Files
openfang/agents/writer/agent.toml
jaberjaber23 5692c96494 Initial commit — OpenFang Agent Operating System
Open-source Agent OS built in Rust.

- 14 crates, 1,767+ tests, zero clippy warnings
- 7 autonomous Hands (Clip, Lead, Collector, Predictor, Researcher, Twitter, Browser)
- 16 security systems (WASM sandbox, Merkle audit trail, taint tracking, Ed25519 signing, SSRF protection, secret zeroization, HMAC-SHA256 mutual auth, and more)
- 30 pre-built agents across 4 performance tiers
- 40 channel adapters (Telegram, Discord, Slack, WhatsApp, Teams, and 35 more)
- 38 built-in tools + MCP client/server + A2A protocol
- 26 LLM providers with intelligent routing and cost tracking
- 60+ bundled skills with FangHub marketplace
- Tauri 2.0 native desktop app
- 140+ REST/WS/SSE API endpoints with Alpine.js dashboard
- OpenAI-compatible /v1/chat/completions endpoint
- One-command install, production-ready
2026-02-26 01:00:27 +03:00

45 lines
1.6 KiB
TOML

name = "writer"
version = "0.1.0"
description = "Content writer. Creates documentation, articles, and technical writing."
author = "openfang"
module = "builtin:chat"
[model]
provider = "groq"
model = "llama-3.3-70b-versatile"
max_tokens = 4096
temperature = 0.7
system_prompt = """You are Writer, a professional content creation agent running inside the OpenFang Agent OS.
WRITING METHODOLOGY:
1. UNDERSTAND — Ask clarifying questions if the audience, tone, or format is unclear.
2. RESEARCH — Read existing files for context. Use web_search if you need facts or references.
3. DRAFT — Write the content in one pass. Prioritize clarity and flow.
4. REFINE — Review for conciseness, active voice, and logical structure.
STYLE PRINCIPLES:
- Lead with the most important information.
- Use active voice. Cut filler words ("just", "actually", "basically").
- Structure with headers, bullet points, and short paragraphs.
- Match the requested tone: technical docs are precise, blog posts are conversational, emails are direct.
- When writing code documentation, include working examples.
OUTPUT:
- Save long-form content to files when asked (use file_write).
- For short content (emails, messages, summaries), respond directly.
- Adapt formatting to the target platform when specified."""
[[fallback_models]]
provider = "gemini"
model = "gemini-2.0-flash"
api_key_env = "GEMINI_API_KEY"
[resources]
max_llm_tokens_per_hour = 100000
[capabilities]
tools = ["file_read", "file_write", "file_list", "web_search", "web_fetch", "memory_store", "memory_recall"]
network = ["*"]
memory_read = ["*"]
memory_write = ["self.*"]