mirror of
https://github.com/thedotmack/claude-mem
synced 2026-04-25 17:15:04 +02:00
c648d5d8d2
* feat: add knowledge agent types, store, builder, and renderer Phase 1 of Knowledge Agents feature. Introduces corpus compilation pipeline that filters observations from the database into portable corpus files stored at ~/.claude-mem/corpora/. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add corpus CRUD HTTP endpoints and wire into worker service Phase 2 of Knowledge Agents. Adds CorpusRoutes with 5 endpoints (build, list, get, delete, rebuild) and registers them during worker background initialization alongside SearchRoutes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add KnowledgeAgent with V1 SDK prime/query/reprime Phase 3 of Knowledge Agents. Uses Agent SDK V1 query() with resume and disallowedTools for Q&A-only knowledge sessions. Auto-reprimes on session expiry. Adds prime, query, and reprime HTTP endpoints to CorpusRoutes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add MCP tools and skill for knowledge agents Phase 4 of Knowledge Agents. Adds build_corpus, list_corpora, prime_corpus, and query_corpus MCP tools delegating to worker HTTP endpoints. Includes /knowledge-agent skill with workflow docs. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: handle SDK process exit in KnowledgeAgent, add e2e test The Agent SDK may throw after yielding all messages when the Claude process exits with a non-zero code. Now tolerates this if session_id/answer were already captured. Adds comprehensive e2e test script (31 assertions) orchestrated via tmux-cli. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: use settings model ID instead of hardcoded model in KnowledgeAgent Reads CLAUDE_MEM_MODEL from user settings via getModelId(), matching the existing SDKAgent pattern. No more hardcoded model assumptions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: improve knowledge agents developer experience Add public documentation page, rebuild/reprime MCP tools, and actionable error messages. DX review scored knowledge agents 4/10 — core engineering works (31/31 e2e) but the feature was invisible. This addresses discoverability (docs, cross-links), API completeness (missing MCP tools), and error quality (fix/example fields in error responses). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: add quick start guide to knowledge agents page Covers the three main use cases upfront: creating an agent, asking a single question, and starting a fresh conversation with reprime. Includes keeping-it-current section for rebuild + reprime workflow. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address code review issues — path traversal, session safety, prompt injection - Block path traversal in CorpusStore with alphanumeric name validation and resolved path check - Harden system prompt against instruction injection from untrusted corpus content - Validate question field as non-empty string in query endpoint - Only persist session_id after successful prime (not null on failure) - Persist refreshed session_id after query execution - Only auto-reprime on session resume errors, not all query failures - Add fenced code block language tags to SKILL.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address remaining code review issues — e2e robustness, MCP validation, docs - Harden e2e curl wrappers with connect-timeout, fallback to HTTP 000 on transport failure - Use curl_post wrapper consistently for all long-running POST calls - Add runtime name validation to all corpus MCP tool handlers - Fix docs: soften hallucination guarantee to probabilistic claim - Fix architecture diagram: add missing rebuild_corpus and reprime_corpus tools Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: enforce string[] type in safeParseJsonArray for corpus data integrity Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: add blank line before fenced code blocks in SKILL.md maintenance section Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
123 lines
6.4 KiB
Plaintext
123 lines
6.4 KiB
Plaintext
---
|
|
title: "Introduction"
|
|
description: "Persistent memory compression system for Claude Code"
|
|
---
|
|
|
|
# Claude-Mem
|
|
|
|
**Persistent memory compression system for Claude Code**
|
|
|
|
Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions. This enables Claude to maintain continuity of knowledge about projects even after sessions end or reconnect.
|
|
|
|
## Quick Start
|
|
|
|
Install with a single command:
|
|
|
|
```bash
|
|
npx claude-mem install
|
|
```
|
|
|
|
Or install from the plugin marketplace inside Claude Code:
|
|
|
|
```bash
|
|
/plugin marketplace add thedotmack/claude-mem
|
|
/plugin install claude-mem
|
|
```
|
|
|
|
Restart Claude Code. Context from previous sessions will automatically appear in new sessions.
|
|
|
|
## Key Features
|
|
|
|
- 🧠 **Persistent Memory** - Context survives across sessions
|
|
- 📁 **Folder Context Files** - Auto-generated `CLAUDE.md` in project folders with activity timelines
|
|
- 🌐 **Multilingual Modes** - Supports 28 languages (Spanish, Chinese, French, Japanese, etc.)
|
|
- 🎭 **Mode System** - Switch between workflows (Code, Email Investigation, Chill)
|
|
- 🔍 **MCP Search Tools** - Query your project history with natural language
|
|
- 🧠 **Knowledge Agents** - Build queryable "brains" from your observation history
|
|
- 🌐 **Web Viewer UI** - Real-time memory stream visualization at http://localhost:37777
|
|
- 🔒 **Privacy Control** - Use `<private>` tags to exclude sensitive content from storage
|
|
- ⚙️ **Context Configuration** - Fine-grained control over what context gets injected
|
|
- 🤖 **Automatic Operation** - No manual intervention required
|
|
- 📊 **FTS5 Search** - Fast full-text search across observations
|
|
- 🔗 **Citations** - Reference past observations with IDs
|
|
|
|
## How It Works
|
|
|
|
```
|
|
┌─────────────────────────────────────────────────────────────┐
|
|
│ Session Start → Inject context from last 10 sessions │
|
|
└─────────────────────────────────────────────────────────────┘
|
|
↓
|
|
┌─────────────────────────────────────────────────────────────┐
|
|
│ 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. **4 Lifecycle Hooks** - SessionStart, UserPromptSubmit, PostToolUse, Stop
|
|
2. **Smart Install** - Cached dependency checker (pre-hook script)
|
|
3. **Worker Service** - HTTP API on port 37777 managed by Bun
|
|
4. **SQLite Database** - Stores sessions, observations, summaries with FTS5 search
|
|
5. **MCP Search Tools** - Query historical context with natural language
|
|
6. **Web Viewer UI** - Real-time visualization with SSE and infinite scroll
|
|
|
|
See [Architecture Overview](architecture/overview) for details.
|
|
|
|
## System Requirements
|
|
|
|
- **Node.js**: 18.0.0 or higher
|
|
- **Claude Code**: Latest version with plugin support
|
|
- **Bun**: JavaScript runtime and process manager (auto-installed if missing)
|
|
- **SQLite 3**: For persistent storage (bundled)
|
|
|
|
## What's New
|
|
|
|
**v9.0.0 - Live Context:**
|
|
- **Folder Context Files**: Auto-generated `CLAUDE.md` in project folders with activity timelines
|
|
- **Worktree Support**: Unified context from parent repos and git worktrees
|
|
- **Configurable Observation Limits**: Control how many observations appear in context
|
|
- **Windows Fixes**: Resolved IPC detection and hook execution issues
|
|
- **Settings Auto-Creation**: `settings.json` now auto-creates on first run
|
|
- **MCP Tools Naming**: Updated from "mem-search skill" to "MCP tools" terminology
|
|
|
|
**v7.1.0 - Bun Migration:**
|
|
- Replaced PM2 with native Bun process management
|
|
- Switched from better-sqlite3 to bun:sqlite for faster database access
|
|
- Simplified cross-platform support
|
|
|
|
**v7.0.0 - Context Configuration:**
|
|
- 11 settings for fine-grained control over context injection
|
|
- Dual-tag privacy system (`<private>` tags)
|
|
|
|
## Next Steps
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Installation" icon="download" href="/installation">
|
|
Quick start & advanced installation
|
|
</Card>
|
|
<Card title="Getting Started" icon="rocket" href="/usage/getting-started">
|
|
Learn how Claude-Mem works automatically
|
|
</Card>
|
|
<Card title="Folder Context" icon="folder-open" href="/usage/folder-context">
|
|
Auto-generated folder CLAUDE.md files
|
|
</Card>
|
|
<Card title="Search Tools" icon="magnifying-glass" href="/usage/search-tools">
|
|
Query your project history
|
|
</Card>
|
|
<Card title="Knowledge Agents" icon="brain" href="/usage/knowledge-agents">
|
|
Build queryable corpora from your history
|
|
</Card>
|
|
</CardGroup>
|