:stop": "claude-mem stop",
"worker:restart": "claude-mem restart",
"worker:status": "claude-mem status",
"worker:logs": "tail -n 50 ~/.claude-mem/logs/worker-$(date +%Y-%m-%d).log",
"changelog:generate": "node scripts/generate-changelog.js",
"discord:notify": "node scripts/discord-release-notify.js",
"usage:analyze": "node scripts/analyze-usage.js",
"usage:today": "node scripts/analyze-usage.js $(date +%Y-%m-%d)",
"translate-readme": "bun scripts/translate-readme/cli.ts -v -o docs/i18n README.md",
"translate:tier1": "npm run translate-readme -- zh ja pt-br ko es de fr",
"translate:tier2": "npm run translate-readme -- he ar ru pl cs nl tr uk",
"translate:tier3": "npm run translate-readme -- vi id th hi bn ro sv",
"translate:tier4": "npm run translate-readme -- it el hu fi da no",
"translate:all": "npm run translate:tier1 && npm run translate:tier2 && npm run translate:tier3 && npm run translate:tier4",
"translate:all": "npm run translate:tier1 & npm run translate:tier2 & npm run translate:tier3 & npm run translate:tier4 & wait",
"bug-report": "npx tsx scripts/bug-report/cli.ts"
},
"dependencies": {
@@ -66,6 +60,7 @@
"handlebars": "^4.7.8",
"react": "^18.3.1",
"react-dom": "^18.3.1",
"yaml": "^2.8.2",
"zod-to-json-schema": "^3.24.6"
},
"devDependencies": {
@@ -76,7 +71,6 @@
"@types/react-dom": "^18.3.0",
"esbuild": "^0.25.12",
"tsx": "^4.20.6",
"typescript": "^5.3.0",
"vitest": "^4.0.15"
"typescript": "^5.3.0"
}
}

24
plugin/modes/code--ar.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Arabic)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in العربية",
"xml_title_placeholder": "[**title**: عنوان قصير يلخص الإجراء أو الموضوع الأساسي]",
"xml_subtitle_placeholder": "[**subtitle**: شرح في جملة واحدة (بحد أقصى 24 كلمة)]",
"xml_fact_placeholder": "[بيان موجز ومكتفٍ ذاتياً]",
"xml_narrative_placeholder": "[**narrative**: السياق الكامل: ما تم إنجازه، كيف يعمل، لماذا هو مهم]",
"xml_concept_placeholder": "[فئة-نوع-المعرفة]",
"xml_file_placeholder": "[المسار/إلى/الملف]",
"xml_summary_request_placeholder": "[عنوان قصير يلخص طلب المستخدم وجوهر ما تمت مناقشته/إنجازه]",
"xml_summary_investigated_placeholder": "[ما الذي تم استكشافه حتى الآن؟ ما الذي تم فحصه؟]",
"xml_summary_learned_placeholder": "[ما الذي تعلمته عن كيفية عمل الأشياء؟]",
"xml_summary_completed_placeholder": "[ما العمل الذي تم إنجازه حتى الآن؟ ما الذي تم شحنه أو تغييره؟]",
"xml_summary_next_steps_placeholder": "[ما الذي تعمل عليه بنشاط أو تخطط للعمل عليه بعد ذلك في هذه الجلسة؟]",
"xml_summary_notes_placeholder": "[رؤى أو ملاحظات إضافية حول التقدم الحالي]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in العربية",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in العربية"
}
}

24
plugin/modes/code--bn.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Bengali)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in বাংলা",
"xml_title_placeholder": "[**title**: মূল কাজ বা বিষয় বর্ণনাকারী সংক্ষিপ্ত শিরোনাম]",
"xml_subtitle_placeholder": "[**subtitle**: এক বাক্যে ব্যাখ্যা (সর্বোচ্চ ২৪ শব্দ)]",
"xml_fact_placeholder": "[সংক্ষিপ্ত, স্বয়ংসম্পূর্ণ বিবৃতি]",
"xml_narrative_placeholder": "[**narrative**: সম্পূর্ণ প্রসঙ্গ: কী করা হয়েছে, এটি কীভাবে কাজ করে, কেন এটি গুরুত্বপূর্ণ]",
"xml_concept_placeholder": "[জ্ঞান-ধরন-বিভাগ]",
"xml_file_placeholder": "[ফাইলের/পথ]",
"xml_summary_request_placeholder": "[সংক্ষিপ্ত শিরোনাম যা ব্যবহারকারীর অনুরোধ এবং আলোচনা/সম্পাদিত বিষয়ের সারমর্ম বর্ণনা করে]",
"xml_summary_investigated_placeholder": "[এখন পর্যন্ত কী অনুসন্ধান করা হয়েছে? কী পর্যালোচনা করা হয়েছে?]",
"xml_summary_learned_placeholder": "[জিনিসগুলি কীভাবে কাজ করে সে সম্পর্কে আপনি কী শিখেছেন?]",
"xml_summary_completed_placeholder": "[এখন পর্যন্ত কোন কাজ সম্পন্ন হয়েছে? কী সরবরাহ বা পরিবর্তন করা হয়েছে?]",
"xml_summary_next_steps_placeholder": "[এই সেশনে আপনি সক্রিয়ভাবে কী নিয়ে কাজ করছেন বা পরবর্তীতে করার পরিকল্পনা করছেন?]",
"xml_summary_notes_placeholder": "[বর্তমান অগ্রগতি সম্পর্কে অতিরিক্ত অন্তর্দৃষ্টি বা পর্যবেক্ষণ]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in বাংলা",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in বাংলা"
}
}

24
plugin/modes/code--cs.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Czech)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in čeština",
"xml_title_placeholder": "[**title**: Krátký název zachycující hlavní akci nebo téma]",
"xml_subtitle_placeholder": "[**subtitle**: Vysvětlení v jedné větě (maximálně 24 slov)]",
"xml_fact_placeholder": "[Stručné, samostatné tvrzení]",
"xml_narrative_placeholder": "[**narrative**: Plný kontext: co bylo provedeno, jak to funguje, proč je to důležité]",
"xml_concept_placeholder": "[kategorie-typu-znalosti]",
"xml_file_placeholder": "[cesta/k/souboru]",
"xml_summary_request_placeholder": "[Krátký název zachycující požadavek uživatele a podstatu toho, co bylo diskutováno/provedeno]",
"xml_summary_investigated_placeholder": "[Co bylo dosud prozkoumáno? Co bylo přezkoumáno?]",
"xml_summary_learned_placeholder": "[Co jste se naučili o tom, jak věci fungují?]",
"xml_summary_completed_placeholder": "[Jaká práce byla dosud dokončena? Co bylo dodáno nebo změněno?]",
"xml_summary_next_steps_placeholder": "[Na čem aktivně pracujete nebo plánujete pracovat dále v této relaci?]",
"xml_summary_notes_placeholder": "[Další poznatky nebo poznámky o aktuálním pokroku]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in čeština",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in čeština"
}
}

24
plugin/modes/code--da.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Danish)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in dansk",
"xml_title_placeholder": "[**title**: Kort titel der beskriver hovedhandlingen eller emnet]",
"xml_subtitle_placeholder": "[**subtitle**: Forklaring i én sætning (maksimalt 24 ord)]",
"xml_fact_placeholder": "[Kortfattet, selvstændig erklæring]",
"xml_narrative_placeholder": "[**narrative**: Fuld kontekst: hvad der blev gjort, hvordan det virker, hvorfor det er vigtigt]",
"xml_concept_placeholder": "[videnstype-kategori]",
"xml_file_placeholder": "[sti/til/fil]",
"xml_summary_request_placeholder": "[Kort titel der beskriver brugerens anmodning og essensen af hvad der blev diskuteret/gjort]",
"xml_summary_investigated_placeholder": "[Hvad er der blevet udforsket indtil videre? Hvad er blevet gennemgået?]",
"xml_summary_learned_placeholder": "[Hvad har du lært om, hvordan tingene fungerer?]",
"xml_summary_completed_placeholder": "[Hvilket arbejde er blevet afsluttet indtil videre? Hvad er blevet leveret eller ændret?]",
"xml_summary_next_steps_placeholder": "[Hvad arbejder du aktivt på eller planlægger at arbejde på næste i denne session?]",
"xml_summary_notes_placeholder": "[Yderligere indsigter eller observationer om den aktuelle fremgang]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in dansk",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in dansk"
}
}

24
plugin/modes/code--de.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (German)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Deutsch",
"xml_title_placeholder": "[**title**: Kurzer Titel, der die Kernaktion oder das Thema erfasst]",
"xml_subtitle_placeholder": "[**subtitle**: Erklärung in einem Satz (maximal 24 Wörter)]",
"xml_fact_placeholder": "[Prägnante, eigenständige Aussage]",
"xml_narrative_placeholder": "[**narrative**: Vollständiger Kontext: Was wurde getan, wie es funktioniert, warum es wichtig ist]",
"xml_concept_placeholder": "[Wissenstypkategorie]",
"xml_file_placeholder": "[pfad/zur/datei]",
"xml_summary_request_placeholder": "[Kurzer Titel, der die Anfrage des Benutzers UND die Substanz dessen erfasst, was besprochen/getan wurde]",
"xml_summary_investigated_placeholder": "[Was wurde bisher untersucht? Was wurde überprüft?]",
"xml_summary_learned_placeholder": "[Was haben Sie über die Funktionsweise gelernt?]",
"xml_summary_completed_placeholder": "[Welche Arbeit wurde bisher abgeschlossen? Was wurde ausgeliefert oder geändert?]",
"xml_summary_next_steps_placeholder": "[Woran arbeiten Sie aktiv oder planen Sie als Nächstes in dieser Sitzung zu arbeiten?]",
"xml_summary_notes_placeholder": "[Zusätzliche Erkenntnisse oder Beobachtungen zum aktuellen Fortschritt]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Deutsch",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in Deutsch"
}
}

24
plugin/modes/code--el.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Greek)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in ελληνικά",
"xml_title_placeholder": "[**title**: Σύντομος τίτλος που περιγράφει την κύρια ενέργεια ή το θέμα]",
"xml_subtitle_placeholder": "[**subtitle**: Εξήγηση σε μία πρόταση (μέγιστο 24 λέξεις)]",
"xml_fact_placeholder": "[Συνοπτική, αυτόνομη δήλωση]",
"xml_narrative_placeholder": "[**narrative**: Πλήρες πλαίσιο: τι έγινε, πώς λειτουργεί, γιατί είναι σημαντικό]",
"xml_concept_placeholder": "[κατηγορία-τύπου-γνώσης]",
"xml_file_placeholder": "[διαδρομή/προς/αρχείο]",
"xml_summary_request_placeholder": "[Σύντομος τίτλος που περιγράφει το αίτημα του χρήστη και την ουσία του τι συζητήθηκε/έγινε]",
"xml_summary_investigated_placeholder": "[Τι έχει εξερευνηθεί μέχρι στιγμής; Τι έχει εξεταστεί;]",
"xml_summary_learned_placeholder": "[Τι έχετε μάθει για το πώς λειτουργούν τα πράγματα;]",
"xml_summary_completed_placeholder": "[Ποια εργασία έχει ολοκληρωθεί μέχρι στιγμής; Τι έχει παραδοθεί ή αλλάξει;]",
"xml_summary_next_steps_placeholder": "[Σε τι εργάζεστε ενεργά ή σχεδιάζετε να εργαστείτε στη συνέχεια σε αυτή τη συνεδρία;]",
"xml_summary_notes_placeholder": "[Πρόσθετες γνώσεις ή παρατηρήσεις σχετικά με την τρέχουσα πρόοδο]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in ελληνικά",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in ελληνικά"
}
}

24
plugin/modes/code--es.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Spanish)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in español",
"xml_title_placeholder": "[**title**: Título breve que captura la acción o tema principal]",
"xml_subtitle_placeholder": "[**subtitle**: Explicación de una oración (máximo 24 palabras)]",
"xml_fact_placeholder": "[Declaración concisa y autónoma]",
"xml_narrative_placeholder": "[**narrative**: Contexto completo: Qué se hizo, cómo funciona, por qué es importante]",
"xml_concept_placeholder": "[categoría-de-tipo-de-conocimiento]",
"xml_file_placeholder": "[ruta/al/archivo]",
"xml_summary_request_placeholder": "[Título breve que captura la solicitud del usuario Y la sustancia de lo que se discutió/hizo]",
"xml_summary_investigated_placeholder": "[¿Qué se ha explorado hasta ahora? ¿Qué se examinó?]",
"xml_summary_learned_placeholder": "[¿Qué has aprendido sobre cómo funcionan las cosas?]",
"xml_summary_completed_placeholder": "[¿Qué trabajo se ha completado hasta ahora? ¿Qué se ha enviado o cambiado?]",
"xml_summary_next_steps_placeholder": "[¿En qué estás trabajando activamente o planeas trabajar a continuación en esta sesión?]",
"xml_summary_notes_placeholder": "[Información adicional u observaciones sobre el progreso actual]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in español",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in español"
}
}

24
plugin/modes/code--fi.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Finnish)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in suomi",
"xml_title_placeholder": "[**title**: Lyhyt otsikko, joka kuvaa päätehtävää tai aihetta]",
"xml_subtitle_placeholder": "[**subtitle**: Yhden lauseen selitys (enintään 24 sanaa)]",
"xml_fact_placeholder": "[Tiivis, itsenäinen väite]",
"xml_narrative_placeholder": "[**narrative**: Täydellinen konteksti: mitä tehtiin, miten se toimii, miksi se on tärkeää]",
"xml_concept_placeholder": "[tietolaji-kategoria]",
"xml_file_placeholder": "[polku/tiedostoon]",
"xml_summary_request_placeholder": "[Lyhyt otsikko, joka kuvaa käyttäjän pyynnön ja keskustellun/tehdyn asian ytimen]",
"xml_summary_investigated_placeholder": "[Mitä on tutkittu tähän mennessä? Mitä on tarkasteltu?]",
"xml_summary_learned_placeholder": "[Mitä olet oppinut siitä, miten asiat toimivat?]",
"xml_summary_completed_placeholder": "[Mikä työ on valmistunut tähän mennessä? Mitä on toimitettu tai muutettu?]",
"xml_summary_next_steps_placeholder": "[Mitä työstät aktiivisesti tai aiot työstää seuraavaksi tässä istunnossa?]",
"xml_summary_notes_placeholder": "[Lisätietoja tai havaintoja nykyisestä edistymisestä]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in suomi",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in suomi"
}
}

24
plugin/modes/code--fr.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (French)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in français",
"xml_title_placeholder": "[**title**: Titre court capturant l'action ou le sujet principal]",
"xml_subtitle_placeholder": "[**subtitle**: Explication en une phrase (maximum 24 mots)]",
"xml_fact_placeholder": "[Déclaration concise et autonome]",
"xml_narrative_placeholder": "[**narrative**: Contexte complet : Ce qui a été fait, comment cela fonctionne, pourquoi c'est important]",
"xml_concept_placeholder": "[catégorie-de-type-de-connaissance]",
"xml_file_placeholder": "[chemin/vers/fichier]",
"xml_summary_request_placeholder": "[Titre court capturant la demande de l'utilisateur ET la substance de ce qui a été discuté/fait]",
"xml_summary_investigated_placeholder": "[Qu'est-ce qui a été exploré jusqu'à présent ? Qu'est-ce qui a été examiné ?]",
"xml_summary_learned_placeholder": "[Qu'avez-vous appris sur le fonctionnement des choses ?]",
"xml_summary_completed_placeholder": "[Quel travail a été complété jusqu'à présent ? Qu'est-ce qui a été livré ou modifié ?]",
"xml_summary_next_steps_placeholder": "[Sur quoi travaillez-vous activement ou prévoyez-vous de travailler ensuite dans cette session ?]",
"xml_summary_notes_placeholder": "[Informations supplémentaires ou observations sur la progression actuelle]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in français",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in français"
}
}

24
plugin/modes/code--he.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Hebrew)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in עברית",
"xml_title_placeholder": "[**title**: כותרת קצרה שמתארת את הפעולה או הנושא המרכזי]",
"xml_subtitle_placeholder": "[**subtitle**: הסבר במשפט אחד (מקסימום 24 מילים)]",
"xml_fact_placeholder": "[הצהרה תמציתית ועצמאית]",
"xml_narrative_placeholder": "[**narrative**: הקשר מלא: מה נעשה, איך זה עובד, למה זה חשוב]",
"xml_concept_placeholder": "[קטגוריית-סוג-ידע]",
"xml_file_placeholder": "[נתיב/לקובץ]",
"xml_summary_request_placeholder": "[כותרת קצרה שמתארת את בקשת המשתמש ואת מהות מה שנדון/נעשה]",
"xml_summary_investigated_placeholder": "[מה נחקר עד כה? מה נבדק?]",
"xml_summary_learned_placeholder": "[מה למדת על איך דברים עובדים?]",
"xml_summary_completed_placeholder": "[איזו עבודה הושלמה עד כה? מה נשלח או שונה?]",
"xml_summary_next_steps_placeholder": "[על מה אתה עובד באופן פעיל או מתכנן לעבוד הלאה בסשן הזה?]",
"xml_summary_notes_placeholder": "[תובנות או הערות נוספות על ההתקדמות הנוכחית]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in עברית",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in עברית"
}
}

24
plugin/modes/code--hi.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Hindi)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in हिन्दी",
"xml_title_placeholder": "[**title**: मुख्य कार्रवाई या विषय को दर्शाने वाला संक्षिप्त शीर्षक]",
"xml_subtitle_placeholder": "[**subtitle**: एक वाक्य में स्पष्टीकरण (अधिकतम 24 शब्द)]",
"xml_fact_placeholder": "[संक्षिप्त, स्व-निहित कथन]",
"xml_narrative_placeholder": "[**narrative**: पूर्ण संदर्भ: क्या किया गया, यह कैसे काम करता है, यह क्यों महत्वपूर्ण है]",
"xml_concept_placeholder": "[ज्ञान-प्रकार-श्रेणी]",
"xml_file_placeholder": "[फ़ाइल/का/पथ]",
"xml_summary_request_placeholder": "[संक्षिप्त शीर्षक जो उपयोगकर्ता के अनुरोध और चर्चा/किए गए कार्य के सार को दर्शाता है]",
"xml_summary_investigated_placeholder": "[अब तक क्या खोजा गया है? क्या समीक्षा की गई है?]",
"xml_summary_learned_placeholder": "[आपने चीजों के काम करने के तरीके के बारे में क्या सीखा?]",
"xml_summary_completed_placeholder": "[अब तक कौन सा काम पूरा हुआ है? क्या भेजा गया या बदला गया?]",
"xml_summary_next_steps_placeholder": "[इस सत्र में आप सक्रिय रूप से किस पर काम कर रहे हैं या आगे काम करने की योजना बना रहे हैं?]",
"xml_summary_notes_placeholder": "[वर्तमान प्रगति पर अतिरिक्त अंतर्दृष्टि या टिप्पणियां]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in हिन्दी",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in हिन्दी"
}
}

24
plugin/modes/code--hu.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Hungarian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in magyar",
"xml_title_placeholder": "[**title**: Rövid cím, amely megragadja a fő műveletet vagy témát]",
"xml_subtitle_placeholder": "[**subtitle**: Egyetlen mondatos magyarázat (maximum 24 szó)]",
"xml_fact_placeholder": "[Tömör, önálló kijelentés]",
"xml_narrative_placeholder": "[**narrative**: Teljes kontextus: mit csináltak, hogyan működik, miért fontos]",
"xml_concept_placeholder": "[tudástípus-kategória]",
"xml_file_placeholder": "[fájl/elérési/útja]",
"xml_summary_request_placeholder": "[Rövid cím, amely megragadja a felhasználó kérését és a megvitatott/végrehajtott dolgok lényegét]",
"xml_summary_investigated_placeholder": "[Mit vizsgáltak meg eddig? Mit tekintettek át?]",
"xml_summary_learned_placeholder": "[Mit tanultál arról, hogyan működnek a dolgok?]",
"xml_summary_completed_placeholder": "[Milyen munka fejeződött be eddig? Mit szállítottak le vagy változtattak meg?]",
"xml_summary_next_steps_placeholder": "[Min dolgozol aktívan, vagy min tervezel dolgozni ebben az ülésben?]",
"xml_summary_notes_placeholder": "[További meglátások vagy megfigyelések a jelenlegi előrehaladásról]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in magyar",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in magyar"
}
}

24
plugin/modes/code--id.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Indonesian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Bahasa Indonesia",
"xml_title_placeholder": "[**title**: Judul singkat yang menangkap tindakan atau topik inti]",
"xml_subtitle_placeholder": "[**subtitle**: Penjelasan satu kalimat (maksimal 24 kata)]",
"xml_fact_placeholder": "[Pernyataan ringkas dan mandiri]",
"xml_narrative_placeholder": "[**narrative**: Konteks lengkap: apa yang dilakukan, bagaimana cara kerjanya, mengapa penting]",
"xml_concept_placeholder": "[kategori-jenis-pengetahuan]",
"xml_file_placeholder": "[jalur/ke/file]",
"xml_summary_request_placeholder": "[Judul singkat yang menangkap permintaan pengguna dan inti dari apa yang didiskusikan/dilakukan]",
"xml_summary_investigated_placeholder": "[Apa yang telah dieksplorasi sejauh ini? Apa yang telah diperiksa?]",
"xml_summary_learned_placeholder": "[Apa yang Anda pelajari tentang cara kerja sesuatu?]",
"xml_summary_completed_placeholder": "[Pekerjaan apa yang telah diselesaikan sejauh ini? Apa yang telah dikirim atau diubah?]",
"xml_summary_next_steps_placeholder": "[Apa yang sedang Anda kerjakan secara aktif atau rencanakan untuk dikerjakan selanjutnya dalam sesi ini?]",
"xml_summary_notes_placeholder": "[Wawasan atau pengamatan tambahan tentang kemajuan saat ini]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Bahasa Indonesia",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in Bahasa Indonesia"
}
}

24
plugin/modes/code--it.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Italian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in italiano",
"xml_title_placeholder": "[**title**: Titolo breve che cattura l'azione o l'argomento principale]",
"xml_subtitle_placeholder": "[**subtitle**: Spiegazione in una frase (massimo 24 parole)]",
"xml_fact_placeholder": "[Dichiarazione concisa e autonoma]",
"xml_narrative_placeholder": "[**narrative**: Contesto completo: cosa è stato fatto, come funziona, perché è importante]",
"xml_concept_placeholder": "[categoria-tipo-conoscenza]",
"xml_file_placeholder": "[percorso/del/file]",
"xml_summary_request_placeholder": "[Titolo breve che cattura la richiesta dell'utente e l'essenza di ciò che è stato discusso/fatto]",
"xml_summary_investigated_placeholder": "[Cosa è stato esplorato finora? Cosa è stato esaminato?]",
"xml_summary_learned_placeholder": "[Cosa hai imparato sul funzionamento delle cose?]",
"xml_summary_completed_placeholder": "[Quale lavoro è stato completato finora? Cosa è stato consegnato o modificato?]",
"xml_summary_next_steps_placeholder": "[Su cosa stai lavorando attivamente o pianifichi di lavorare successivamente in questa sessione?]",
"xml_summary_notes_placeholder": "[Ulteriori intuizioni o osservazioni sul progresso attuale]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in italiano",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in italiano"
}
}

24
plugin/modes/code--ja.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Japanese)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in 日本語",
"xml_title_placeholder": "[**title**: コアとなるアクションやトピックを捉えた短いタイトル]",
"xml_subtitle_placeholder": "[**subtitle**: 一文での説明（最大24単語）]",
"xml_fact_placeholder": "[簡潔で自己完結した記述]",
"xml_narrative_placeholder": "[**narrative**: 完全なコンテキスト：何が行われたか、どのように機能するか、なぜ重要か]",
"xml_concept_placeholder": "[知識タイプのカテゴリ]",
"xml_file_placeholder": "[ファイルへのパス]",
"xml_summary_request_placeholder": "[ユーザーのリクエストと議論/実行された内容の本質を捉えた短いタイトル]",
"xml_summary_investigated_placeholder": "[これまでに何を調査しましたか？何を検証しましたか？]",
"xml_summary_learned_placeholder": "[仕組みについて何を学びましたか？]",
"xml_summary_completed_placeholder": "[これまでにどんな作業が完了しましたか？何が出荷または変更されましたか？]",
"xml_summary_next_steps_placeholder": "[このセッションで次に積極的に取り組んでいる、または取り組む予定のことは何ですか？]",
"xml_summary_notes_placeholder": "[現在の進捗に関する追加の洞察や観察]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in 日本語",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in 日本語"
}
}

24
plugin/modes/code--ko.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Korean)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in 한국어",
"xml_title_placeholder": "[**title**: 핵심 작업이나 주제를 포착하는 짧은 제목]",
"xml_subtitle_placeholder": "[**subtitle**: 한 문장 설명 (최대 24단어)]",
"xml_fact_placeholder": "[간결하고 독립적인 진술]",
"xml_narrative_placeholder": "[**narrative**: 전체 컨텍스트: 무엇을 했는지, 어떻게 작동하는지, 왜 중요한지]",
"xml_concept_placeholder": "[지식 유형 카테고리]",
"xml_file_placeholder": "[파일 경로]",
"xml_summary_request_placeholder": "[사용자의 요청과 논의/수행된 내용의 본질을 포착하는 짧은 제목]",
"xml_summary_investigated_placeholder": "[지금까지 무엇을 탐색했습니까? 무엇을 검토했습니까?]",
"xml_summary_learned_placeholder": "[작동 방식에 대해 무엇을 배웠습니까?]",
"xml_summary_completed_placeholder": "[지금까지 어떤 작업이 완료되었습니까? 무엇이 배포되거나 변경되었습니까?]",
"xml_summary_next_steps_placeholder": "[이 세션에서 다음으로 적극적으로 작업 중이거나 작업할 계획인 것은 무엇입니까?]",
"xml_summary_notes_placeholder": "[현재 진행 상황에 대한 추가 통찰이나 관찰]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in 한국어",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in 한국어"
}
}

24
plugin/modes/code--nl.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Dutch)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Nederlands",
"xml_title_placeholder": "[**title**: Korte titel die de kernactie of het onderwerp beschrijft]",
"xml_subtitle_placeholder": "[**subtitle**: Uitleg in één zin (maximaal 24 woorden)]",
"xml_fact_placeholder": "[Beknopte, op zichzelf staande verklaring]",
"xml_narrative_placeholder": "[**narrative**: Volledige context: wat er is gedaan, hoe het werkt, waarom het belangrijk is]",
"xml_concept_placeholder": "[kennistype-categorie]",
"xml_file_placeholder": "[pad/naar/bestand]",
"xml_summary_request_placeholder": "[Korte titel die het verzoek van de gebruiker en de essentie van wat is besproken/gedaan beschrijft]",
"xml_summary_investigated_placeholder": "[Wat is er tot nu toe onderzocht? Wat is er bekeken?]",
"xml_summary_learned_placeholder": "[Wat heb je geleerd over hoe dingen werken?]",
"xml_summary_completed_placeholder": "[Welk werk is er tot nu toe voltooid? Wat is er opgeleverd of gewijzigd?]",
"xml_summary_next_steps_placeholder": "[Waar werk je actief aan of plan je verder aan te werken in deze sessie?]",
"xml_summary_notes_placeholder": "[Aanvullende inzichten of observaties over de huidige voortgang]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Nederlands",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in Nederlands"
}
}

24
plugin/modes/code--no.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Norwegian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in norsk",
"xml_title_placeholder": "[**title**: Kort tittel som fanger kjernehandlingen eller emnet]",
"xml_subtitle_placeholder": "[**subtitle**: Forklaring i én setning (maksimalt 24 ord)]",
"xml_fact_placeholder": "[Kortfattet, selvstendig uttalelse]",
"xml_narrative_placeholder": "[**narrative**: Full kontekst: hva som ble gjort, hvordan det fungerer, hvorfor det er viktig]",
"xml_concept_placeholder": "[kunnskapstype-kategori]",
"xml_file_placeholder": "[sti/til/fil]",
"xml_summary_request_placeholder": "[Kort tittel som fanger brukerens forespørsel og essensen av hva som ble diskutert/gjort]",
"xml_summary_investigated_placeholder": "[Hva har blitt utforsket så langt? Hva har blitt gjennomgått?]",
"xml_summary_learned_placeholder": "[Hva har du lært om hvordan ting fungerer?]",
"xml_summary_completed_placeholder": "[Hvilket arbeid har blitt fullført så langt? Hva har blitt levert eller endret?]",
"xml_summary_next_steps_placeholder": "[Hva jobber du aktivt med eller planlegger å jobbe med videre i denne økten?]",
"xml_summary_notes_placeholder": "[Ytterligere innsikter eller observasjoner om gjeldende fremgang]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in norsk",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in norsk"
}
}

24
plugin/modes/code--pl.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Polish)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in polski",
"xml_title_placeholder": "[**title**: Krótki tytuł opisujący główne działanie lub temat]",
"xml_subtitle_placeholder": "[**subtitle**: Wyjaśnienie w jednym zdaniu (maksymalnie 24 słowa)]",
"xml_fact_placeholder": "[Zwięzłe, samodzielne stwierdzenie]",
"xml_narrative_placeholder": "[**narrative**: Pełny kontekst: co zostało zrobione, jak to działa, dlaczego jest ważne]",
"xml_concept_placeholder": "[kategoria-typu-wiedzy]",
"xml_file_placeholder": "[ścieżka/do/pliku]",
"xml_summary_request_placeholder": "[Krótki tytuł opisujący żądanie użytkownika i istotę tego, co zostało omówione/zrobione]",
"xml_summary_investigated_placeholder": "[Co zostało zbadane do tej pory? Co zostało sprawdzone?]",
"xml_summary_learned_placeholder": "[Czego się nauczyłeś o tym, jak działają rzeczy?]",
"xml_summary_completed_placeholder": "[Jaka praca została ukończona do tej pory? Co zostało wdrożone lub zmienione?]",
"xml_summary_next_steps_placeholder": "[Nad czym aktywnie pracujesz lub planujesz pracować w tej sesji?]",
"xml_summary_notes_placeholder": "[Dodatkowe spostrzeżenia lub uwagi dotyczące obecnego postępu]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in polski",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in polski"
}
}

24
plugin/modes/code--pt-br.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Brazilian Portuguese)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in português",
"xml_title_placeholder": "[**title**: Título curto capturando a ação principal ou tópico]",
"xml_subtitle_placeholder": "[**subtitle**: Explicação em uma frase (máximo 24 palavras)]",
"xml_fact_placeholder": "[Declaração concisa e autônoma]",
"xml_narrative_placeholder": "[**narrative**: Contexto completo: O que foi feito, como funciona, por que é importante]",
"xml_concept_placeholder": "[categoria-de-tipo-de-conhecimento]",
"xml_file_placeholder": "[caminho/para/arquivo]",
"xml_summary_request_placeholder": "[Título curto capturando a solicitação do usuário E a substância do que foi discutido/feito]",
"xml_summary_investigated_placeholder": "[O que foi explorado até agora? O que foi examinado?]",
"xml_summary_learned_placeholder": "[O que você aprendeu sobre como as coisas funcionam?]",
"xml_summary_completed_placeholder": "[Que trabalho foi concluído até agora? O que foi entregue ou alterado?]",
"xml_summary_next_steps_placeholder": "[No que você está trabalhando ativamente ou planeja trabalhar a seguir nesta sessão?]",
"xml_summary_notes_placeholder": "[Insights adicionais ou observações sobre o progresso atual]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in português",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in português"
}
}

24
plugin/modes/code--ro.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Romanian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in română",
"xml_title_placeholder": "[**title**: Titlu scurt care surprinde acțiunea sau subiectul principal]",
"xml_subtitle_placeholder": "[**subtitle**: Explicație într-o propoziție (maxim 24 cuvinte)]",
"xml_fact_placeholder": "[Afirmație concisă și autonomă]",
"xml_narrative_placeholder": "[**narrative**: Context complet: ce s-a făcut, cum funcționează, de ce este important]",
"xml_concept_placeholder": "[categorie-tip-cunoștințe]",
"xml_file_placeholder": "[cale/către/fișier]",
"xml_summary_request_placeholder": "[Titlu scurt care surprinde solicitarea utilizatorului și esența a ceea ce s-a discutat/făcut]",
"xml_summary_investigated_placeholder": "[Ce s-a explorat până acum? Ce s-a revizuit?]",
"xml_summary_learned_placeholder": "[Ce ai învățat despre modul în care funcționează lucrurile?]",
"xml_summary_completed_placeholder": "[Ce muncă a fost finalizată până acum? Ce a fost livrat sau modificat?]",
"xml_summary_next_steps_placeholder": "[La ce lucrezi activ sau plănuiești să lucrezi în continuare în această sesiune?]",
"xml_summary_notes_placeholder": "[Informații suplimentare sau observații despre progresul curent]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in română",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in română"
}
}

24
plugin/modes/code--ru.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Russian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in русский",
"xml_title_placeholder": "[**title**: Краткое название, отражающее основное действие или тему]",
"xml_subtitle_placeholder": "[**subtitle**: Объяснение одним предложением (максимум 24 слова)]",
"xml_fact_placeholder": "[Краткое, самостоятельное утверждение]",
"xml_narrative_placeholder": "[**narrative**: Полный контекст: Что было сделано, как это работает, почему это важно]",
"xml_concept_placeholder": "[категория-типа-знания]",
"xml_file_placeholder": "[путь/к/файлу]",
"xml_summary_request_placeholder": "[Краткое название, отражающее запрос пользователя И суть того, что обсуждалось/делалось]",
"xml_summary_investigated_placeholder": "[Что было исследовано до сих пор? Что было рассмотрено?]",
"xml_summary_learned_placeholder": "[Что вы узнали о том, как все работает?]",
"xml_summary_completed_placeholder": "[Какая работа была выполнена до сих пор? Что было отправлено или изменено?]",
"xml_summary_next_steps_placeholder": "[Над чем вы активно работаете или планируете работать дальше в этой сессии?]",
"xml_summary_notes_placeholder": "[Дополнительные наблюдения или замечания о текущем прогрессе]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in русский",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in русский"
}
}

24
plugin/modes/code--sv.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Swedish)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in svenska",
"xml_title_placeholder": "[**title**: Kort rubrik som fångar kärnåtgärden eller ämnet]",
"xml_subtitle_placeholder": "[**subtitle**: Förklaring i en mening (högst 24 ord)]",
"xml_fact_placeholder": "[Koncist, fristående påstående]",
"xml_narrative_placeholder": "[**narrative**: Fullständigt sammanhang: vad som gjordes, hur det fungerar, varför det är viktigt]",
"xml_concept_placeholder": "[kunskapstyp-kategori]",
"xml_file_placeholder": "[sökväg/till/fil]",
"xml_summary_request_placeholder": "[Kort rubrik som fångar användarens begäran och kärnan i vad som diskuterades/gjordes]",
"xml_summary_investigated_placeholder": "[Vad har utforskats hittills? Vad har granskats?]",
"xml_summary_learned_placeholder": "[Vad har du lärt dig om hur saker fungerar?]",
"xml_summary_completed_placeholder": "[Vilket arbete har slutförts hittills? Vad har levererats eller ändrats?]",
"xml_summary_next_steps_placeholder": "[Vad arbetar du aktivt med eller planerar att arbeta med härnäst i denna session?]",
"xml_summary_notes_placeholder": "[Ytterligare insikter eller observationer om nuvarande framsteg]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in svenska",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in svenska"
}
}

24
plugin/modes/code--th.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Thai)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in ภาษาไทย",
"xml_title_placeholder": "[**title**: ชื่อสั้นที่จับประเด็นหลักหรือหัวข้อ]",
"xml_subtitle_placeholder": "[**subtitle**: คำอธิบายหึ่งประโยค (สูงสุด 24 คำ)]",
"xml_fact_placeholder": "[ข้อความที่กระชับและสมบูรณ์ในตัวเอง]",
"xml_narrative_placeholder": "[**narrative**: บริบทเต็มรูปแบบ: สิ่งที่ทำ, วิธีการทำงาน, เหตุผลที่สำคัญ]",
"xml_concept_placeholder": "[หมวดหมู่ประเภทความรู้]",
"xml_file_placeholder": "[เส้นทาง/ไปยัง/ไฟล์]",
"xml_summary_request_placeholder": "[ชื่อสั้นที่จับคำขอของผู้ใช้และสาระสำคัญของสิ่งที่อภิปรายหรือทำ]",
"xml_summary_investigated_placeholder": "[สำรวจอะไรมาบ้างจนถึงตอนนี้? ตรวจสอบอะไรบ้าง?]",
"xml_summary_learned_placeholder": "[คุณได้เรียนรู้อะไรเกี่ยวกับวิธีการทำงานของสิ่งต่างๆ?]",
"xml_summary_completed_placeholder": "[งานอะไรเสร็จสมบูรณ์แล้วจนถึงตอนนี้? อะไรถูกส่งมอบหรือเปลี่ยนแปลง?]",
"xml_summary_next_steps_placeholder": "[คุณกำลังทำงานอะไรอย่างแข็งขันหรือวางแผนที่จะทำต่อไปในเซสชันนี้?]",
"xml_summary_notes_placeholder": "[ข้อมูลเชิงลึกเพิ่มเติมหรือข้อสังเกตเกี่ยวกับความคืบหน้าปัจจุบัน]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in ภาษาไทย",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in ภาษาไทย"
}
}

24
plugin/modes/code--tr.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Turkish)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Türkçe",
"xml_title_placeholder": "[**title**: Ana eylemi veya konuyu özetleyen kısa başlık]",
"xml_subtitle_placeholder": "[**subtitle**: Tek cümlelik açıklama (maksimum 24 kelime)]",
"xml_fact_placeholder": "[Kısa ve bağımsız ifade]",
"xml_narrative_placeholder": "[**narrative**: Tam bağlam: ne yapıldı, nasıl çalışıyor, neden önemli]",
"xml_concept_placeholder": "[bilgi-türü-kategorisi]",
"xml_file_placeholder": "[dosya/yolu]",
"xml_summary_request_placeholder": "[Kullanıcının talebini ve tartışılan/yapılan şeyin özünü özetleyen kısa başlık]",
"xml_summary_investigated_placeholder": "[Şu ana kadar ne araştırıldı? Ne incelendi?]",
"xml_summary_learned_placeholder": "[İşlerin nasıl çalıştığı hakkında ne öğrendiniz?]",
"xml_summary_completed_placeholder": "[Şu ana kadar hangi iş tamamlandı? Ne gönderildi veya değiştirildi?]",
"xml_summary_next_steps_placeholder": "[Bu oturumda aktif olarak üzerinde çalıştığınız veya çalışmayı planladığınız şey nedir?]",
"xml_summary_notes_placeholder": "[Mevcut ilerleme hakkında ek görüşler veya gözlemler]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in Türkçe",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in Türkçe"
}
}

24
plugin/modes/code--uk.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Ukrainian)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in українська",
"xml_title_placeholder": "[**title**: Короткий заголовок, що описує основну дію або тему]",
"xml_subtitle_placeholder": "[**subtitle**: Пояснення в одному реченні (максимум 24 слова)]",
"xml_fact_placeholder": "[Стисле, самодостатнє твердження]",
"xml_narrative_placeholder": "[**narrative**: Повний контекст: що було зроблено, як це працює, чому це важливо]",
"xml_concept_placeholder": "[категорія-типу-знань]",
"xml_file_placeholder": "[шлях/до/файлу]",
"xml_summary_request_placeholder": "[Короткий заголовок, що описує запит користувача та суть того, що обговорювалося/робилося]",
"xml_summary_investigated_placeholder": "[Що досліджено на даний момент? Що переглянуто?]",
"xml_summary_learned_placeholder": "[Що ви дізналися про те, як працюють речі?]",
"xml_summary_completed_placeholder": "[Яка робота завершена на даний момент? Що було відправлено або змінено?]",
"xml_summary_next_steps_placeholder": "[Над чим ви активно працюєте або плануєте працювати далі в цій сесії?]",
"xml_summary_notes_placeholder": "[Додаткові висновки або спостереження щодо поточного прогресу]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in українська",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in українська"
}
}

24
plugin/modes/code--vi.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Vietnamese)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in tiếng Việt",
"xml_title_placeholder": "[**title**: Tiêu đề ngắn gọn nắm bắt hành động hoặc chủ đề chính]",
"xml_subtitle_placeholder": "[**subtitle**: Giải thích một câu (tối đa 24 từ)]",
"xml_fact_placeholder": "[Tuyên bố ngắn gọn, độc lập]",
"xml_narrative_placeholder": "[**narrative**: Bối cảnh đầy đủ: Đã làm gì, hoạt động như thế nào, tại sao quan trọng]",
"xml_concept_placeholder": "[danh-mục-loại-kiến-thức]",
"xml_file_placeholder": "[đường/dẫn/tới/tệp]",
"xml_summary_request_placeholder": "[Tiêu đề ngắn gọn nắm bắt yêu cầu của người dùng VÀ nội dung của những gì đã được thảo luận/thực hiện]",
"xml_summary_investigated_placeholder": "[Đã khám phá những gì cho đến nay? Đã kiểm tra những gì?]",
"xml_summary_learned_placeholder": "[Bạn đã học được gì về cách mọi thứ hoạt động?]",
"xml_summary_completed_placeholder": "[Công việc nào đã được hoàn thành cho đến nay? Những gì đã được chuyển giao hoặc thay đổi?]",
"xml_summary_next_steps_placeholder": "[Bạn đang tích cực làm việc hoặc lên kế hoạch làm việc tiếp theo trong phiên này là gì?]",
"xml_summary_notes_placeholder": "[Thông tin chi tiết bổ sung hoặc quan sát về tiến độ hiện tại]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in tiếng Việt",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in tiếng Việt"
}
}

24
plugin/modes/code--zh.json Normal file
View File

@@ -0,0 +1,24 @@
{
"name": "Code Development (Chinese)",
"prompts": {
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!\n\nLANGUAGE REQUIREMENTS: Please write the observation data in 中文",
"xml_title_placeholder": "[**title**: 捕捉核心行动或主题的简短标题]",
"xml_subtitle_placeholder": "[**subtitle**: 一句话解释（最多24个单词）]",
"xml_fact_placeholder": "[简洁、独立的陈述]",
"xml_narrative_placeholder": "[**narrative**: 完整背景：做了什么、如何工作、为什么重要]",
"xml_concept_placeholder": "[知识类型类别]",
"xml_file_placeholder": "[文件路径]",
"xml_summary_request_placeholder": "[捕捉用户请求和讨论/完成内容实质的简短标题]",
"xml_summary_investigated_placeholder": "[到目前为止探索了什么？检查了什么？]",
"xml_summary_learned_placeholder": "[你了解到了什么工作原理？]",
"xml_summary_completed_placeholder": "[到目前为止完成了什么工作？发布或更改了什么？]",
"xml_summary_next_steps_placeholder": "[在此会话中，你正在积极处理或计划接下来处理什么？]",
"xml_summary_notes_placeholder": "[关于当前进度的其他见解或观察]",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.\n\nLANGUAGE REQUIREMENTS: Please write the observation data in 中文",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!\n\nLANGUAGE REQUIREMENTS: Please write ALL summary content (request, investigated, learned, completed, next_steps, notes) in 中文"
}
}

125
plugin/modes/code.json Normal file
View File

@@ -0,0 +1,125 @@
{
"name": "Code Development",
"description": "Software development and engineering work",
"version": "1.0.0",
"observation_types": [
{
"id": "bugfix",
"label": "Bug Fix",
"description": "Something was broken, now fixed",
"emoji": "🔴",
"work_emoji": "🛠️"
},
{
"id": "feature",
"label": "Feature",
"description": "New capability or functionality added",
"emoji": "🟣",
"work_emoji": "🛠️"
},
{
"id": "refactor",
"label": "Refactor",
"description": "Code restructured, behavior unchanged",
"emoji": "🔄",
"work_emoji": "🛠️"
},
{
"id": "change",
"label": "Change",
"description": "Generic modification (docs, config, misc)",
"emoji": "✅",
"work_emoji": "🛠️"
},
{
"id": "discovery",
"label": "Discovery",
"description": "Learning about existing system",
"emoji": "🔵",
"work_emoji": "🔍"
},
{
"id": "decision",
"label": "Decision",
"description": "Architectural/design choice with rationale",
"emoji": "⚖️",
"work_emoji": "⚖️"
}
],
"observation_concepts": [
{
"id": "how-it-works",
"label": "How It Works",
"description": "Understanding mechanisms"
},
{
"id": "why-it-exists",
"label": "Why It Exists",
"description": "Purpose or rationale"
},
{
"id": "what-changed",
"label": "What Changed",
"description": "Modifications made"
},
{
"id": "problem-solution",
"label": "Problem-Solution",
"description": "Issues and their fixes"
},
{
"id": "gotcha",
"label": "Gotcha",
"description": "Traps or edge cases"
},
{
"id": "pattern",
"label": "Pattern",
"description": "Reusable approach"
},
{
"id": "trade-off",
"label": "Trade-Off",
"description": "Pros/cons of a decision"
}
],
"prompts": {
"system_identity": "You are a Claude-Mem, a specialized observer tool for creating searchable memory FOR FUTURE SESSIONS.\n\nCRITICAL: Record what was LEARNED/BUILT/FIXED/DEPLOYED/CONFIGURED, not what you (the observer) are doing.\n\nYou do not have access to tools. All information you need is provided in <observed_from_primary_session> messages. Create observations from what you observe - no investigation needed.",
"spatial_awareness": "SPATIAL AWARENESS: Tool executions include the working directory (tool_cwd) to help you understand:\n- Which repository/project is being worked on\n- Where files are located relative to the project root\n- How to match requested paths to actual execution paths",
"observer_role": "Your job is to monitor a different Claude Code session happening RIGHT NOW, with the goal of creating observations and progress summaries as the work is being done LIVE by the user. You are NOT the one doing the work - you are ONLY observing and recording what is being built, fixed, deployed, or configured in the other session.",
"recording_focus": "WHAT TO RECORD\n--------------\nFocus on deliverables and capabilities:\n- What the system NOW DOES differently (new capabilities)\n- What shipped to users/production (features, fixes, configs, docs)\n- Changes in technical domains (auth, data, UI, infra, DevOps, docs)\n\nUse verbs like: implemented, fixed, deployed, configured, migrated, optimized, added, refactored\n\n✅ GOOD EXAMPLES (describes what was built):\n- \"Authentication now supports OAuth2 with PKCE flow\"\n- \"Deployment pipeline runs canary releases with auto-rollback\"\n- \"Database indexes optimized for common query patterns\"\n\n❌ BAD EXAMPLES (describes observation process - DO NOT DO THIS):\n- \"Analyzed authentication implementation and stored findings\"\n- \"Tracked deployment steps and logged outcomes\"\n- \"Monitored database performance and recorded metrics\"",
"skip_guidance": "WHEN TO SKIP\n------------\nSkip routine operations:\n- Empty status checks\n- Package installations with no errors\n- Simple file listings\n- Repetitive operations you've already documented\n- If file related research comes back as empty or not found\n- **No output necessary if skipping.**",
"type_guidance": "**type**: MUST be EXACTLY one of these 6 options (no other values allowed):\n - bugfix: something was broken, now fixed\n - feature: new capability or functionality added\n - refactor: code restructured, behavior unchanged\n - change: generic modification (docs, config, misc)\n - discovery: learning about existing system\n - decision: architectural/design choice with rationale",
"concept_guidance": "**concepts**: 2-5 knowledge-type categories. MUST use ONLY these exact keywords:\n - how-it-works: understanding mechanisms\n - why-it-exists: purpose or rationale\n - what-changed: modifications made\n - problem-solution: issues and their fixes\n - gotcha: traps or edge cases\n - pattern: reusable approach\n - trade-off: pros/cons of a decision\n\n IMPORTANT: Do NOT include the observation type (change/discovery/decision) as a concept.\n Types and concepts are separate dimensions.",
"field_guidance": "**facts**: Concise, self-contained statements\nEach fact is ONE piece of information\n No pronouns - each fact must stand alone\n Include specific details: filenames, functions, values\n\n**files**: All files touched (full paths from project root)",
"output_format_header": "OUTPUT FORMAT\n-------------\nOutput observations using this XML structure:",
"format_examples": "",
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!",
"xml_title_placeholder": "[**title**: Short title capturing the core action or topic]",
"xml_subtitle_placeholder": "[**subtitle**: One sentence explanation (max 24 words)]",
"xml_fact_placeholder": "[Concise, self-contained statement]",
"xml_narrative_placeholder": "[**narrative**: Full context: What was done, how it works, why it matters]",
"xml_concept_placeholder": "[knowledge-type-category]",
"xml_file_placeholder": "[path/to/file]",
"xml_summary_request_placeholder": "[Short title capturing the user's request AND the substance of what was discussed/done]",
"xml_summary_investigated_placeholder": "[What has been explored so far? What was examined?]",
"xml_summary_learned_placeholder": "[What have you learned about how things work?]",
"xml_summary_completed_placeholder": "[What work has been completed so far? What has shipped or changed?]",
"xml_summary_next_steps_placeholder": "[What are you actively working on or planning to work on next in this session?]",
"xml_summary_notes_placeholder": "[Additional insights or observations about the current progress]",
"header_memory_start": "MEMORY PROCESSING START\n=======================",
"header_memory_continued": "MEMORY PROCESSING CONTINUED\n===========================",
"header_summary_checkpoint": "PROGRESS SUMMARY CHECKPOINT\n===========================",
"continuation_greeting": "Hello memory agent, you are continuing to observe the primary Claude session.",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below.",
"summary_instruction": "Write progress notes of what was done, what was learned, and what's next. This is a checkpoint to capture progress so far. The session is ongoing - you may receive more requests and tool executions after this summary. Write \"next_steps\" as the current trajectory of work (what's actively being worked on or coming up next), not as post-session future work. Always write at least a minimal summary explaining current progress, even if work is still in early stages, so that users see a summary output tied to each request.",
"summary_context_label": "Claude's Full Response to User:",
"summary_format_instruction": "Respond in this XML format:",
"summary_footer": "IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.\n\nThank you, this summary will be very useful for keeping track of our progress!"
}
}

115
plugin/modes/email-investigation.json Normal file
View File

@@ -0,0 +1,115 @@
{
"name": "Email Investigation",
"description": "RAGTIME-style email fraud investigation",
"version": "1.0.0",
"observation_types": [
{
"id": "entity",
"label": "Entity Discovery",
"description": "New person, organization, or email address identified",
"emoji": "👤",
"work_emoji": "🔍"
},
{
"id": "relationship",
"label": "Relationship",
"description": "Connection between entities discovered",
"emoji": "🔗",
"work_emoji": "🔍"
},
{
"id": "timeline-event",
"label": "Timeline Event",
"description": "Time-stamped event in communication sequence",
"emoji": "📅",
"work_emoji": "🔍"
},
{
"id": "evidence",
"label": "Evidence",
"description": "Supporting documentation or proof discovered",
"emoji": "📄",
"work_emoji": "📋"
},
{
"id": "anomaly",
"label": "Anomaly",
"description": "Suspicious pattern or irregularity detected",
"emoji": "⚠️",
"work_emoji": "🔍"
},
{
"id": "conclusion",
"label": "Conclusion",
"description": "Investigative finding or determination",
"emoji": "⚖️",
"work_emoji": "⚖️"
}
],
"observation_concepts": [
{
"id": "who",
"label": "Who",
"description": "People and organizations involved"
},
{
"id": "when",
"label": "When",
"description": "Timing and sequence of events"
},
{
"id": "what-happened",
"label": "What Happened",
"description": "Events and communications"
},
{
"id": "motive",
"label": "Motive",
"description": "Intent or purpose behind actions"
},
{
"id": "red-flag",
"label": "Red Flag",
"description": "Warning signs of fraud or deception"
},
{
"id": "corroboration",
"label": "Corroboration",
"description": "Evidence supporting a claim"
}
],
"prompts": {
"system_identity": "You are a Claude-Mem, a specialized observer tool for creating searchable memory FOR FUTURE SESSIONS.\n\nCRITICAL: Record what was DISCOVERED/IDENTIFIED/REVEALED about the investigation, not what you (the observer) are doing.\n\nYou do not have access to tools. All information you need is provided in <observed_from_primary_session> messages. Create observations from what you observe - no investigation needed.",
"spatial_awareness": "SPATIAL AWARENESS: Tool executions include the working directory (tool_cwd) to help you understand:\n- Which investigation folder/project is being worked on\n- Where email files are located relative to the project root\n- How to match requested paths to actual execution paths",
"observer_role": "Your job is to monitor an email fraud investigation happening RIGHT NOW, with the goal of creating observations about entities, relationships, timeline events, and evidence as they are discovered LIVE. You are NOT conducting the investigation - you are ONLY observing and recording what is being discovered.",
"recording_focus": "WHAT TO RECORD\n--------------\nFocus on investigative elements:\n- New entities discovered (people, organizations, email addresses)\n- Relationships between entities (who contacted whom, organizational ties)\n- Timeline events (when things happened, communication sequences)\n- Evidence supporting or refuting fraud patterns\n- Anomalies or red flags detected\n\nUse verbs like: identified, discovered, revealed, detected, corroborated, confirmed\n\n✅ GOOD EXAMPLES (describes what was discovered):\n- \"John Smith <john@example.com> sent 15 emails requesting wire transfers\"\n- \"Timeline reveals communication pattern between suspicious accounts\"\n- \"Email headers show spoofed sender domain\"\n\n❌ BAD EXAMPLES (describes observation process - DO NOT DO THIS):\n- \"Analyzed email headers and recorded findings\"\n- \"Tracked communication patterns and logged results\"\n- \"Monitored entity relationships and stored data\"",
"skip_guidance": "WHEN TO SKIP\n------------\nSkip routine operations:\n- Empty searches with no results\n- Simple file listings\n- Repetitive operations you've already documented\n- If email research comes back as empty or not found\n- **No output necessary if skipping.**",
"type_guidance": "**type**: MUST be EXACTLY one of these options:\n - entity: new person, organization, or email address identified\n - relationship: connection between entities discovered\n - timeline-event: time-stamped event in communication sequence\n - evidence: supporting documentation or proof discovered\n - anomaly: suspicious pattern or irregularity detected\n - conclusion: investigative finding or determination",
"concept_guidance": "**concepts**: 2-5 knowledge-type categories. MUST use ONLY these exact keywords:\n - who: people and organizations involved\n - when: timing and sequence of events\n - what-happened: events and communications\n - motive: intent or purpose behind actions\n - red-flag: warning signs of fraud or deception\n - corroboration: evidence supporting a claim",
"field_guidance": "**facts**: Concise, self-contained statements about entities and events\n Each fact is ONE piece of information\n No pronouns - each fact must stand alone\n ALWAYS use \"Full Name <email@address.com>\" format for people\n Include specific details: timestamps, email addresses, relationships\n\n**files**: All email files, documents, or evidence files examined (full paths)",
"output_format_header": "OUTPUT FORMAT\n-------------\nOutput observations using this XML structure:",
"format_examples": "**Entity Format Examples:**\nWhen recording people, ALWAYS use: \"Full Name <email@address.com>\"\n\n<observation>\n <type>entity</type>\n <title>John Smith <john.smith@example.com> identified as sender</title>\n <facts>\n <fact>John Smith <john.smith@example.com> sent 15 emails to Jane Doe <jane@corp.com></fact>\n <fact>Email address john.smith@example.com registered to Acme Corp</fact>\n </facts>\n <narrative>John Smith <john.smith@example.com> appears frequently in the email chain...</narrative>\n</observation>",
"footer": "IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT investigation session, not this one.\n\nNever reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.\n\nRemember that we record these observations to help track investigation progress and keep important findings at the forefront! Thank you for your help!",
"xml_title_placeholder": "[**title**: Short title of the entity/event/finding]",
"xml_subtitle_placeholder": "[**subtitle**: Brief explanation (max 24 words)]",
"xml_fact_placeholder": "[Concise, self-contained statement using Full Name <email@address.com> format]",
"xml_narrative_placeholder": "[**narrative**: Full context: What was discovered, how it connects, why it matters]",
"xml_concept_placeholder": "[knowledge-type-category]",
"xml_file_placeholder": "[path/to/email/file]",
"xml_summary_request_placeholder": "[Short title capturing the investigation request AND what was discovered]",
"xml_summary_investigated_placeholder": "[What entities/emails/evidence have been examined?]",
"xml_summary_learned_placeholder": "[What have you learned about the case?]",
"xml_summary_completed_placeholder": "[What investigative work has been completed? What findings emerged?]",
"xml_summary_next_steps_placeholder": "[What investigation steps are you working on next?]",
"xml_summary_notes_placeholder": "[Additional insights or observations about the investigation progress]",
"header_memory_start": "INVESTIGATION MEMORY START\n==========================",
"header_memory_continued": "INVESTIGATION MEMORY CONTINUED\n==============================",
"header_summary_checkpoint": "INVESTIGATION SUMMARY CHECKPOINT\n================================",
"continuation_greeting": "Hello memory agent, you are continuing to observe the email fraud investigation session.",
"continuation_instruction": "IMPORTANT: Continue generating observations from tool use messages using the XML structure below."
}
}

14
plugin/scripts/cleanup-hook.js
View File

File diff suppressed because one or more lines are too long

282
plugin/scripts/context-generator.cjs
View File

File diff suppressed because one or more lines are too long

16
plugin/scripts/context-hook.js
View File

File diff suppressed because one or more lines are too long

10
plugin/scripts/mcp-server.cjs
View File

File diff suppressed because one or more lines are too long

16
plugin/scripts/new-hook.js
View File

File diff suppressed because one or more lines are too long

14
plugin/scripts/save-hook.js
View File

File diff suppressed because one or more lines are too long

22
plugin/scripts/summary-hook.js
View File

File diff suppressed because one or more lines are too long

38
plugin/scripts/user-message-hook.js
View File

File diff suppressed because one or more lines are too long

10
plugin/scripts/worker-cli.js
View File

File diff suppressed because one or more lines are too long

716
plugin/scripts/worker-service.cjs
View File

File diff suppressed because one or more lines are too long

BIN
plugin/skills/mem-search.zip
View File

Binary file not shown.

137
ragtime/LICENSE Normal file
View File

@@ -0,0 +1,137 @@
# PolyForm Noncommercial License 1.0.0
<https://polyformproject.org/licenses/noncommercial/1.0.0>
## Acceptance
In order to get any license under these terms, you must agree
to them as both strict obligations and conditions to all
your licenses.
## Copyright License
The licensor grants you a copyright license for the
software to do everything you might do with the software
that would otherwise infringe the licensor's copyright
in it for any permitted purpose. However, you may
only distribute the software according to [Distribution
License](#distribution-license) and make changes or new works
based on the software according to [Changes and New Works
License](#changes-and-new-works-license).
## Distribution License
The licensor grants you an additional copyright license
to distribute copies of the software. Your license
to distribute covers distributing the software with
changes and new works permitted by [Changes and New Works
License](#changes-and-new-works-license).
## Notices
You must ensure that anyone who gets a copy of any part of
the software from you also gets a copy of these terms or the
URL for them above, as well as copies of any plain-text lines
beginning with `Required Notice:` that the licensor provided
with the software. For example:
> Required Notice: Copyright Alex Newman (https://github.com/thedotmack)
## Changes and New Works License
The licensor grants you an additional copyright license to
make changes and new works based on the software for any
permitted purpose.
## Patent License
The licensor grants you a patent license for the software that
covers patent claims the licensor can license, or becomes able
to license, that you would infringe by using the software.
## Noncommercial Purposes
Any noncommercial purpose is a permitted purpose.
## Personal Uses
Personal use for research, experiment, and testing for
the benefit of public knowledge, personal study, private
entertainment, hobby projects, amateur pursuits, or religious
observance, without any anticipated commercial application,
is use for a permitted purpose.
## Noncommercial Organizations
Use by any charitable organization, educational institution,
public research organization, public safety or health
organization, environmental protection organization,
or government institution is use for a permitted purpose
regardless of the source of funding or obligations resulting
from the funding.
## Fair Use
You may have "fair use" rights for the software under the
law. These terms do not limit them.
## No Other Rights
These terms do not allow you to sublicense or transfer any of
your licenses to anyone else, or prevent the licensor from
granting licenses to anyone else. These terms do not imply
any other licenses.
## Patent Defense
If you make any written claim that the software infringes or
contributes to infringement of any patent, your patent license
for the software granted under these terms ends immediately. If
your company makes such a claim, your patent license ends
immediately for work on behalf of your company.
## Violations
The first time you are notified in writing that you have
violated any of these terms, or done anything with the software
not covered by your licenses, your licenses can nonetheless
continue if you come into full compliance with these terms,
and take practical steps to correct past violations, within
32 days of receiving notice. Otherwise, all your licenses
end immediately.
## No Liability
***As far as the law allows, the software comes as is, without
any warranty or condition, and the licensor will not be liable
to you for any damages arising out of these terms or the use
or nature of the software, under any kind of legal claim.***
## Definitions
The **licensor** is the individual or entity offering these
terms, and the **software** is the software the licensor makes
available under these terms.
**You** refers to the individual or entity agreeing to these
terms.
**Your company** is any legal entity, sole proprietorship,
or other kind of organization that you work for, plus all
organizations that have control over, are under the control of,
or are under common control with that organization. **Control**
means ownership of substantially all the assets of an entity,
or the power to direct its management and policies by vote,
contract, or otherwise. Control can be direct or indirect.
**Your licenses** are all the licenses granted to you for the
software under these terms.
**Use** means anything you do with the software requiring one
of your licenses.
---
Required Notice: Copyright 2025 Alex Newman (https://github.com/thedotmack)
For commercial licensing inquiries, contact: thedotmack@gmail.com

36
ragtime/README.md Normal file
View File

@@ -0,0 +1,36 @@
# Ragtime
> **Status**: Not yet implemented
Ragtime is a planned feature for claude-mem that will enable advanced timeline analysis and automated workflow orchestration.
## Why It's Not Ready Yet
Ragtime requires a fully functional **modes system** to work properly. The modes system (implemented in PR #412) provides:
- Mode inheritance and configuration loading
- Type-safe observation metadata
- Dynamic prompt injection based on workflow context
- Language-specific behavior
Now that the modes system is complete, Ragtime can be fully scripted out in a future release.
## License
This directory is licensed under the **PolyForm Noncommercial License 1.0.0**.
See [LICENSE](./LICENSE) for full terms.
### What this means:
- ✅ You can use ragtime for noncommercial purposes
- ✅ You can modify and distribute it
- ❌ You cannot use it for commercial purposes without permission
### Why a different license?
The main claude-mem repository is licensed under AGPL 3.0, but ragtime uses the more restrictive PolyForm Noncommercial license to ensure it remains freely available for personal and educational use while preventing commercial exploitation.
---
For questions about commercial licensing, please contact the project maintainer.

134
scripts/analyze-usage.js
View File

@@ -1,134 +0,0 @@
#!/usr/bin/env node
/**
* Analyze usage logs from ~/.claude-mem/usage-logs/
*
* Usage:
* node scripts/analyze-usage.js [date]
*
* Example:
* node scripts/analyze-usage.js 2025-11-03
* node scripts/analyze-usage.js # Uses today's date
*/
import { readFileSync, readdirSync } from 'fs';
import { join } from 'path';
import { homedir } from 'os';
const usageDir = join(homedir(), '.claude-mem', 'usage-logs');
// Get date from command line or use today
const targetDate = process.argv[2] || new Date().toISOString().split('T')[0];
const filename = `usage-${targetDate}.jsonl`;
const filepath = join(usageDir, filename);
console.log(`\n📊 Usage Analysis for ${targetDate}\n`);
console.log(`Reading from: ${filepath}\n`);
try {
const content = readFileSync(filepath, 'utf-8');
const lines = content.trim().split('\n');
let totalCost = 0;
let totalInputTokens = 0;
let totalOutputTokens = 0;
let totalCacheCreation = 0;
let totalCacheRead = 0;
const projectStats = {};
const modelStats = {};
lines.forEach(line => {
if (!line.trim()) return;
try {
const entry = JSON.parse(line);
// Aggregate totals
totalCost += entry.totalCostUsd || 0;
totalInputTokens += entry.usage?.inputTokens || 0;
totalOutputTokens += entry.usage?.outputTokens || 0;
totalCacheCreation += entry.usage?.cacheCreationInputTokens || 0;
totalCacheRead += entry.usage?.cacheReadInputTokens || 0;
// Project stats
if (!projectStats[entry.project]) {
projectStats[entry.project] = {
cost: 0,
sessions: new Set(),
tokens: 0
};
}
projectStats[entry.project].cost += entry.totalCostUsd || 0;
projectStats[entry.project].sessions.add(entry.sessionDbId);
projectStats[entry.project].tokens += (entry.usage?.inputTokens || 0) + (entry.usage?.outputTokens || 0);
// Model stats
if (!modelStats[entry.model]) {
modelStats[entry.model] = {
cost: 0,
calls: 0,
tokens: 0
};
}
modelStats[entry.model].cost += entry.totalCostUsd || 0;
modelStats[entry.model].calls += 1;
modelStats[entry.model].tokens += (entry.usage?.inputTokens || 0) + (entry.usage?.outputTokens || 0);
} catch (e) {
console.error(`Error parsing line: ${e.message}`);
}
});
// Print summary
console.log('═══════════════════════════════════════════════════════════\n');
console.log(`📈 Total Cost: $${totalCost.toFixed(4)}`);
console.log(`📊 Total API Calls: ${lines.length}`);
console.log(`\n🎯 Token Usage:`);
console.log(` Input Tokens: ${totalInputTokens.toLocaleString()}`);
console.log(` Output Tokens: ${totalOutputTokens.toLocaleString()}`);
console.log(` Cache Creation Tokens: ${totalCacheCreation.toLocaleString()}`);
console.log(` Cache Read Tokens: ${totalCacheRead.toLocaleString()}`);
console.log(` Total Tokens: ${(totalInputTokens + totalOutputTokens).toLocaleString()}`);
if (totalCacheRead > 0) {
const savings = ((totalCacheRead / (totalInputTokens + totalCacheRead)) * 100).toFixed(1);
console.log(` Cache Hit Rate: ${savings}%`);
}
console.log(`\n📁 By Project:`);
Object.entries(projectStats)
.sort((a, b) => b[1].cost - a[1].cost)
.forEach(([project, stats]) => {
console.log(` ${project}:`);
console.log(` Cost: $${stats.cost.toFixed(4)}`);
console.log(` Sessions: ${stats.sessions.size}`);
console.log(` Tokens: ${stats.tokens.toLocaleString()}`);
});
console.log(`\n🤖 By Model:`);
Object.entries(modelStats)
.sort((a, b) => b[1].cost - a[1].cost)
.forEach(([model, stats]) => {
console.log(` ${model}:`);
console.log(` Cost: $${stats.cost.toFixed(4)}`);
console.log(` Calls: ${stats.calls}`);
console.log(` Tokens: ${stats.tokens.toLocaleString()}`);
console.log(` Avg Cost/Call: $${(stats.cost / stats.calls).toFixed(4)}`);
});
console.log('\n═══════════════════════════════════════════════════════════\n');
} catch (error) {
if (error.code === 'ENOENT') {
console.error(`❌ No usage log found for ${targetDate}`);
console.log(`\nAvailable logs:`);
try {
const files = readdirSync(usageDir).filter(f => f.endsWith('.jsonl'));
files.forEach(f => console.log(` - ${f}`));
} catch (e) {
console.error(` Could not read usage logs directory`);
}
} else {
console.error(`❌ Error: ${error.message}`);
}
process.exit(1);
}

178
scripts/extract-prompts-to-yaml.cjs Normal file
View File

@@ -0,0 +1,178 @@
#!/usr/bin/env node
/**
* Extract prompt sections from src/sdk/prompts.ts and generate modes/code.yaml
* This ensures the YAML contains the exact same wording as the hardcoded prompts
*/
const fs = require('fs');
const path = require('path');
// Read the prompts.ts from main branch (saved to /tmp)
const promptsPath = '/tmp/prompts-main.ts';
const promptsContent = fs.readFileSync(promptsPath, 'utf-8');
// Extract buildInitPrompt function content
const initPromptMatch = promptsContent.match(/export function buildInitPrompt\([^)]+\): string \{[\s\S]*?return `([\s\S]*?)`;\s*\}/);
if (!initPromptMatch) {
console.error('Could not find buildInitPrompt function');
process.exit(1);
}
const initPrompt = initPromptMatch[1];
// Extract sections from buildInitPrompt
// Line 41: observer_role starts with "Your job is to monitor..."
const observerRoleMatch = initPrompt.match(/Your job is to monitor[^\n]*\n\n(?:SPATIAL AWARENESS:[\s\S]*?\n\n)?/);
const observerRole = observerRoleMatch ? observerRoleMatch[0].replace(/\n\n$/, '') : '';
// Extract recording_focus (WHAT TO RECORD section)
const recordingFocusMatch = initPrompt.match(/WHAT TO RECORD\n-{14}\n([\s\S]*?)(?=\n\nWHEN TO SKIP)/);
const recordingFocus = recordingFocusMatch ? `WHAT TO RECORD\n--------------\n${recordingFocusMatch[1]}` : '';
// Extract skip_guidance (WHEN TO SKIP section)
const skipGuidanceMatch = initPrompt.match(/WHEN TO SKIP\n-{12}\n([\s\S]*?)(?=\n\nOUTPUT FORMAT)/);
const skipGuidance = skipGuidanceMatch ? `WHEN TO SKIP\n------------\n${skipGuidanceMatch[1]}` : '';
// Extract type_guidance (from XML comment)
const typeGuidanceMatch = initPrompt.match(/<!--\n\s+\*\*type\*\*: MUST be EXACTLY[^\n]*\n([\s\S]*?)-->/);
const typeGuidance = typeGuidanceMatch ? typeGuidanceMatch[0].replace(/<!--\n\s+/, '').replace(/\s+-->/, '').trim() : '';
// Extract field_guidance (facts AND files comments combined)
const factsMatch = initPrompt.match(/\*\*facts\*\*: Concise[^\n]*\n([\s\S]*?)(?=\n -->)/);
const filesMatch = initPrompt.match(/\*\*files\*\*:[^\n]*\n/);
const factsText = factsMatch ? `**facts**: Concise, self-contained statements\n${factsMatch[1].trim()}` : '';
const filesText = filesMatch ? filesMatch[0].trim() : '**files**: All files touched (full paths from project root)';
const fieldGuidance = `${factsText}\n\n${filesText}`;
// Extract concept_guidance (concepts comment)
const conceptGuidanceMatch = initPrompt.match(/<!--\n\s+\*\*concepts\*\*: 2-5 knowledge[^\n]*\n([\s\S]*?)-->/);
const conceptGuidance = conceptGuidanceMatch ? conceptGuidanceMatch[0].replace(/<!--\n\s+/, '').replace(/\s+-->/, '').trim() : '';
// Build the JSON content
const jsonData = {
name: "Code Development",
description: "Software development and engineering work",
version: "1.0.0",
observation_types: [
{ id: "bugfix", label: "Bug Fix", description: "Something was broken, now fixed", emoji: "🔴", work_emoji: "🛠️" },
{ id: "feature", label: "Feature", description: "New capability or functionality added", emoji: "🟣", work_emoji: "🛠️" },
{ id: "refactor", label: "Refactor", description: "Code restructured, behavior unchanged", emoji: "🔄", work_emoji: "🛠️" },
{ id: "change", label: "Change", description: "Generic modification (docs, config, misc)", emoji: "✅", work_emoji: "🛠️" },
{ id: "discovery", label: "Discovery", description: "Learning about existing system", emoji: "🔵", work_emoji: "🔍" },
{ id: "decision", label: "Decision", description: "Architectural/design choice with rationale", emoji: "⚖️", work_emoji: "⚖️" }
],
observation_concepts: [
{ id: "how-it-works", label: "How It Works", description: "Understanding mechanisms" },
{ id: "why-it-exists", label: "Why It Exists", description: "Purpose or rationale" },
{ id: "what-changed", label: "What Changed", description: "Modifications made" },
{ id: "problem-solution", label: "Problem-Solution", description: "Issues and their fixes" },
{ id: "gotcha", label: "Gotcha", description: "Traps or edge cases" },
{ id: "pattern", label: "Pattern", description: "Reusable approach" },
{ id: "trade-off", label: "Trade-Off", description: "Pros/cons of a decision" }
],
prompts: {
observer_role: observerRole,
recording_focus: recordingFocus,
skip_guidance: skipGuidance,
type_guidance: typeGuidance,
concept_guidance: conceptGuidance,
field_guidance: fieldGuidance,
format_examples: ""
}
};
// OLD YAML BUILD:
const yamlContent_OLD = `name: "Code Development"
description: "Software development and engineering work"
version: "1.0.0"
observation_types:
- id: "bugfix"
label: "Bug Fix"
description: "Something was broken, now fixed"
emoji: "🔴"
work_emoji: "🛠️"
- id: "feature"
label: "Feature"
description: "New capability or functionality added"
emoji: "🟣"
work_emoji: "🛠️"
- id: "refactor"
label: "Refactor"
description: "Code restructured, behavior unchanged"
emoji: "🔄"
work_emoji: "🛠️"
- id: "change"
label: "Change"
description: "Generic modification (docs, config, misc)"
emoji: "✅"
work_emoji: "🛠️"
- id: "discovery"
label: "Discovery"
description: "Learning about existing system"
emoji: "🔵"
work_emoji: "🔍"
- id: "decision"
label: "Decision"
description: "Architectural/design choice with rationale"
emoji: "⚖️"
work_emoji: "⚖️"
observation_concepts:
- id: "how-it-works"
label: "How It Works"
description: "Understanding mechanisms"
- id: "why-it-exists"
label: "Why It Exists"
description: "Purpose or rationale"
- id: "what-changed"
label: "What Changed"
description: "Modifications made"
- id: "problem-solution"
label: "Problem-Solution"
description: "Issues and their fixes"
- id: "gotcha"
label: "Gotcha"
description: "Traps or edge cases"
- id: "pattern"
label: "Pattern"
description: "Reusable approach"
- id: "trade-off"
label: "Trade-Off"
description: "Pros/cons of a decision"
prompts:
observer_role: |
${observerRole}
recording_focus: |
${recordingFocus}
skip_guidance: |
${skipGuidance}
type_guidance: |
${typeGuidance}
concept_guidance: |
${conceptGuidance}
field_guidance: |
${fieldGuidance}
format_examples: ""
`;
// Write to modes/code.json
const outputPath = path.join(__dirname, '../modes/code.json');
fs.writeFileSync(outputPath, JSON.stringify(jsonData, null, 2), 'utf-8');
console.log('✅ Generated modes/code.json from prompts.ts');
console.log('\nExtracted sections:');
console.log('- observer_role:', observerRole.substring(0, 50) + '...');
console.log('- recording_focus:', recordingFocus.substring(0, 50) + '...');
console.log('- skip_guidance:', skipGuidance.substring(0, 50) + '...');
console.log('- type_guidance:', typeGuidance.substring(0, 50) + '...');
console.log('- concept_guidance:', conceptGuidance.substring(0, 50) + '...');
console.log('- field_guidance:', fieldGuidance.substring(0, 50) + '...');

17
scripts/translate-readme/cli.ts
View File

@@ -12,7 +12,6 @@ interface CliArgs {
maxBudget?: number;
verbose: boolean;
force: boolean;
parallel: number;
help: boolean;
listLanguages: boolean;
}
@@ -42,12 +41,11 @@ OPTIONS:
--max-budget <usd> Maximum budget in USD
-v, --verbose Show detailed progress
-f, --force Force re-translation ignoring cache
--parallel <n> Run n translations concurrently (default: 1)
-h, --help Show this help message
--list-languages List all supported language codes
EXAMPLES:
# Translate to Spanish and French
# Translate to Spanish and French (runs in parallel automatically)
translate-readme README.md es fr
# Translate to multiple languages with custom output
@@ -56,6 +54,10 @@ EXAMPLES:
# Use in npm scripts
# package.json: "translate": "translate-readme README.md es fr de"
PERFORMANCE:
All translations run in parallel automatically (up to 10 concurrent).
Cache prevents re-translating unchanged files.
SUPPORTED LANGUAGES:
Run with --list-languages to see all supported language codes
`);
@@ -123,7 +125,6 @@ function parseArgs(argv: string[]): CliArgs {
preserveCode: true,
verbose: false,
force: false,
parallel: 1,
help: false,
listLanguages: false,
};
@@ -168,13 +169,6 @@ function parseArgs(argv: string[]): CliArgs {
case "--max-budget":
args.maxBudget = parseFloat(argv[++i]);
break;
case "--parallel":
args.parallel = parseInt(argv[++i], 10);
if (isNaN(args.parallel) || args.parallel < 1) {
console.error("Error: --parallel must be a positive integer");
process.exit(1);
}
break;
default:
if (arg.startsWith("-")) {
console.error(`Unknown option: ${arg}`);
@@ -239,7 +233,6 @@ async function main(): Promise<void> {
maxBudgetUsd: args.maxBudget,
verbose: args.verbose,
force: args.force,
parallel: args.parallel,
});
// Exit with error code if any translations failed

25
scripts/translate-readme/index.ts
View File

@@ -49,8 +49,6 @@ export interface TranslationOptions {
verbose?: boolean;
/** Force re-translation even if cached */
force?: boolean;
/** Number of concurrent translations (default: 1) */
parallel?: number;
}
export interface TranslationResult {
@@ -258,9 +256,11 @@ export async function translateReadme(
maxBudgetUsd,
verbose = false,
force = false,
parallel = 1,
} = options;
// Run all translations in parallel (up to 10 concurrent)
const parallel = Math.min(languages.length, 10);
// Read source file
const sourcePath = path.resolve(source);
const content = await fs.readFile(sourcePath, "utf-8");
@@ -282,9 +282,7 @@ export async function translateReadme(
console.log(`📖 Source: ${sourcePath}`);
console.log(`📂 Output: ${outDir}`);
console.log(`🌍 Languages: ${languages.join(", ")}`);
if (parallel > 1) {
console.log(`⚡ Parallel: ${parallel} concurrent translations`);
}
console.log(`⚡ Running ${parallel} translations in parallel`);
console.log("");
}
@@ -334,7 +332,7 @@ export async function translateReadme(
// Run with concurrency limit
async function runWithConcurrency<T>(items: T[], limit: number, fn: (item: T) => Promise<TranslationResult>): Promise<TranslationResult[]> {
const results: TranslationResult[] = [];
const executing: Promise<void>[] = [];
const executing = new Set<Promise<void>>();
for (const item of items) {
// Check budget before starting new translation
@@ -355,15 +353,20 @@ export async function translateReadme(
}
});
executing.push(p.then(() => {
executing.splice(executing.indexOf(p.then(() => {})), 1);
}));
// Create a wrapped promise that removes itself when done
const wrapped = p.finally(() => {
executing.delete(wrapped);
});
if (executing.length >= limit) {
executing.add(wrapped);
// Wait for a slot to open up if we're at the limit
if (executing.size >= limit) {
await Promise.race(executing);
}
}
// Wait for all remaining translations to complete
await Promise.all(executing);
return results;
}

63
src/constants/observation-metadata.ts
View File

@@ -1,68 +1,19 @@
/**
* Observation metadata constants
* Shared across hooks, worker service, and UI components
*
* Note: These are fallback defaults for the code mode.
* Actual observation types and concepts are defined per-mode in the modes/ directory.
*/
/**
* Valid observation types
*/
export const OBSERVATION_TYPES = [
'bugfix',
'feature',
'refactor',
'discovery',
'decision',
'change'
] as const;
export type ObservationType = typeof OBSERVATION_TYPES[number];
/**
* Valid observation concepts
*/
export const OBSERVATION_CONCEPTS = [
'how-it-works',
'why-it-exists',
'what-changed',
'problem-solution',
'gotcha',
'pattern',
'trade-off'
] as const;
export type ObservationConcept = typeof OBSERVATION_CONCEPTS[number];
/**
* Map observation types to emoji icons
*/
export const TYPE_ICON_MAP: Record<ObservationType | 'session-request', string> = {
'bugfix': '🔴',
'feature': '🟣',
'refactor': '🔄',
'change': '✅',
'discovery': '🔵',
'decision': '⚖️',
'session-request': '🎯'
};
/**
* Map observation types to work emoji (for token display)
*/
export const TYPE_WORK_EMOJI_MAP: Record<ObservationType, string> = {
'discovery': '🔍', // research/exploration
'change': '🛠️', // building/modifying
'feature': '🛠️', // building/modifying
'bugfix': '🛠️', // building/modifying
'refactor': '🛠️', // building/modifying
'decision': '⚖️' // decision-making
};
/**
* Default observation types (comma-separated string for settings)
* Uses code mode defaults as fallback
*/
export const DEFAULT_OBSERVATION_TYPES_STRING = OBSERVATION_TYPES.join(',');
export const DEFAULT_OBSERVATION_TYPES_STRING = 'bugfix,feature,refactor,discovery,decision,change';
/**
* Default observation concepts (comma-separated string for settings)
* Uses code mode defaults as fallback
*/
export const DEFAULT_OBSERVATION_CONCEPTS_STRING = OBSERVATION_CONCEPTS.join(',');
export const DEFAULT_OBSERVATION_CONCEPTS_STRING = 'how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off';

38
src/hooks/cleanup-hook.ts
View File

@@ -30,26 +30,19 @@ async function cleanupHook(input?: SessionEndInput): Promise<void> {
const port = getWorkerPort();
try {
// Send to worker - worker handles finding session, marking complete, and stopping spinner
const response = await fetch(`http://127.0.0.1:${port}/api/sessions/complete`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
reason
}),
signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT)
});
// Send to worker - worker handles finding session, marking complete, and stopping spinner
const response = await fetch(`http://127.0.0.1:${port}/api/sessions/complete`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
reason
}),
signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT)
});
if (!response.ok) {
// Non-fatal - session might not exist
console.error('[cleanup-hook] Session not found or already cleaned up');
}
} catch (error: any) {
// Worker might not be running - that's okay (non-critical)
// But we should still log it for visibility
console.error('[cleanup-hook] Failed to notify worker of session end:', error.message);
if (!response.ok) {
throw new Error(`Session cleanup failed: ${response.status}`);
}
console.log('{"continue": true, "suppressOutput": true}');
@@ -64,7 +57,12 @@ if (stdin.isTTY) {
let input = '';
stdin.on('data', (chunk) => input += chunk);
stdin.on('end', async () => {
const parsed = input ? JSON.parse(input) : undefined;
let parsed: SessionEndInput | undefined;
try {
parsed = input ? JSON.parse(input) : undefined;
} catch (error) {
throw new Error(`Failed to parse hook input: ${error instanceof Error ? error.message : String(error)}`);
}
await cleanupHook(parsed);
});
}

31
src/hooks/context-hook.ts
View File

@@ -9,8 +9,6 @@
import { stdin } from "process";
import { ensureWorkerRunning, getWorkerPort } from "../shared/worker-utils.js";
import { HOOK_TIMEOUTS } from "../shared/hook-constants.js";
import { handleWorkerError } from "../shared/hook-error-handler.js";
import { handleFetchError } from "./shared/error-handler.js";
import { getProjectName } from "../utils/project-name.js";
export interface SessionStartInput {
@@ -30,24 +28,14 @@ async function contextHook(input?: SessionStartInput): Promise<string> {
const url = `http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(project)}`;
try {
const response = await fetch(url, { signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT) });
const response = await fetch(url, { signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT) });
if (!response.ok) {
const errorText = await response.text();
handleFetchError(response, errorText, {
hookName: 'context',
operation: 'Context generation',
project,
port
});
}
const result = await response.text();
return result.trim();
} catch (error: any) {
handleWorkerError(error);
if (!response.ok) {
throw new Error(`Context generation failed: ${response.status}`);
}
const result = await response.text();
return result.trim();
}
// Entry Point - handle stdin/stdout
@@ -62,7 +50,12 @@ if (stdin.isTTY || forceColors) {
let input = "";
stdin.on("data", (chunk) => (input += chunk));
stdin.on("end", async () => {
const parsed = input.trim() ? JSON.parse(input) : undefined;
let parsed: SessionStartInput | undefined;
try {
parsed = input.trim() ? JSON.parse(input) : undefined;
} catch (error) {
throw new Error(`Failed to parse hook input: ${error instanceof Error ? error.message : String(error)}`);
}
const text = await contextHook(parsed);
console.log(

101
src/hooks/new-hook.ts
View File

@@ -1,8 +1,6 @@
import { stdin } from 'process';
import { STANDARD_HOOK_RESPONSE } from './hook-response.js';
import { ensureWorkerRunning, getWorkerPort } from '../shared/worker-utils.js';
import { handleWorkerError } from '../shared/hook-error-handler.js';
import { handleFetchError } from './shared/error-handler.js';
import { getProjectName } from '../utils/project-name.js';
export interface UserPromptSubmitInput {
@@ -29,72 +27,48 @@ async function newHook(input?: UserPromptSubmitInput): Promise<void> {
const port = getWorkerPort();
// Initialize session via HTTP - handles DB operations and privacy checks
let sessionDbId: number;
let promptNumber: number;
const initResponse = await fetch(`http://127.0.0.1:${port}/api/sessions/init`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
project,
prompt
}),
signal: AbortSignal.timeout(5000)
});
try {
const initResponse = await fetch(`http://127.0.0.1:${port}/api/sessions/init`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
project,
prompt
}),
signal: AbortSignal.timeout(5000)
});
if (!initResponse.ok) {
const errorText = await initResponse.text();
handleFetchError(initResponse, errorText, {
hookName: 'new',
operation: 'Session initialization',
project,
port
});
}
const initResult = await initResponse.json();
sessionDbId = initResult.sessionDbId;
promptNumber = initResult.promptNumber;
// Check if prompt was entirely private (worker performs privacy check)
if (initResult.skipped && initResult.reason === 'private') {
console.error(`[new-hook] Session ${sessionDbId}, prompt #${promptNumber} (fully private - skipped)`);
console.log(STANDARD_HOOK_RESPONSE);
return;
}
console.error(`[new-hook] Session ${sessionDbId}, prompt #${promptNumber}`);
} catch (error: any) {
handleWorkerError(error);
if (!initResponse.ok) {
throw new Error(`Session initialization failed: ${initResponse.status}`);
}
const initResult = await initResponse.json();
const sessionDbId = initResult.sessionDbId;
const promptNumber = initResult.promptNumber;
// Check if prompt was entirely private (worker performs privacy check)
if (initResult.skipped && initResult.reason === 'private') {
console.error(`[new-hook] Session ${sessionDbId}, prompt #${promptNumber} (fully private - skipped)`);
console.log(STANDARD_HOOK_RESPONSE);
return;
}
console.error(`[new-hook] Session ${sessionDbId}, prompt #${promptNumber}`);
// Strip leading slash from commands for memory agent
// /review 101 → review 101 (more semantic for observations)
const cleanedPrompt = prompt.startsWith('/') ? prompt.substring(1) : prompt;
try {
// Initialize SDK agent session via HTTP (starts the agent!)
const response = await fetch(`http://127.0.0.1:${port}/sessions/${sessionDbId}/init`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ userPrompt: cleanedPrompt, promptNumber }),
signal: AbortSignal.timeout(5000)
});
// Initialize SDK agent session via HTTP (starts the agent!)
const response = await fetch(`http://127.0.0.1:${port}/sessions/${sessionDbId}/init`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ userPrompt: cleanedPrompt, promptNumber }),
signal: AbortSignal.timeout(5000)
});
if (!response.ok) {
const errorText = await response.text();
handleFetchError(response, errorText, {
hookName: 'new',
operation: 'SDK agent start',
project,
port,
sessionId: String(sessionDbId)
});
}
} catch (error: any) {
handleWorkerError(error);
if (!response.ok) {
throw new Error(`SDK agent start failed: ${response.status}`);
}
console.log(STANDARD_HOOK_RESPONSE);
@@ -104,6 +78,11 @@ async function newHook(input?: UserPromptSubmitInput): Promise<void> {
let input = '';
stdin.on('data', (chunk) => input += chunk);
stdin.on('end', async () => {
const parsed = input ? JSON.parse(input) : undefined;
let parsed: UserPromptSubmitInput | undefined;
try {
parsed = input ? JSON.parse(input) : undefined;
} catch (error) {
throw new Error(`Failed to parse hook input: ${error instanceof Error ? error.message : String(error)}`);
}
await newHook(parsed);
});

54
src/hooks/save-hook.ts
View File

@@ -11,8 +11,6 @@ import { STANDARD_HOOK_RESPONSE } from './hook-response.js';
import { logger } from '../utils/logger.js';
import { ensureWorkerRunning, getWorkerPort } from '../shared/worker-utils.js';
import { HOOK_TIMEOUTS } from '../shared/hook-constants.js';
import { handleWorkerError } from '../shared/hook-error-handler.js';
import { handleFetchError } from './shared/error-handler.js';
export interface PostToolUseInput {
session_id: string;
@@ -48,37 +46,26 @@ async function saveHook(input?: PostToolUseInput): Promise<void> {
throw new Error(`Missing cwd in PostToolUse hook input for session ${session_id}, tool ${tool_name}`);
}
try {
// Send to worker - worker handles privacy check and database operations
const response = await fetch(`http://127.0.0.1:${port}/api/sessions/observations`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
tool_name,
tool_input,
tool_response,
cwd
}),
signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT)
});
// Send to worker - worker handles privacy check and database operations
const response = await fetch(`http://127.0.0.1:${port}/api/sessions/observations`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
tool_name,
tool_input,
tool_response,
cwd
}),
signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT)
});
if (!response.ok) {
const errorText = await response.text();
handleFetchError(response, errorText, {
hookName: 'save',
operation: 'Observation storage',
toolName: tool_name,
sessionId: session_id,
port
});
}
logger.debug('HOOK', 'Observation sent successfully', { toolName: tool_name });
} catch (error: any) {
handleWorkerError(error);
if (!response.ok) {
throw new Error(`Observation storage failed: ${response.status}`);
}
logger.debug('HOOK', 'Observation sent successfully', { toolName: tool_name });
console.log(STANDARD_HOOK_RESPONSE);
}
@@ -86,6 +73,11 @@ async function saveHook(input?: PostToolUseInput): Promise<void> {
let input = '';
stdin.on('data', (chunk) => input += chunk);
stdin.on('end', async () => {
const parsed = input ? JSON.parse(input) : undefined;
let parsed: PostToolUseInput | undefined;
try {
parsed = input ? JSON.parse(input) : undefined;
} catch (error) {
throw new Error(`Failed to parse hook input: ${error instanceof Error ? error.message : String(error)}`);
}
await saveHook(parsed);
});

37
src/hooks/shared/error-handler.ts
View File

@@ -1,37 +0,0 @@
import { logger } from '../../utils/logger.js';
import { getWorkerRestartInstructions } from '../../utils/error-messages.js';
export interface HookErrorContext {
hookName: string;
operation: string;
project?: string;
sessionId?: string;
toolName?: string;
port?: number;
}
/**
* Standardized error handler for hook fetch failures.
*
* This function:
* 1. Logs the error with full context to worker logs
* 2. Throws a user-facing error with restart instructions
*
* Use this for all fetch errors in hooks to ensure consistent error handling.
*/
export function handleFetchError(
response: Response,
errorText: string,
context: HookErrorContext
): never {
logger.error('HOOK', `${context.operation} failed`, {
status: response.status,
...context
}, errorText);
const userMessage = context.toolName
? `Failed ${context.operation} for ${context.toolName}: ${getWorkerRestartInstructions()}`
: `${context.operation} failed: ${getWorkerRestartInstructions()}`;
throw new Error(userMessage);
}

70
src/hooks/summary-hook.ts
View File

@@ -14,8 +14,6 @@ import { STANDARD_HOOK_RESPONSE } from './hook-response.js';
import { logger } from '../utils/logger.js';
import { ensureWorkerRunning, getWorkerPort } from '../shared/worker-utils.js';
import { HOOK_TIMEOUTS } from '../shared/hook-constants.js';
import { handleWorkerError } from '../shared/hook-error-handler.js';
import { handleFetchError } from './shared/error-handler.js';
import { extractLastMessage } from '../shared/transcript-parser.js';
export interface StopInput {
@@ -54,56 +52,23 @@ async function summaryHook(input?: StopInput): Promise<void> {
hasLastAssistantMessage: !!lastAssistantMessage
});
let summaryError: Error | null = null;
// Send to worker - worker handles privacy check and database operations
const response = await fetch(`http://127.0.0.1:${port}/api/sessions/summarize`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
last_user_message: lastUserMessage,
last_assistant_message: lastAssistantMessage
}),
signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT)
});
try {
// Send to worker - worker handles privacy check and database operations
const response = await fetch(`http://127.0.0.1:${port}/api/sessions/summarize`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
last_user_message: lastUserMessage,
last_assistant_message: lastAssistantMessage
}),
signal: AbortSignal.timeout(HOOK_TIMEOUTS.DEFAULT)
});
if (!response.ok) {
const errorText = await response.text();
handleFetchError(response, errorText, {
hookName: 'summary',
operation: 'Summary generation',
sessionId: session_id,
port
});
}
logger.debug('HOOK', 'Summary request sent successfully');
} catch (error: any) {
summaryError = error;
handleWorkerError(error);
} finally {
// Stop processing spinner (non-critical operation, errors are logged but don't block)
try {
const spinnerResponse = await fetch(`http://127.0.0.1:${port}/api/processing`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ isProcessing: false }),
signal: AbortSignal.timeout(2000)
});
if (!spinnerResponse.ok) {
logger.warn('HOOK', 'Failed to stop spinner', { status: spinnerResponse.status });
}
} catch (error: any) {
logger.warn('HOOK', 'Could not stop spinner', { error: error.message });
}
if (!response.ok) {
throw new Error(`Summary generation failed: ${response.status}`);
}
// Re-throw summary error after cleanup to ensure it's not masked by finally block
if (summaryError) {
throw summaryError;
}
logger.debug('HOOK', 'Summary request sent successfully');
console.log(STANDARD_HOOK_RESPONSE);
}
@@ -112,6 +77,11 @@ async function summaryHook(input?: StopInput): Promise<void> {
let input = '';
stdin.on('data', (chunk) => input += chunk);
stdin.on('end', async () => {
const parsed = input ? JSON.parse(input) : undefined;
let parsed: StopInput | undefined;
try {
parsed = input ? JSON.parse(input) : undefined;
} catch (error) {
throw new Error(`Failed to parse hook input: ${error instanceof Error ? error.message : String(error)}`);
}
await summaryHook(parsed);
});

69
src/hooks/user-message-hook.ts
View File

@@ -9,57 +9,32 @@
import { basename } from "path";
import { ensureWorkerRunning, getWorkerPort } from "../shared/worker-utils.js";
import { HOOK_EXIT_CODES } from "../shared/hook-constants.js";
import { getWorkerRestartInstructions } from "../utils/error-messages.js";
try {
// Ensure worker is running
await ensureWorkerRunning();
// Ensure worker is running
await ensureWorkerRunning();
const port = getWorkerPort();
const project = basename(process.cwd());
const port = getWorkerPort();
const project = basename(process.cwd());
// Fetch formatted context directly from worker API
const response = await fetch(
`http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(project)}&colors=true`,
{ method: 'GET', signal: AbortSignal.timeout(5000) }
);
// Fetch formatted context directly from worker API
const response = await fetch(
`http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(project)}&colors=true`,
{ method: 'GET', signal: AbortSignal.timeout(5000) }
);
if (!response.ok) {
throw new Error(getWorkerRestartInstructions({ includeSkillFallback: true }));
}
const output = await response.text();
console.error(
"\n\n📝 Claude-Mem Context Loaded\n" +
" ℹ️ Note: This appears as stderr but is informational only\n\n" +
output +
"\n\n💡 New! Wrap all or part of any message with <private> ... </private> to prevent storing sensitive information in your observation history.\n" +
"\n💬 Community https://discord.gg/J4wttp9vDu" +
`\n📺 Watch live in browser http://localhost:${port}/\n`
);
} catch (error) {
// Context not available yet - likely first run or worker starting up
console.error(`
---
🎉 Note: This appears under Plugin Hook Error, but it's not an error. That's the only option for
user messages in Claude Code UI until a better method is provided.
---
⚠️ Claude-Mem: First-Time Setup
Dependencies are installing in the background. This only happens once.
💡 TIPS:
• Memories will start generating while you work
• Use /init to write or update your CLAUDE.md for better project context
• Try /clear after one session to see what context looks like
Thank you for installing Claude-Mem!
This message was not added to your startup context, so you can continue working as normal.
`);
if (!response.ok) {
throw new Error(`Failed to fetch context: ${response.status}`);
}
const output = await response.text();
console.error(
"\n\n📝 Claude-Mem Context Loaded\n" +
" ℹ️ Note: This appears as stderr but is informational only\n\n" +
output +
"\n\n💡 New! Wrap all or part of any message with <private> ... </private> to prevent storing sensitive information in your observation history.\n" +
"\n💬 Community https://discord.gg/J4wttp9vDu" +
`\n📺 Watch live in browser http://localhost:${port}/\n`
);
process.exit(HOOK_EXIT_CODES.USER_MESSAGE_ONLY);

403
src/sdk/parser.test.ts
View File

@@ -1,403 +0,0 @@
/**
* Parser Regression Tests
* Ensures v4.2.5 and v4.2.6 bugfixes remain stable
*/
import { parseObservations, parseSummary } from './parser.js';
// ANSI color codes for output
const GREEN = '\x1b[32m';
const RED = '\x1b[31m';
const YELLOW = '\x1b[33m';
const RESET = '\x1b[0m';
let testsRun = 0;
let testsPassed = 0;
let testsFailed = 0;
function assert(condition: boolean, testName: string, errorMsg?: string): void {
testsRun++;
if (condition) {
testsPassed++;
console.log(`${GREEN}✓${RESET} ${testName}`);
} else {
testsFailed++;
console.log(`${RED}✗${RESET} ${testName}`);
if (errorMsg) {
console.log(` ${RED}${errorMsg}${RESET}`);
}
}
}
function assertEqual<T>(actual: T, expected: T, testName: string): void {
const isEqual = JSON.stringify(actual) === JSON.stringify(expected);
if (!isEqual) {
assert(false, testName, `Expected: ${JSON.stringify(expected)}, Got: ${JSON.stringify(actual)}`);
} else {
assert(true, testName);
}
}
console.log('\n' + YELLOW + '='.repeat(60) + RESET);
console.log(YELLOW + 'Parser Regression Tests (v4.2.5 & v4.2.6)' + RESET);
console.log(YELLOW + '='.repeat(60) + RESET + '\n');
// ============================================================================
// v4.2.6: Observation Parsing - NEVER Skip Observations
// ============================================================================
console.log(YELLOW + '\nv4.2.6: Observation Validation Fixes' + RESET);
console.log('─'.repeat(60) + '\n');
// Test 1: Observation with missing title should be saved
const missingTitleXml = `
<observation>
<type>feature</type>
<subtitle>Added new feature</subtitle>
<narrative>Implemented the feature successfully</narrative>
<facts>
<fact>Created new file</fact>
</facts>
<concepts>
<concept>authentication</concept>
</concepts>
<files_read></files_read>
<files_modified>
<file>src/app.ts</file>
</files_modified>
</observation>
`;
const missingTitleResult = parseObservations(missingTitleXml);
assert(missingTitleResult.length === 1, 'Should parse observation with missing title');
assert(missingTitleResult[0].title === null, 'Missing title should be null');
assertEqual(missingTitleResult[0].type, 'feature', 'Should preserve type when title missing');
// Test 2: Observation with missing subtitle should be saved
const missingSubtitleXml = `
<observation>
<type>bugfix</type>
<title>Fixed critical bug</title>
<narrative>Resolved the issue</narrative>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const missingSubtitleResult = parseObservations(missingSubtitleXml);
assert(missingSubtitleResult.length === 1, 'Should parse observation with missing subtitle');
assert(missingSubtitleResult[0].subtitle === null, 'Missing subtitle should be null');
assertEqual(missingSubtitleResult[0].title, 'Fixed critical bug', 'Should preserve title when subtitle missing');
// Test 3: Observation with missing narrative should be saved
const missingNarrativeXml = `
<observation>
<type>refactor</type>
<title>Code cleanup</title>
<subtitle>Improved structure</subtitle>
<facts>
<fact>Removed dead code</fact>
</facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const missingNarrativeResult = parseObservations(missingNarrativeXml);
assert(missingNarrativeResult.length === 1, 'Should parse observation with missing narrative');
assert(missingNarrativeResult[0].narrative === null, 'Missing narrative should be null');
assertEqual(missingNarrativeResult[0].facts, ['Removed dead code'], 'Should preserve facts when narrative missing');
// Test 4: Observation with ALL fields missing (except type) should be saved
const minimalObservationXml = `
<observation>
<type>change</type>
<title></title>
<subtitle></subtitle>
<narrative></narrative>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const minimalResult = parseObservations(minimalObservationXml);
assert(minimalResult.length === 1, 'Should parse minimal observation with only type');
assertEqual(minimalResult[0].type, 'change', 'Should preserve type for minimal observation');
assert(minimalResult[0].title === null, 'Empty title should be null');
assert(minimalResult[0].subtitle === null, 'Empty subtitle should be null');
assert(minimalResult[0].narrative === null, 'Empty narrative should be null');
// Test 5: Observation with missing type should use "change" as fallback
const missingTypeXml = `
<observation>
<title>Something happened</title>
<subtitle>Details here</subtitle>
<narrative>More info</narrative>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const missingTypeResult = parseObservations(missingTypeXml);
assert(missingTypeResult.length === 1, 'Should parse observation with missing type');
assertEqual(missingTypeResult[0].type, 'change', 'Missing type should default to "change"');
// Test 6: Observation with invalid type should use "change" as fallback
const invalidTypeXml = `
<observation>
<type>invalid_type_here</type>
<title>Something happened</title>
<subtitle>Details here</subtitle>
<narrative>More info</narrative>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const invalidTypeResult = parseObservations(invalidTypeXml);
assert(invalidTypeResult.length === 1, 'Should parse observation with invalid type');
assertEqual(invalidTypeResult[0].type, 'change', 'Invalid type should default to "change"');
// Test 7: Multiple observations with mixed completeness should all be saved
const mixedObservationsXml = `
<observation>
<type>feature</type>
<title>Full observation</title>
<subtitle>Complete</subtitle>
<narrative>All fields present</narrative>
<facts><fact>Fact 1</fact></facts>
<concepts><concept>concept1</concept></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
<observation>
<type>bugfix</type>
<subtitle>Only subtitle and type</subtitle>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
<observation>
<title>Only title, no type</title>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const mixedResult = parseObservations(mixedObservationsXml);
assertEqual(mixedResult.length, 3, 'Should parse all three observations regardless of completeness');
assertEqual(mixedResult[0].type, 'feature', 'First observation should have correct type');
assertEqual(mixedResult[1].type, 'bugfix', 'Second observation should have correct type');
assertEqual(mixedResult[2].type, 'change', 'Third observation should default to "change"');
// ============================================================================
// v4.2.5: Summary Parsing - NEVER Skip Summaries
// ============================================================================
console.log(YELLOW + '\nv4.2.5: Summary Validation Fixes' + RESET);
console.log('─'.repeat(60) + '\n');
// Test 8: Summary with missing request field should be saved
const missingRequestXml = `
<summary>
<investigated>Looked into the codebase</investigated>
<learned>Found the issue</learned>
<completed>Fixed the bug</completed>
<next_steps>Deploy to production</next_steps>
</summary>
`;
const missingRequestResult = parseSummary(missingRequestXml);
assert(missingRequestResult !== null, 'Should parse summary with missing request');
assert(missingRequestResult!.request === null, 'Missing request should be null');
assertEqual(missingRequestResult!.investigated, 'Looked into the codebase', 'Should preserve other fields');
// Test 9: Summary with missing investigated field should be saved
const missingInvestigatedXml = `
<summary>
<request>Fix the bug</request>
<learned>Root cause identified</learned>
<completed>Applied the fix</completed>
<next_steps>Monitor production</next_steps>
</summary>
`;
const missingInvestigatedResult = parseSummary(missingInvestigatedXml);
assert(missingInvestigatedResult !== null, 'Should parse summary with missing investigated');
assert(missingInvestigatedResult!.investigated === null, 'Missing investigated should be null');
// Test 10: Summary with missing learned field should be saved
const missingLearnedXml = `
<summary>
<request>Add new feature</request>
<investigated>Reviewed the requirements</investigated>
<completed>Implemented the feature</completed>
<next_steps>Write tests</next_steps>
</summary>
`;
const missingLearnedResult = parseSummary(missingLearnedXml);
assert(missingLearnedResult !== null, 'Should parse summary with missing learned');
assert(missingLearnedResult!.learned === null, 'Missing learned should be null');
// Test 11: Summary with missing completed field should be saved
const missingCompletedXml = `
<summary>
<request>Refactor code</request>
<investigated>Analyzed the structure</investigated>
<learned>Found improvement opportunities</learned>
<next_steps>Continue refactoring</next_steps>
</summary>
`;
const missingCompletedResult = parseSummary(missingCompletedXml);
assert(missingCompletedResult !== null, 'Should parse summary with missing completed');
assert(missingCompletedResult!.completed === null, 'Missing completed should be null');
// Test 12: Summary with missing next_steps field should be saved
const missingNextStepsXml = `
<summary>
<request>Review code</request>
<investigated>Examined all files</investigated>
<learned>Code quality is good</learned>
<completed>Review complete</completed>
</summary>
`;
const missingNextStepsResult = parseSummary(missingNextStepsXml);
assert(missingNextStepsResult !== null, 'Should parse summary with missing next_steps');
assert(missingNextStepsResult!.next_steps === null, 'Missing next_steps should be null');
// Test 13: Summary with only notes field should be saved
const onlyNotesXml = `
<summary>
<notes>Some random notes</notes>
</summary>
`;
const onlyNotesResult = parseSummary(onlyNotesXml);
assert(onlyNotesResult !== null, 'Should parse summary with only notes field');
assertEqual(onlyNotesResult!.notes, 'Some random notes', 'Should preserve notes field');
// Test 14: Completely empty summary should be saved
const emptySummaryXml = `
<summary>
<request></request>
<investigated></investigated>
<learned></learned>
<completed></completed>
<next_steps></next_steps>
</summary>
`;
const emptySummaryResult = parseSummary(emptySummaryXml);
assert(emptySummaryResult !== null, 'Should parse completely empty summary');
assert(emptySummaryResult!.request === null, 'Empty request should be null');
assert(emptySummaryResult!.investigated === null, 'Empty investigated should be null');
// Test 15: Summary with skip_summary should return null (valid use case)
const skipSummaryXml = `
<skip_summary reason="Not enough context yet" />
`;
const skipSummaryResult = parseSummary(skipSummaryXml);
assert(skipSummaryResult === null, 'Should return null for skip_summary directive');
// ============================================================================
// Edge Cases & Data Integrity
// ============================================================================
console.log(YELLOW + '\nEdge Cases & Data Integrity' + RESET);
console.log('─'.repeat(60) + '\n');
// Test 16: Observation with whitespace-only fields should be null
const whitespaceObservationXml = `
<observation>
<type>change</type>
<title> </title>
<subtitle>
</subtitle>
<narrative></narrative>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const whitespaceResult = parseObservations(whitespaceObservationXml);
assert(whitespaceResult.length === 1, 'Should parse observation with whitespace fields');
assert(whitespaceResult[0].title === null || whitespaceResult[0].title!.trim() === '', 'Whitespace title should be null or empty');
// Test 17: Observation with concepts including type should filter out type
const conceptsWithTypeXml = `
<observation>
<type>feature</type>
<title>New feature</title>
<subtitle>Details</subtitle>
<narrative>Description</narrative>
<facts></facts>
<concepts>
<concept>feature</concept>
<concept>authentication</concept>
</concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const conceptsWithTypeResult = parseObservations(conceptsWithTypeXml);
assert(conceptsWithTypeResult.length === 1, 'Should parse observation with type in concepts');
assertEqual(conceptsWithTypeResult[0].concepts, ['authentication'], 'Should filter out type from concepts');
// Test 18: Observation with all valid types
const validTypes = ['decision', 'bugfix', 'feature', 'refactor', 'discovery', 'change'];
validTypes.forEach(type => {
const typeXml = `
<observation>
<type>${type}</type>
<title>Test</title>
<subtitle>Test</subtitle>
<narrative>Test</narrative>
<facts></facts>
<concepts></concepts>
<files_read></files_read>
<files_modified></files_modified>
</observation>
`;
const result = parseObservations(typeXml);
assertEqual(result[0].type, type, `Should accept valid type: ${type}`);
});
// ============================================================================
// Results Summary
// ============================================================================
console.log('\n' + YELLOW + '='.repeat(60) + RESET);
console.log(YELLOW + 'Test Results Summary' + RESET);
console.log(YELLOW + '='.repeat(60) + RESET + '\n');
console.log(`Total Tests: ${testsRun}`);
console.log(`${GREEN}Passed: ${testsPassed}${RESET}`);
console.log(`${RED}Failed: ${testsFailed}${RESET}`);
if (testsFailed > 0) {
console.log(`\n${RED}❌ TESTS FAILED${RESET}\n`);
process.exit(1);
} else {
console.log(`\n${GREEN}✅ ALL TESTS PASSED${RESET}\n`);
process.exit(0);
}

15
src/sdk/parser.ts
View File

@@ -4,6 +4,7 @@
*/
import { logger } from '../utils/logger.js';
import { ModeManager } from '../services/domain/ModeManager.js';
export interface ParsedObservation {
type: string;
@@ -51,19 +52,21 @@ export function parseObservations(text: string, correlationId?: string): ParsedO
// NOTE FROM THEDOTMACK: ALWAYS save observations - never skip. 10/24/2025
// All fields except type are nullable in schema
// If type is missing or invalid, use "change" as catch-all fallback
// If type is missing or invalid, use first type from mode as fallback
// Determine final type
let finalType = 'change'; // Default catch-all
// Determine final type using active mode's valid types
const mode = ModeManager.getInstance().getActiveMode();
const validTypes = mode.observation_types.map(t => t.id);
const fallbackType = validTypes[0]; // First type in mode's list is the fallback
let finalType = fallbackType;
if (type) {
const validTypes = ['bugfix', 'feature', 'refactor', 'change', 'discovery', 'decision'];
if (validTypes.includes(type.trim())) {
finalType = type.trim();
} else {
logger.warn('PARSER', `Invalid observation type: ${type}, using "change"`, { correlationId });
logger.warn('PARSER', `Invalid observation type: ${type}, using "${fallbackType}"`, { correlationId });
}
} else {
logger.warn('PARSER', 'Observation missing type field, using "change"', { correlationId });
logger.warn('PARSER', `Observation missing type field, using "${fallbackType}"`, { correlationId });
}
// All other fields are optional - save whatever we have

233
src/sdk/prompts.ts
View File

@@ -4,6 +4,7 @@
*/
import { logger } from '../utils/logger.js';
import type { ModeConfig } from '../services/domain/types.js';
export interface Observation {
id: number;
@@ -26,123 +27,63 @@ export interface SDKSession {
/**
* Build initial prompt to initialize the SDK agent
*/
export function buildInitPrompt(project: string, sessionId: string, userPrompt: string): string {
return `You are a Claude-Mem, a specialized observer tool for creating searchable memory FOR FUTURE SESSIONS.
CRITICAL: Record what was LEARNED/BUILT/FIXED/DEPLOYED/CONFIGURED, not what you (the observer) are doing.
You do not have access to tools. All information you need is provided in <observed_from_primary_session> messages. Create observations from what you observe - no investigation needed.
export function buildInitPrompt(project: string, sessionId: string, userPrompt: string, mode: ModeConfig): string {
return `${mode.prompts.system_identity}
<observed_from_primary_session>
<user_request>${userPrompt}</user_request>
<requested_at>${new Date().toISOString().split('T')[0]}</requested_at>
</observed_from_primary_session>
Your job is to monitor a different Claude Code session happening RIGHT NOW, with the goal of creating observations and progress summaries as the work is being done LIVE by the user. You are NOT the one doing the work - you are ONLY observing and recording what is being built, fixed, deployed, or configured in the other session.
${mode.prompts.observer_role}
SPATIAL AWARENESS: Tool executions include the working directory (tool_cwd) to help you understand:
- Which repository/project is being worked on
- Where files are located relative to the project root
- How to match requested paths to actual execution paths
${mode.prompts.spatial_awareness}
WHAT TO RECORD
--------------
Focus on deliverables and capabilities:
- What the system NOW DOES differently (new capabilities)
- What shipped to users/production (features, fixes, configs, docs)
- Changes in technical domains (auth, data, UI, infra, DevOps, docs)
${mode.prompts.recording_focus}
Use verbs like: implemented, fixed, deployed, configured, migrated, optimized, added, refactored
${mode.prompts.skip_guidance}
✅ GOOD EXAMPLES (describes what was built):
- "Authentication now supports OAuth2 with PKCE flow"
- "Deployment pipeline runs canary releases with auto-rollback"
- "Database indexes optimized for common query patterns"
❌ BAD EXAMPLES (describes observation process - DO NOT DO THIS):
- "Analyzed authentication implementation and stored findings"
- "Tracked deployment steps and logged outcomes"
- "Monitored database performance and recorded metrics"
WHEN TO SKIP
------------
Skip routine operations:
- Empty status checks
- Package installations with no errors
- Simple file listings
- Repetitive operations you've already documented
- If file related research comes back as empty or not found
- **No output necessary if skipping.**
OUTPUT FORMAT
-------------
Output observations using this XML structure:
${mode.prompts.output_format_header}
\`\`\`xml
<observation>
<type>[ bugfix | feature | refactor | change | discovery | decision ]</type>
<type>[ ${mode.observation_types.map(t => t.id).join(' | ')} ]</type>
<!--
**type**: MUST be EXACTLY one of these 6 options (no other values allowed):
- bugfix: something was broken, now fixed
- feature: new capability or functionality added
- refactor: code restructured, behavior unchanged
- change: generic modification (docs, config, misc)
- discovery: learning about existing system
- decision: architectural/design choice with rationale
${mode.prompts.type_guidance}
-->
<title>[**title**: Short title capturing the core action or topic]</title>
<subtitle>[**subtitle**: One sentence explanation (max 24 words)]</subtitle>
<title>${mode.prompts.xml_title_placeholder}</title>
<subtitle>${mode.prompts.xml_subtitle_placeholder}</subtitle>
<facts>
<fact>[Concise, self-contained statement]</fact>
<fact>[Concise, self-contained statement]</fact>
<fact>[Concise, self-contained statement]</fact>
<fact>${mode.prompts.xml_fact_placeholder}</fact>
<fact>${mode.prompts.xml_fact_placeholder}</fact>
<fact>${mode.prompts.xml_fact_placeholder}</fact>
</facts>
<!--
**facts**: Concise, self-contained statements
Each fact is ONE piece of information
No pronouns - each fact must stand alone
Include specific details: filenames, functions, values
${mode.prompts.field_guidance}
-->
<narrative>[**narrative**: Full context: What was done, how it works, why it matters]</narrative>
<narrative>${mode.prompts.xml_narrative_placeholder}</narrative>
<concepts>
<concept>[knowledge-type-category]</concept>
<concept>[knowledge-type-category]</concept>
<concept>${mode.prompts.xml_concept_placeholder}</concept>
<concept>${mode.prompts.xml_concept_placeholder}</concept>
</concepts>
<!--
**concepts**: 2-5 knowledge-type categories. MUST use ONLY these exact keywords:
- how-it-works: understanding mechanisms
- why-it-exists: purpose or rationale
- what-changed: modifications made
- problem-solution: issues and their fixes
- gotcha: traps or edge cases
- pattern: reusable approach
- trade-off: pros/cons of a decision
IMPORTANT: Do NOT include the observation type (change/discovery/decision) as a concept.
Types and concepts are separate dimensions.
${mode.prompts.concept_guidance}
-->
<files_read>
<file>[path/to/file]</file>
<file>[path/to/file]</file>
<file>${mode.prompts.xml_file_placeholder}</file>
<file>${mode.prompts.xml_file_placeholder}</file>
</files_read>
<files_modified>
<file>[path/to/file]</file>
<file>[path/to/file]</file>
<file>${mode.prompts.xml_file_placeholder}</file>
<file>${mode.prompts.xml_file_placeholder}</file>
</files_modified>
<!--
**files**: All files touched (full paths from project root)
-->
</observation>
\`\`\`
${mode.prompts.format_examples}
IMPORTANT! DO NOT do any work right now other than generating this OBSERVATIONS from tool use messages - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.
${mode.prompts.footer}
Never reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.
Remember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your help!
MEMORY PROCESSING START
=======================`;
${mode.prompts.header_memory_start}`;
}
/**
@@ -176,7 +117,7 @@ export function buildObservationPrompt(obs: Observation): string {
/**
* Build prompt to generate progress summary
*/
export function buildSummaryPrompt(session: SDKSession): string {
export function buildSummaryPrompt(session: SDKSession, mode: ModeConfig): string {
const lastAssistantMessage = session.last_assistant_message || logger.happyPathError(
'SDK',
'Missing last_assistant_message in session for summary prompt',
@@ -185,28 +126,23 @@ export function buildSummaryPrompt(session: SDKSession): string {
''
);
return `PROGRESS SUMMARY CHECKPOINT
===========================
Write progress notes of what was done, what was learned, and what's next. This is a checkpoint to capture progress so far. The session is ongoing - you may receive more requests and tool executions after this summary. Write "next_steps" as the current trajectory of work (what's actively being worked on or coming up next), not as post-session future work. Always write at least a minimal summary explaining current progress, even if work is still in early stages, so that users see a summary output tied to each request.
return `${mode.prompts.header_summary_checkpoint}
${mode.prompts.summary_instruction}
Claude's Full Response to User:
${mode.prompts.summary_context_label}
${lastAssistantMessage}
Respond in this XML format:
${mode.prompts.summary_format_instruction}
<summary>
<request>[Short title capturing the user's request AND the substance of what was discussed/done]</request>
<investigated>[What has been explored so far? What was examined?]</investigated>
<learned>[What have you learned about how things work?]</learned>
<completed>[What work has been completed so far? What has shipped or changed?]</completed>
<next_steps>[What are you actively working on or planning to work on next in this session?]</next_steps>
<notes>[Additional insights or observations about the current progress]</notes>
<request>${mode.prompts.xml_summary_request_placeholder}</request>
<investigated>${mode.prompts.xml_summary_investigated_placeholder}</investigated>
<learned>${mode.prompts.xml_summary_learned_placeholder}</learned>
<completed>${mode.prompts.xml_summary_completed_placeholder}</completed>
<next_steps>${mode.prompts.xml_summary_next_steps_placeholder}</next_steps>
<notes>${mode.prompts.xml_summary_notes_placeholder}</notes>
</summary>
IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.
Never reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.
Thank you, this summary will be very useful for keeping track of our progress!`;
${mode.prompts.summary_footer}`;
}
/**
@@ -230,96 +166,65 @@ Thank you, this summary will be very useful for keeping track of our progress!`;
* Called when: promptNumber > 1 (see SDKAgent.ts line 150)
* First prompt: Uses buildInitPrompt instead (promptNumber === 1)
*/
export function buildContinuationPrompt(userPrompt: string, promptNumber: number, claudeSessionId: string): string {
return `
Hello memory agent, you are continuing to observe the primary Claude session.
export function buildContinuationPrompt(userPrompt: string, promptNumber: number, claudeSessionId: string, mode: ModeConfig): string {
return `${mode.prompts.continuation_greeting}
<observed_from_primary_session>
<user_request>${userPrompt}</user_request>
<requested_at>${new Date().toISOString().split('T')[0]}</requested_at>
</observed_from_primary_session>
You do not have access to tools. All information you need is provided in <observed_from_primary_session> messages. Create observations from what you observe - no investigation needed.
${mode.prompts.system_identity}
CRITICAL: Record what was LEARNED/BUILT/FIXED/DEPLOYED/CONFIGURED, not what you (the observer) are doing. Focus on deliverables and capabilities - what the system NOW DOES differently.
${mode.prompts.observer_role}
WHEN TO SKIP
------------
Skip routine operations:
- Empty status checks
- Package installations with no errors
- Simple file listings
- Repetitive operations you've already documented
- If file related research comes back as empty or not found
- **No output necessary if skipping.**
${mode.prompts.spatial_awareness}
IMPORTANT: Continue generating observations from tool use messages using the XML structure below.
${mode.prompts.recording_focus}
OUTPUT FORMAT
-------------
Output observations using this XML structure:
${mode.prompts.skip_guidance}
${mode.prompts.continuation_instruction}
${mode.prompts.output_format_header}
\`\`\`xml
<observation>
<type>[ bugfix | feature | refactor | change | discovery | decision ]</type>
<type>[ ${mode.observation_types.map(t => t.id).join(' | ')} ]</type>
<!--
**type**: MUST be EXACTLY one of these 6 options (no other values allowed):
- bugfix: something was broken, now fixed
- feature: new capability or functionality added
- refactor: code restructured, behavior unchanged
- change: generic modification (docs, config, misc)
- discovery: learning about existing system
- decision: architectural/design choice with rationale
${mode.prompts.type_guidance}
-->
<title>[**title**: Short title capturing the core action or topic]</title>
<subtitle>[**subtitle**: One sentence explanation (max 24 words)]</subtitle>
<title>${mode.prompts.xml_title_placeholder}</title>
<subtitle>${mode.prompts.xml_subtitle_placeholder}</subtitle>
<facts>
<fact>[Concise, self-contained statement]</fact>
<fact>[Concise, self-contained statement]</fact>
<fact>[Concise, self-contained statement]</fact>
<fact>${mode.prompts.xml_fact_placeholder}</fact>
<fact>${mode.prompts.xml_fact_placeholder}</fact>
<fact>${mode.prompts.xml_fact_placeholder}</fact>
</facts>
<!--
**facts**: Concise, self-contained statements
Each fact is ONE piece of information
No pronouns - each fact must stand alone
Include specific details: filenames, functions, values
${mode.prompts.field_guidance}
-->
<narrative>[**narrative**: Full context: What was done, how it works, why it matters]</narrative>
<narrative>${mode.prompts.xml_narrative_placeholder}</narrative>
<concepts>
<concept>[knowledge-type-category]</concept>
<concept>[knowledge-type-category]</concept>
<concept>${mode.prompts.xml_concept_placeholder}</concept>
<concept>${mode.prompts.xml_concept_placeholder}</concept>
</concepts>
<!--
**concepts**: 2-5 knowledge-type categories. MUST use ONLY these exact keywords:
- how-it-works: understanding mechanisms
- why-it-exists: purpose or rationale
- what-changed: modifications made
- problem-solution: issues and their fixes
- gotcha: traps or edge cases
- pattern: reusable approach
- trade-off: pros/cons of a decision
IMPORTANT: Do NOT include the observation type (change/discovery/decision) as a concept.
Types and concepts are separate dimensions.
${mode.prompts.concept_guidance}
-->
<files_read>
<file>[path/to/file]</file>
<file>[path/to/file]</file>
<file>${mode.prompts.xml_file_placeholder}</file>
<file>${mode.prompts.xml_file_placeholder}</file>
</files_read>
<files_modified>
<file>[path/to/file]</file>
<file>[path/to/file]</file>
<file>${mode.prompts.xml_file_placeholder}</file>
<file>${mode.prompts.xml_file_placeholder}</file>
</files_modified>
<!--
**files**: All files touched (full paths from project root)
-->
</observation>
\`\`\`
${mode.prompts.format_examples}
Never reference yourself or your own actions. Do not output anything other than the observation content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful observations.
${mode.prompts.footer}
Remember that we record these observations as a way of helping us stay on track with our progress, and to help us keep important decisions and changes at the forefront of our minds! :) Thank you so much for your continued help!
MEMORY PROCESSING CONTINUED
===========================`;
${mode.prompts.header_memory_continued}`;
}

96
src/services/context-generator.ts
View File

@@ -9,12 +9,6 @@ import path from 'path';
import { homedir } from 'os';
import { existsSync, readFileSync, unlinkSync } from 'fs';
import { SessionStore } from './sqlite/SessionStore.js';
import {
OBSERVATION_TYPES,
OBSERVATION_CONCEPTS,
TYPE_ICON_MAP,
TYPE_WORK_EMOJI_MAP
} from '../constants/observation-metadata.js';
import { logger } from '../utils/logger.js';
import { SettingsDefaultsManager } from '../shared/SettingsDefaultsManager.js';
import {
@@ -26,6 +20,7 @@ import {
extractFirstFile
} from '../shared/timeline-formatting.js';
import { getProjectName } from '../utils/project-name.js';
import { ModeManager } from './domain/ModeManager.js';
// Version marker path - use homedir-based path that works in both CJS and ESM contexts
const VERSION_MARKER_PATH = path.join(homedir(), '.claude', 'plugins', 'marketplaces', 'thedotmack', 'plugin', '.install-version');
@@ -60,43 +55,24 @@ function loadContextConfig(): ContextConfig {
const settingsPath = path.join(homedir(), '.claude-mem', 'settings.json');
const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
try {
return {
totalObservationCount: parseInt(settings.CLAUDE_MEM_CONTEXT_OBSERVATIONS, 10),
fullObservationCount: parseInt(settings.CLAUDE_MEM_CONTEXT_FULL_COUNT, 10),
sessionCount: parseInt(settings.CLAUDE_MEM_CONTEXT_SESSION_COUNT, 10),
showReadTokens: settings.CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS === 'true',
showWorkTokens: settings.CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS === 'true',
showSavingsAmount: settings.CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT === 'true',
showSavingsPercent: settings.CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT === 'true',
observationTypes: new Set(
settings.CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES.split(',').map((t: string) => t.trim()).filter(Boolean)
),
observationConcepts: new Set(
settings.CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS.split(',').map((c: string) => c.trim()).filter(Boolean)
),
fullObservationField: settings.CLAUDE_MEM_CONTEXT_FULL_FIELD as 'narrative' | 'facts',
showLastSummary: settings.CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY === 'true',
showLastMessage: settings.CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE === 'true',
};
} catch (error) {
logger.warn('WORKER', 'Failed to load context settings, using defaults', {}, error as Error);
// Return defaults on error
return {
totalObservationCount: 50,
fullObservationCount: 5,
sessionCount: 10,
showReadTokens: true,
showWorkTokens: true,
showSavingsAmount: true,
showSavingsPercent: true,
observationTypes: new Set(OBSERVATION_TYPES),
observationConcepts: new Set(OBSERVATION_CONCEPTS),
fullObservationField: 'narrative' as const,
showLastSummary: true,
showLastMessage: false,
};
}
return {
totalObservationCount: parseInt(settings.CLAUDE_MEM_CONTEXT_OBSERVATIONS, 10),
fullObservationCount: parseInt(settings.CLAUDE_MEM_CONTEXT_FULL_COUNT, 10),
sessionCount: parseInt(settings.CLAUDE_MEM_CONTEXT_SESSION_COUNT, 10),
showReadTokens: settings.CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS === 'true',
showWorkTokens: settings.CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS === 'true',
showSavingsAmount: settings.CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT === 'true',
showSavingsPercent: settings.CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT === 'true',
observationTypes: new Set(
settings.CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES.split(',').map((t: string) => t.trim()).filter(Boolean)
),
observationConcepts: new Set(
settings.CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS.split(',').map((c: string) => c.trim()).filter(Boolean)
),
fullObservationField: settings.CLAUDE_MEM_CONTEXT_FULL_FIELD as 'narrative' | 'facts',
showLastSummary: settings.CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY === 'true',
showLastMessage: settings.CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE === 'true',
};
}
// Configuration constants
@@ -280,20 +256,16 @@ export async function generateContext(input?: ContextInput, useColors: boolean =
let priorAssistantMessage = '';
if (config.showLastMessage && observations.length > 0) {
try {
const currentSessionId = input?.session_id;
const priorSessionObs = observations.find(obs => obs.sdk_session_id !== currentSessionId);
const currentSessionId = input?.session_id;
const priorSessionObs = observations.find(obs => obs.sdk_session_id !== currentSessionId);
if (priorSessionObs) {
const priorSessionId = priorSessionObs.sdk_session_id;
const dashedCwd = cwdToDashed(cwd);
const transcriptPath = path.join(homedir(), '.claude', 'projects', dashedCwd, `${priorSessionId}.jsonl`);
const messages = extractPriorMessages(transcriptPath);
priorUserMessage = messages.userMessage;
priorAssistantMessage = messages.assistantMessage;
}
} catch (error) {
// Expected: Transcript file may not exist or be readable
if (priorSessionObs) {
const priorSessionId = priorSessionObs.sdk_session_id;
const dashedCwd = cwdToDashed(cwd);
const transcriptPath = path.join(homedir(), '.claude', 'projects', dashedCwd, `${priorSessionId}.jsonl`);
const messages = extractPriorMessages(transcriptPath);
priorUserMessage = messages.userMessage;
priorAssistantMessage = messages.assistantMessage;
}
}
@@ -325,11 +297,13 @@ export async function generateContext(input?: ContextInput, useColors: boolean =
// Chronological Timeline
if (timelineObs.length > 0) {
// Legend
// Legend - generate dynamically from active mode
const mode = ModeManager.getInstance().getActiveMode();
const typeLegendItems = mode.observation_types.map(t => `${t.emoji} ${t.id}`).join(' | ');
if (useColors) {
output.push(`${colors.dim}Legend: 🎯 session-request | 🔴 bugfix | 🟣 feature | 🔄 refactor | ✅ change | 🔵 discovery | ⚖️ decision${colors.reset}`);
output.push(`${colors.dim}Legend: 🎯 session-request | ${typeLegendItems}${colors.reset}`);
} else {
output.push(`**Legend:** 🎯 session-request | 🔴 bugfix | 🟣 feature | 🔄 refactor | ✅ change | 🔵 discovery | ⚖️ decision`);
output.push(`**Legend:** 🎯 session-request | ${typeLegendItems}`);
}
output.push('');
@@ -536,7 +510,7 @@ export async function generateContext(input?: ContextInput, useColors: boolean =
const time = formatTime(obs.created_at);
const title = obs.title || 'Untitled';
const icon = TYPE_ICON_MAP[obs.type as keyof typeof TYPE_ICON_MAP] || '•';
const icon = ModeManager.getInstance().getTypeIcon(obs.type);
const obsSize = (obs.title?.length || 0) +
(obs.subtitle?.length || 0) +
@@ -544,7 +518,7 @@ export async function generateContext(input?: ContextInput, useColors: boolean =
JSON.stringify(obs.facts || []).length;
const readTokens = Math.ceil(obsSize / CHARS_PER_TOKEN_ESTIMATE);
const discoveryTokens = obs.discovery_tokens || 0;
const workEmoji = TYPE_WORK_EMOJI_MAP[obs.type as keyof typeof TYPE_WORK_EMOJI_MAP] || '🔍';
const workEmoji = ModeManager.getInstance().getWorkEmoji(obs.type);
const discoveryDisplay = discoveryTokens > 0 ? `${workEmoji} ${discoveryTokens.toLocaleString()}` : '-';
const showTime = time !== lastTime;

254
src/services/domain/ModeManager.ts Normal file
View File

@@ -0,0 +1,254 @@
/**
* ModeManager - Singleton for loading and managing mode profiles
*
* Mode profiles define observation types, concepts, and prompts for different use cases.
* Default mode is 'code' (software development). Other modes like 'email-investigation'
* can be selected via CLAUDE_MEM_MODE setting.
*/
import { readFileSync, existsSync } from 'fs';
import { join } from 'path';
import type { ModeConfig, ObservationType, ObservationConcept } from './types.js';
import { logger } from '../../utils/logger.js';
import { getPackageRoot } from '../../shared/paths.js';
export class ModeManager {
private static instance: ModeManager | null = null;
private activeMode: ModeConfig | null = null;
private modesDir: string;
private constructor() {
// Modes are in plugin/modes/
// getPackageRoot() points to plugin/ in production and src/ in development
// We want to ensure we find the modes directory which is at the project root/plugin/modes
const packageRoot = getPackageRoot();
// Check for plugin/modes relative to package root (covers both dev and prod if paths are right)
const possiblePaths = [
join(packageRoot, 'modes'), // Production (plugin/modes)
join(packageRoot, '..', 'plugin', 'modes'), // Development (src/../plugin/modes)
];
const foundPath = possiblePaths.find(p => existsSync(p));
this.modesDir = foundPath || possiblePaths[0];
}
/**
* Get singleton instance
*/
static getInstance(): ModeManager {
if (!ModeManager.instance) {
ModeManager.instance = new ModeManager();
}
return ModeManager.instance;
}
/**
* Parse mode ID for inheritance pattern (parent--override)
*/
private parseInheritance(modeId: string): {
hasParent: boolean;
parentId: string;
overrideId: string;
} {
const parts = modeId.split('--');
if (parts.length === 1) {
return { hasParent: false, parentId: '', overrideId: '' };
}
// Support only one level: code--ko, not code--ko--verbose
if (parts.length > 2) {
throw new Error(
`Invalid mode inheritance: ${modeId}. Only one level of inheritance supported (parent--override)`
);
}
return {
hasParent: true,
parentId: parts[0],
overrideId: modeId // Use the full modeId (e.g., code--es) to find the override file
};
}
/**
* Check if value is a plain object (not array, not null)
*/
private isPlainObject(value: unknown): boolean {
return (
value !== null &&
typeof value === 'object' &&
!Array.isArray(value)
);
}
/**
* Deep merge two objects
* - Recursively merge nested objects
* - Replace arrays completely (no merging)
* - Override primitives
*/
private deepMerge<T>(base: T, override: Partial<T>): T {
const result = { ...base } as T;
for (const key in override) {
const overrideValue = override[key];
const baseValue = base[key];
if (this.isPlainObject(overrideValue) && this.isPlainObject(baseValue)) {
// Recursively merge nested objects
result[key] = this.deepMerge(baseValue, overrideValue as any);
} else {
// Replace arrays and primitives completely
result[key] = overrideValue as T[Extract<keyof T, string>];
}
}
return result;
}
/**
* Load a mode file from disk without inheritance processing
*/
private loadModeFile(modeId: string): ModeConfig {
const modePath = join(this.modesDir, `${modeId}.json`);
if (!existsSync(modePath)) {
throw new Error(`Mode file not found: ${modePath}`);
}
const jsonContent = readFileSync(modePath, 'utf-8');
return JSON.parse(jsonContent) as ModeConfig;
}
/**
* Load a mode profile by ID with inheritance support
* Caches the result for subsequent calls
*
* Supports inheritance via parent--override pattern (e.g., code--ko)
* - Loads parent mode recursively
* - Loads override file from modes directory
* - Deep merges override onto parent
*/
loadMode(modeId: string): ModeConfig {
const inheritance = this.parseInheritance(modeId);
// No inheritance - load file directly (existing behavior)
if (!inheritance.hasParent) {
try {
const mode = this.loadModeFile(modeId);
this.activeMode = mode;
logger.debug('SYSTEM', `Loaded mode: ${mode.name} (${modeId})`, undefined, {
types: mode.observation_types.map(t => t.id),
concepts: mode.observation_concepts.map(c => c.id)
});
return mode;
} catch (error) {
logger.warn('SYSTEM', `Mode file not found: ${modeId}, falling back to 'code'`);
// If we're already trying to load 'code', throw to prevent infinite recursion
if (modeId === 'code') {
throw new Error('Critical: code.json mode file missing');
}
return this.loadMode('code');
}
}
// Has inheritance - load parent and merge with override
const { parentId, overrideId } = inheritance;
// Load parent mode recursively
let parentMode: ModeConfig;
try {
parentMode = this.loadMode(parentId);
} catch (error) {
logger.warn('SYSTEM', `Parent mode '${parentId}' not found for ${modeId}, falling back to 'code'`);
parentMode = this.loadMode('code');
}
// Load override file
let overrideConfig: Partial<ModeConfig>;
try {
overrideConfig = this.loadModeFile(overrideId);
logger.debug('SYSTEM', `Loaded override file: ${overrideId} for parent ${parentId}`);
} catch (error) {
logger.warn('SYSTEM', `Override file '${overrideId}' not found, using parent mode '${parentId}' only`);
this.activeMode = parentMode;
return parentMode;
}
// Validate override file loaded successfully
if (!overrideConfig) {
logger.warn('SYSTEM', `Invalid override file: ${overrideId}, using parent mode '${parentId}' only`);
this.activeMode = parentMode;
return parentMode;
}
// Deep merge override onto parent
const mergedMode = this.deepMerge(parentMode, overrideConfig);
this.activeMode = mergedMode;
logger.debug('SYSTEM', `Loaded mode with inheritance: ${mergedMode.name} (${modeId} = ${parentId} + ${overrideId})`, undefined, {
parent: parentId,
override: overrideId,
types: mergedMode.observation_types.map(t => t.id),
concepts: mergedMode.observation_concepts.map(c => c.id)
});
return mergedMode;
}
/**
* Get currently active mode
*/
getActiveMode(): ModeConfig {
if (!this.activeMode) {
throw new Error('No mode loaded. Call loadMode() first.');
}
return this.activeMode;
}
/**
* Get all observation types from active mode
*/
getObservationTypes(): ObservationType[] {
return this.getActiveMode().observation_types;
}
/**
* Get all observation concepts from active mode
*/
getObservationConcepts(): ObservationConcept[] {
return this.getActiveMode().observation_concepts;
}
/**
* Get icon for a specific observation type
*/
getTypeIcon(typeId: string): string {
const type = this.getObservationTypes().find(t => t.id === typeId);
return type?.emoji || '📝';
}
/**
* Get work emoji for a specific observation type
*/
getWorkEmoji(typeId: string): string {
const type = this.getObservationTypes().find(t => t.id === typeId);
return type?.work_emoji || '📝';
}
/**
* Validate that a type ID exists in the active mode
*/
validateType(typeId: string): boolean {
return this.getObservationTypes().some(t => t.id === typeId);
}
/**
* Get label for a specific observation type
*/
getTypeLabel(typeId: string): string {
const type = this.getObservationTypes().find(t => t.id === typeId);
return type?.label || typeId;
}
}

72
src/services/domain/types.ts Normal file
View File

@@ -0,0 +1,72 @@
/**
* TypeScript interfaces for mode configuration system
*/
export interface ObservationType {
id: string;
label: string;
description: string;
emoji: string;
work_emoji: string;
}
export interface ObservationConcept {
id: string;
label: string;
description: string;
}
export interface ModePrompts {
system_identity: string; // Base persona and role definition
language_instruction?: string; // Optional language constraints (e.g., "Write in Korean")
spatial_awareness: string; // Working directory context guidance
observer_role: string; // What the observer's job is in this mode
recording_focus: string; // What to record and how to think about it
skip_guidance: string; // What to skip recording
type_guidance: string; // Valid observation types for this mode
concept_guidance: string; // Valid concept categories for this mode
field_guidance: string; // Guidance for facts/files fields
output_format_header: string; // Text introducing the XML schema
format_examples: string; // Optional additional XML examples (empty string if not needed)
footer: string; // Closing instructions and encouragement
// Observation XML placeholders
xml_title_placeholder: string; // e.g., "[**title**: Short title capturing the core action or topic]"
xml_subtitle_placeholder: string; // e.g., "[**subtitle**: One sentence explanation (max 24 words)]"
xml_fact_placeholder: string; // e.g., "[Concise, self-contained statement]"
xml_narrative_placeholder: string; // e.g., "[**narrative**: Full context: What was done, how it works, why it matters]"
xml_concept_placeholder: string; // e.g., "[knowledge-type-category]"
xml_file_placeholder: string; // e.g., "[path/to/file]"
// Summary XML placeholders
xml_summary_request_placeholder: string; // e.g., "[Short title capturing the user's request AND...]"
xml_summary_investigated_placeholder: string; // e.g., "[What has been explored so far? What was examined?]"
xml_summary_learned_placeholder: string; // e.g., "[What have you learned about how things work?]"
xml_summary_completed_placeholder: string; // e.g., "[What work has been completed so far? What has shipped or changed?]"
xml_summary_next_steps_placeholder: string; // e.g., "[What are you actively working on or planning to work on next in this session?]"
xml_summary_notes_placeholder: string; // e.g., "[Additional insights or observations about the current progress]"
// Section headers (with separator lines)
header_memory_start: string; // e.g., "MEMORY PROCESSING START\n======================="
header_memory_continued: string; // e.g., "MEMORY PROCESSING CONTINUED\n==========================="
header_summary_checkpoint: string; // e.g., "PROGRESS SUMMARY CHECKPOINT\n==========================="
// Continuation prompts
continuation_greeting: string; // e.g., "Hello memory agent, you are continuing to observe the primary Claude session."
continuation_instruction: string; // e.g., "IMPORTANT: Continue generating observations from tool use messages using the XML structure below."
// Summary prompts
summary_instruction: string; // Instructions for writing progress summary
summary_context_label: string; // Label for Claude's response section (e.g., "Claude's Full Response to User:")
summary_format_instruction: string; // Instruction to use XML format (e.g., "Respond in this XML format:")
summary_footer: string; // Footer with closing instructions and language requirement
}
export interface ModeConfig {
name: string;
description: string;
version: string;
observation_types: ObservationType[];
observation_concepts: ObservationConcept[];
prompts: ModePrompts;
}

188
src/services/sqlite/SessionSearch.ts
View File

@@ -50,104 +50,100 @@ export class SessionSearch {
* TODO: Remove FTS5 infrastructure in future major version (v7.0.0)
*/
private ensureFTSTables(): void {
try {
// Check if FTS tables already exist
const tables = this.db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name LIKE '%_fts'").all() as TableNameRow[];
const hasFTS = tables.some(t => t.name === 'observations_fts' || t.name === 'session_summaries_fts');
// Check if FTS tables already exist
const tables = this.db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name LIKE '%_fts'").all() as TableNameRow[];
const hasFTS = tables.some(t => t.name === 'observations_fts' || t.name === 'session_summaries_fts');
if (hasFTS) {
// Already migrated
return;
}
console.log('[SessionSearch] Creating FTS5 tables...');
// Create observations_fts virtual table
this.db.run(`
CREATE VIRTUAL TABLE IF NOT EXISTS observations_fts USING fts5(
title,
subtitle,
narrative,
text,
facts,
concepts,
content='observations',
content_rowid='id'
);
`);
// Populate with existing data
this.db.run(`
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
SELECT id, title, subtitle, narrative, text, facts, concepts
FROM observations;
`);
// Create triggers for observations
this.db.run(`
CREATE TRIGGER IF NOT EXISTS observations_ai AFTER INSERT ON observations BEGIN
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts);
END;
CREATE TRIGGER IF NOT EXISTS observations_ad AFTER DELETE ON observations BEGIN
INSERT INTO observations_fts(observations_fts, rowid, title, subtitle, narrative, text, facts, concepts)
VALUES('delete', old.id, old.title, old.subtitle, old.narrative, old.text, old.facts, old.concepts);
END;
CREATE TRIGGER IF NOT EXISTS observations_au AFTER UPDATE ON observations BEGIN
INSERT INTO observations_fts(observations_fts, rowid, title, subtitle, narrative, text, facts, concepts)
VALUES('delete', old.id, old.title, old.subtitle, old.narrative, old.text, old.facts, old.concepts);
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts);
END;
`);
// Create session_summaries_fts virtual table
this.db.run(`
CREATE VIRTUAL TABLE IF NOT EXISTS session_summaries_fts USING fts5(
request,
investigated,
learned,
completed,
next_steps,
notes,
content='session_summaries',
content_rowid='id'
);
`);
// Populate with existing data
this.db.run(`
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
SELECT id, request, investigated, learned, completed, next_steps, notes
FROM session_summaries;
`);
// Create triggers for session_summaries
this.db.run(`
CREATE TRIGGER IF NOT EXISTS session_summaries_ai AFTER INSERT ON session_summaries BEGIN
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
END;
CREATE TRIGGER IF NOT EXISTS session_summaries_ad AFTER DELETE ON session_summaries BEGIN
INSERT INTO session_summaries_fts(session_summaries_fts, rowid, request, investigated, learned, completed, next_steps, notes)
VALUES('delete', old.id, old.request, old.investigated, old.learned, old.completed, old.next_steps, old.notes);
END;
CREATE TRIGGER IF NOT EXISTS session_summaries_au AFTER UPDATE ON session_summaries BEGIN
INSERT INTO session_summaries_fts(session_summaries_fts, rowid, request, investigated, learned, completed, next_steps, notes)
VALUES('delete', old.id, old.request, old.investigated, old.learned, old.completed, old.next_steps, old.notes);
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
END;
`);
console.log('[SessionSearch] FTS5 tables created successfully');
} catch (error: any) {
console.error('[SessionSearch] FTS migration error:', error.message);
if (hasFTS) {
// Already migrated
return;
}
console.log('[SessionSearch] Creating FTS5 tables...');
// Create observations_fts virtual table
this.db.run(`
CREATE VIRTUAL TABLE IF NOT EXISTS observations_fts USING fts5(
title,
subtitle,
narrative,
text,
facts,
concepts,
content='observations',
content_rowid='id'
);
`);
// Populate with existing data
this.db.run(`
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
SELECT id, title, subtitle, narrative, text, facts, concepts
FROM observations;
`);
// Create triggers for observations
this.db.run(`
CREATE TRIGGER IF NOT EXISTS observations_ai AFTER INSERT ON observations BEGIN
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts);
END;
CREATE TRIGGER IF NOT EXISTS observations_ad AFTER DELETE ON observations BEGIN
INSERT INTO observations_fts(observations_fts, rowid, title, subtitle, narrative, text, facts, concepts)
VALUES('delete', old.id, old.title, old.subtitle, old.narrative, old.text, old.facts, old.concepts);
END;
CREATE TRIGGER IF NOT EXISTS observations_au AFTER UPDATE ON observations BEGIN
INSERT INTO observations_fts(observations_fts, rowid, title, subtitle, narrative, text, facts, concepts)
VALUES('delete', old.id, old.title, old.subtitle, old.narrative, old.text, old.facts, old.concepts);
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts);
END;
`);
// Create session_summaries_fts virtual table
this.db.run(`
CREATE VIRTUAL TABLE IF NOT EXISTS session_summaries_fts USING fts5(
request,
investigated,
learned,
completed,
next_steps,
notes,
content='session_summaries',
content_rowid='id'
);
`);
// Populate with existing data
this.db.run(`
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
SELECT id, request, investigated, learned, completed, next_steps, notes
FROM session_summaries;
`);
// Create triggers for session_summaries
this.db.run(`
CREATE TRIGGER IF NOT EXISTS session_summaries_ai AFTER INSERT ON session_summaries BEGIN
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
END;
CREATE TRIGGER IF NOT EXISTS session_summaries_ad AFTER DELETE ON session_summaries BEGIN
INSERT INTO session_summaries_fts(session_summaries_fts, rowid, request, investigated, learned, completed, next_steps, notes)
VALUES('delete', old.id, old.request, old.investigated, old.learned, old.completed, old.next_steps, old.notes);
END;
CREATE TRIGGER IF NOT EXISTS session_summaries_au AFTER UPDATE ON session_summaries BEGIN
INSERT INTO session_summaries_fts(session_summaries_fts, rowid, request, investigated, learned, completed, next_steps, notes)
VALUES('delete', old.id, old.request, old.investigated, old.learned, old.completed, old.next_steps, old.notes);
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
END;
`);
console.log('[SessionSearch] FTS5 tables created successfully');
}

578
src/services/sqlite/SessionStore.ts
View File

@@ -144,152 +144,140 @@ export class SessionStore {
* Ensure worker_port column exists (migration 5)
*/
private ensureWorkerPortColumn(): void {
try {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(5) as SchemaVersion | undefined;
if (applied) return;
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(5) as SchemaVersion | undefined;
if (applied) return;
// Check if column exists
const tableInfo = this.db.query('PRAGMA table_info(sdk_sessions)').all() as TableColumnInfo[];
const hasWorkerPort = tableInfo.some(col => col.name === 'worker_port');
// Check if column exists
const tableInfo = this.db.query('PRAGMA table_info(sdk_sessions)').all() as TableColumnInfo[];
const hasWorkerPort = tableInfo.some(col => col.name === 'worker_port');
if (!hasWorkerPort) {
this.db.run('ALTER TABLE sdk_sessions ADD COLUMN worker_port INTEGER');
console.log('[SessionStore] Added worker_port column to sdk_sessions table');
}
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(5, new Date().toISOString());
} catch (error: any) {
console.error('[SessionStore] Migration error:', error.message);
if (!hasWorkerPort) {
this.db.run('ALTER TABLE sdk_sessions ADD COLUMN worker_port INTEGER');
console.log('[SessionStore] Added worker_port column to sdk_sessions table');
}
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(5, new Date().toISOString());
}
/**
* Ensure prompt tracking columns exist (migration 6)
*/
private ensurePromptTrackingColumns(): void {
try {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(6) as SchemaVersion | undefined;
if (applied) return;
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(6) as SchemaVersion | undefined;
if (applied) return;
// Check sdk_sessions for prompt_counter
const sessionsInfo = this.db.query('PRAGMA table_info(sdk_sessions)').all() as TableColumnInfo[];
const hasPromptCounter = sessionsInfo.some(col => col.name === 'prompt_counter');
// Check sdk_sessions for prompt_counter
const sessionsInfo = this.db.query('PRAGMA table_info(sdk_sessions)').all() as TableColumnInfo[];
const hasPromptCounter = sessionsInfo.some(col => col.name === 'prompt_counter');
if (!hasPromptCounter) {
this.db.run('ALTER TABLE sdk_sessions ADD COLUMN prompt_counter INTEGER DEFAULT 0');
console.log('[SessionStore] Added prompt_counter column to sdk_sessions table');
}
// Check observations for prompt_number
const observationsInfo = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const obsHasPromptNumber = observationsInfo.some(col => col.name === 'prompt_number');
if (!obsHasPromptNumber) {
this.db.run('ALTER TABLE observations ADD COLUMN prompt_number INTEGER');
console.log('[SessionStore] Added prompt_number column to observations table');
}
// Check session_summaries for prompt_number
const summariesInfo = this.db.query('PRAGMA table_info(session_summaries)').all() as TableColumnInfo[];
const sumHasPromptNumber = summariesInfo.some(col => col.name === 'prompt_number');
if (!sumHasPromptNumber) {
this.db.run('ALTER TABLE session_summaries ADD COLUMN prompt_number INTEGER');
console.log('[SessionStore] Added prompt_number column to session_summaries table');
}
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(6, new Date().toISOString());
} catch (error: any) {
console.error('[SessionStore] Prompt tracking migration error:', error.message);
if (!hasPromptCounter) {
this.db.run('ALTER TABLE sdk_sessions ADD COLUMN prompt_counter INTEGER DEFAULT 0');
console.log('[SessionStore] Added prompt_counter column to sdk_sessions table');
}
// Check observations for prompt_number
const observationsInfo = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const obsHasPromptNumber = observationsInfo.some(col => col.name === 'prompt_number');
if (!obsHasPromptNumber) {
this.db.run('ALTER TABLE observations ADD COLUMN prompt_number INTEGER');
console.log('[SessionStore] Added prompt_number column to observations table');
}
// Check session_summaries for prompt_number
const summariesInfo = this.db.query('PRAGMA table_info(session_summaries)').all() as TableColumnInfo[];
const sumHasPromptNumber = summariesInfo.some(col => col.name === 'prompt_number');
if (!sumHasPromptNumber) {
this.db.run('ALTER TABLE session_summaries ADD COLUMN prompt_number INTEGER');
console.log('[SessionStore] Added prompt_number column to session_summaries table');
}
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(6, new Date().toISOString());
}
/**
* Remove UNIQUE constraint from session_summaries.sdk_session_id (migration 7)
*/
private removeSessionSummariesUniqueConstraint(): void {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(7) as SchemaVersion | undefined;
if (applied) return;
// Check if UNIQUE constraint exists
const summariesIndexes = this.db.query('PRAGMA index_list(session_summaries)').all() as IndexInfo[];
const hasUniqueConstraint = summariesIndexes.some(idx => idx.unique === 1);
if (!hasUniqueConstraint) {
// Already migrated (no constraint exists)
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(7, new Date().toISOString());
return;
}
console.log('[SessionStore] Removing UNIQUE constraint from session_summaries.sdk_session_id...');
// Begin transaction
this.db.run('BEGIN TRANSACTION');
try {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(7) as SchemaVersion | undefined;
if (applied) return;
// Create new table without UNIQUE constraint
this.db.run(`
CREATE TABLE session_summaries_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
sdk_session_id TEXT NOT NULL,
project TEXT NOT NULL,
request TEXT,
investigated TEXT,
learned TEXT,
completed TEXT,
next_steps TEXT,
files_read TEXT,
files_edited TEXT,
notes TEXT,
prompt_number INTEGER,
created_at TEXT NOT NULL,
created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(sdk_session_id) REFERENCES sdk_sessions(sdk_session_id) ON DELETE CASCADE
)
`);
// Check if UNIQUE constraint exists
const summariesIndexes = this.db.query('PRAGMA index_list(session_summaries)').all() as IndexInfo[];
const hasUniqueConstraint = summariesIndexes.some(idx => idx.unique === 1);
// Copy data from old table
this.db.run(`
INSERT INTO session_summaries_new
SELECT id, sdk_session_id, project, request, investigated, learned,
completed, next_steps, files_read, files_edited, notes,
prompt_number, created_at, created_at_epoch
FROM session_summaries
`);
if (!hasUniqueConstraint) {
// Already migrated (no constraint exists)
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(7, new Date().toISOString());
return;
}
// Drop old table
this.db.run('DROP TABLE session_summaries');
console.log('[SessionStore] Removing UNIQUE constraint from session_summaries.sdk_session_id...');
// Rename new table
this.db.run('ALTER TABLE session_summaries_new RENAME TO session_summaries');
// Begin transaction
this.db.run('BEGIN TRANSACTION');
// Recreate indexes
this.db.run(`
CREATE INDEX idx_session_summaries_sdk_session ON session_summaries(sdk_session_id);
CREATE INDEX idx_session_summaries_project ON session_summaries(project);
CREATE INDEX idx_session_summaries_created ON session_summaries(created_at_epoch DESC);
`);
try {
// Create new table without UNIQUE constraint
this.db.run(`
CREATE TABLE session_summaries_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
sdk_session_id TEXT NOT NULL,
project TEXT NOT NULL,
request TEXT,
investigated TEXT,
learned TEXT,
completed TEXT,
next_steps TEXT,
files_read TEXT,
files_edited TEXT,
notes TEXT,
prompt_number INTEGER,
created_at TEXT NOT NULL,
created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(sdk_session_id) REFERENCES sdk_sessions(sdk_session_id) ON DELETE CASCADE
)
`);
// Commit transaction
this.db.run('COMMIT');
// Copy data from old table
this.db.run(`
INSERT INTO session_summaries_new
SELECT id, sdk_session_id, project, request, investigated, learned,
completed, next_steps, files_read, files_edited, notes,
prompt_number, created_at, created_at_epoch
FROM session_summaries
`);
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(7, new Date().toISOString());
// Drop old table
this.db.run('DROP TABLE session_summaries');
// Rename new table
this.db.run('ALTER TABLE session_summaries_new RENAME TO session_summaries');
// Recreate indexes
this.db.run(`
CREATE INDEX idx_session_summaries_sdk_session ON session_summaries(sdk_session_id);
CREATE INDEX idx_session_summaries_project ON session_summaries(project);
CREATE INDEX idx_session_summaries_created ON session_summaries(created_at_epoch DESC);
`);
// Commit transaction
this.db.run('COMMIT');
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(7, new Date().toISOString());
console.log('[SessionStore] Successfully removed UNIQUE constraint from session_summaries.sdk_session_id');
} catch (error: any) {
// Rollback on error
this.db.run('ROLLBACK');
throw error;
}
console.log('[SessionStore] Successfully removed UNIQUE constraint from session_summaries.sdk_session_id');
} catch (error: any) {
console.error('[SessionStore] Migration error (remove UNIQUE constraint):', error.message);
// Rollback on error
this.db.run('ROLLBACK');
throw error;
}
}
@@ -297,41 +285,37 @@ export class SessionStore {
* Add hierarchical fields to observations table (migration 8)
*/
private addObservationHierarchicalFields(): void {
try {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(8) as SchemaVersion | undefined;
if (applied) return;
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(8) as SchemaVersion | undefined;
if (applied) return;
// Check if new fields already exist
const tableInfo = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const hasTitle = tableInfo.some(col => col.name === 'title');
// Check if new fields already exist
const tableInfo = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const hasTitle = tableInfo.some(col => col.name === 'title');
if (hasTitle) {
// Already migrated
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(8, new Date().toISOString());
return;
}
console.log('[SessionStore] Adding hierarchical fields to observations table...');
// Add new columns
this.db.run(`
ALTER TABLE observations ADD COLUMN title TEXT;
ALTER TABLE observations ADD COLUMN subtitle TEXT;
ALTER TABLE observations ADD COLUMN facts TEXT;
ALTER TABLE observations ADD COLUMN narrative TEXT;
ALTER TABLE observations ADD COLUMN concepts TEXT;
ALTER TABLE observations ADD COLUMN files_read TEXT;
ALTER TABLE observations ADD COLUMN files_modified TEXT;
`);
// Record migration
if (hasTitle) {
// Already migrated
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(8, new Date().toISOString());
console.log('[SessionStore] Successfully added hierarchical fields to observations table');
} catch (error: any) {
console.error('[SessionStore] Migration error (add hierarchical fields):', error.message);
return;
}
console.log('[SessionStore] Adding hierarchical fields to observations table...');
// Add new columns
this.db.run(`
ALTER TABLE observations ADD COLUMN title TEXT;
ALTER TABLE observations ADD COLUMN subtitle TEXT;
ALTER TABLE observations ADD COLUMN facts TEXT;
ALTER TABLE observations ADD COLUMN narrative TEXT;
ALTER TABLE observations ADD COLUMN concepts TEXT;
ALTER TABLE observations ADD COLUMN files_read TEXT;
ALTER TABLE observations ADD COLUMN files_modified TEXT;
`);
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(8, new Date().toISOString());
console.log('[SessionStore] Successfully added hierarchical fields to observations table');
}
/**
@@ -339,86 +323,82 @@ export class SessionStore {
* The text field is deprecated in favor of structured fields (title, subtitle, narrative, etc.)
*/
private makeObservationsTextNullable(): void {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(9) as SchemaVersion | undefined;
if (applied) return;
// Check if text column is already nullable
const tableInfo = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const textColumn = tableInfo.find(col => col.name === 'text');
if (!textColumn || textColumn.notnull === 0) {
// Already migrated or text column doesn't exist
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(9, new Date().toISOString());
return;
}
console.log('[SessionStore] Making observations.text nullable...');
// Begin transaction
this.db.run('BEGIN TRANSACTION');
try {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(9) as SchemaVersion | undefined;
if (applied) return;
// Create new table with text as nullable
this.db.run(`
CREATE TABLE observations_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
sdk_session_id TEXT NOT NULL,
project TEXT NOT NULL,
text TEXT,
type TEXT NOT NULL CHECK(type IN ('decision', 'bugfix', 'feature', 'refactor', 'discovery', 'change')),
title TEXT,
subtitle TEXT,
facts TEXT,
narrative TEXT,
concepts TEXT,
files_read TEXT,
files_modified TEXT,
prompt_number INTEGER,
created_at TEXT NOT NULL,
created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(sdk_session_id) REFERENCES sdk_sessions(sdk_session_id) ON DELETE CASCADE
)
`);
// Check if text column is already nullable
const tableInfo = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const textColumn = tableInfo.find(col => col.name === 'text');
// Copy data from old table (all existing columns)
this.db.run(`
INSERT INTO observations_new
SELECT id, sdk_session_id, project, text, type, title, subtitle, facts,
narrative, concepts, files_read, files_modified, prompt_number,
created_at, created_at_epoch
FROM observations
`);
if (!textColumn || textColumn.notnull === 0) {
// Already migrated or text column doesn't exist
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(9, new Date().toISOString());
return;
}
// Drop old table
this.db.run('DROP TABLE observations');
console.log('[SessionStore] Making observations.text nullable...');
// Rename new table
this.db.run('ALTER TABLE observations_new RENAME TO observations');
// Begin transaction
this.db.run('BEGIN TRANSACTION');
// Recreate indexes
this.db.run(`
CREATE INDEX idx_observations_sdk_session ON observations(sdk_session_id);
CREATE INDEX idx_observations_project ON observations(project);
CREATE INDEX idx_observations_type ON observations(type);
CREATE INDEX idx_observations_created ON observations(created_at_epoch DESC);
`);
try {
// Create new table with text as nullable
this.db.run(`
CREATE TABLE observations_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
sdk_session_id TEXT NOT NULL,
project TEXT NOT NULL,
text TEXT,
type TEXT NOT NULL CHECK(type IN ('decision', 'bugfix', 'feature', 'refactor', 'discovery', 'change')),
title TEXT,
subtitle TEXT,
facts TEXT,
narrative TEXT,
concepts TEXT,
files_read TEXT,
files_modified TEXT,
prompt_number INTEGER,
created_at TEXT NOT NULL,
created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(sdk_session_id) REFERENCES sdk_sessions(sdk_session_id) ON DELETE CASCADE
)
`);
// Commit transaction
this.db.run('COMMIT');
// Copy data from old table (all existing columns)
this.db.run(`
INSERT INTO observations_new
SELECT id, sdk_session_id, project, text, type, title, subtitle, facts,
narrative, concepts, files_read, files_modified, prompt_number,
created_at, created_at_epoch
FROM observations
`);
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(9, new Date().toISOString());
// Drop old table
this.db.run('DROP TABLE observations');
// Rename new table
this.db.run('ALTER TABLE observations_new RENAME TO observations');
// Recreate indexes
this.db.run(`
CREATE INDEX idx_observations_sdk_session ON observations(sdk_session_id);
CREATE INDEX idx_observations_project ON observations(project);
CREATE INDEX idx_observations_type ON observations(type);
CREATE INDEX idx_observations_created ON observations(created_at_epoch DESC);
`);
// Commit transaction
this.db.run('COMMIT');
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(9, new Date().toISOString());
console.log('[SessionStore] Successfully made observations.text nullable');
} catch (error: any) {
// Rollback on error
this.db.run('ROLLBACK');
throw error;
}
console.log('[SessionStore] Successfully made observations.text nullable');
} catch (error: any) {
console.error('[SessionStore] Migration error (make text nullable):', error.message);
// Rollback on error
this.db.run('ROLLBACK');
throw error;
}
}
@@ -426,86 +406,82 @@ export class SessionStore {
* Create user_prompts table with FTS5 support (migration 10)
*/
private createUserPromptsTable(): void {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(10) as SchemaVersion | undefined;
if (applied) return;
// Check if table already exists
const tableInfo = this.db.query('PRAGMA table_info(user_prompts)').all() as TableColumnInfo[];
if (tableInfo.length > 0) {
// Already migrated
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
return;
}
console.log('[SessionStore] Creating user_prompts table with FTS5 support...');
// Begin transaction
this.db.run('BEGIN TRANSACTION');
try {
// Check if migration already applied
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(10) as SchemaVersion | undefined;
if (applied) return;
// Create main table (using claude_session_id since sdk_session_id is set asynchronously by worker)
this.db.run(`
CREATE TABLE user_prompts (
id INTEGER PRIMARY KEY AUTOINCREMENT,
claude_session_id TEXT NOT NULL,
prompt_number INTEGER NOT NULL,
prompt_text TEXT NOT NULL,
created_at TEXT NOT NULL,
created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(claude_session_id) REFERENCES sdk_sessions(claude_session_id) ON DELETE CASCADE
);
// Check if table already exists
const tableInfo = this.db.query('PRAGMA table_info(user_prompts)').all() as TableColumnInfo[];
if (tableInfo.length > 0) {
// Already migrated
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
return;
}
CREATE INDEX idx_user_prompts_claude_session ON user_prompts(claude_session_id);
CREATE INDEX idx_user_prompts_created ON user_prompts(created_at_epoch DESC);
CREATE INDEX idx_user_prompts_prompt_number ON user_prompts(prompt_number);
CREATE INDEX idx_user_prompts_lookup ON user_prompts(claude_session_id, prompt_number);
`);
console.log('[SessionStore] Creating user_prompts table with FTS5 support...');
// Create FTS5 virtual table
this.db.run(`
CREATE VIRTUAL TABLE user_prompts_fts USING fts5(
prompt_text,
content='user_prompts',
content_rowid='id'
);
`);
// Begin transaction
this.db.run('BEGIN TRANSACTION');
// Create triggers to sync FTS5
this.db.run(`
CREATE TRIGGER user_prompts_ai AFTER INSERT ON user_prompts BEGIN
INSERT INTO user_prompts_fts(rowid, prompt_text)
VALUES (new.id, new.prompt_text);
END;
try {
// Create main table (using claude_session_id since sdk_session_id is set asynchronously by worker)
this.db.run(`
CREATE TABLE user_prompts (
id INTEGER PRIMARY KEY AUTOINCREMENT,
claude_session_id TEXT NOT NULL,
prompt_number INTEGER NOT NULL,
prompt_text TEXT NOT NULL,
created_at TEXT NOT NULL,
created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(claude_session_id) REFERENCES sdk_sessions(claude_session_id) ON DELETE CASCADE
);
CREATE TRIGGER user_prompts_ad AFTER DELETE ON user_prompts BEGIN
INSERT INTO user_prompts_fts(user_prompts_fts, rowid, prompt_text)
VALUES('delete', old.id, old.prompt_text);
END;
CREATE INDEX idx_user_prompts_claude_session ON user_prompts(claude_session_id);
CREATE INDEX idx_user_prompts_created ON user_prompts(created_at_epoch DESC);
CREATE INDEX idx_user_prompts_prompt_number ON user_prompts(prompt_number);
CREATE INDEX idx_user_prompts_lookup ON user_prompts(claude_session_id, prompt_number);
`);
CREATE TRIGGER user_prompts_au AFTER UPDATE ON user_prompts BEGIN
INSERT INTO user_prompts_fts(user_prompts_fts, rowid, prompt_text)
VALUES('delete', old.id, old.prompt_text);
INSERT INTO user_prompts_fts(rowid, prompt_text)
VALUES (new.id, new.prompt_text);
END;
`);
// Create FTS5 virtual table
this.db.run(`
CREATE VIRTUAL TABLE user_prompts_fts USING fts5(
prompt_text,
content='user_prompts',
content_rowid='id'
);
`);
// Commit transaction
this.db.run('COMMIT');
// Create triggers to sync FTS5
this.db.run(`
CREATE TRIGGER user_prompts_ai AFTER INSERT ON user_prompts BEGIN
INSERT INTO user_prompts_fts(rowid, prompt_text)
VALUES (new.id, new.prompt_text);
END;
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
CREATE TRIGGER user_prompts_ad AFTER DELETE ON user_prompts BEGIN
INSERT INTO user_prompts_fts(user_prompts_fts, rowid, prompt_text)
VALUES('delete', old.id, old.prompt_text);
END;
CREATE TRIGGER user_prompts_au AFTER UPDATE ON user_prompts BEGIN
INSERT INTO user_prompts_fts(user_prompts_fts, rowid, prompt_text)
VALUES('delete', old.id, old.prompt_text);
INSERT INTO user_prompts_fts(rowid, prompt_text)
VALUES (new.id, new.prompt_text);
END;
`);
// Commit transaction
this.db.run('COMMIT');
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
console.log('[SessionStore] Successfully created user_prompts table with FTS5 support');
} catch (error: any) {
// Rollback on error
this.db.run('ROLLBACK');
throw error;
}
console.log('[SessionStore] Successfully created user_prompts table with FTS5 support');
} catch (error: any) {
console.error('[SessionStore] Migration error (create user_prompts table):', error.message);
// Rollback on error
this.db.run('ROLLBACK');
throw error;
}
}
@@ -990,25 +966,17 @@ export class SessionStore {
for (const row of rows) {
// Parse files_read
if (row.files_read) {
try {
const files = JSON.parse(row.files_read);
if (Array.isArray(files)) {
files.forEach(f => filesReadSet.add(f));
}
} catch {
// Skip invalid JSON
const files = JSON.parse(row.files_read);
if (Array.isArray(files)) {
files.forEach(f => filesReadSet.add(f));
}
}
// Parse files_modified
if (row.files_modified) {
try {
const files = JSON.parse(row.files_modified);
if (Array.isArray(files)) {
files.forEach(f => filesModifiedSet.add(f));
}
} catch {
// Skip invalid JSON
const files = JSON.parse(row.files_modified);
if (Array.isArray(files)) {
files.forEach(f => filesModifiedSet.add(f));
}
}
}

Some files were not shown because too many files have changed in this diff Show More