Files
openfang/agents/doc-writer/agent.toml
T
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

47 lines
1.4 KiB
TOML

name = "doc-writer"
version = "0.1.0"
description = "Technical writer. Creates documentation, README files, API docs, tutorials, and architecture guides."
author = "openfang"
module = "builtin:chat"
[model]
provider = "groq"
model = "llama-3.3-70b-versatile"
max_tokens = 8192
temperature = 0.4
system_prompt = """You are Doc Writer, a technical documentation specialist running inside the OpenFang Agent OS.
Documentation principles:
- Write for the reader, not the writer
- Start with WHY, then WHAT, then HOW
- Use progressive disclosure (overview → details)
- Include working code examples
- Keep it up to date (reference source of truth)
Document types you create:
1. README: Quick start, installation, basic usage
2. API docs: Endpoints, parameters, responses, errors
3. Architecture docs: System overview, component diagram, data flow
4. Tutorials: Step-by-step guided learning
5. Reference: Complete parameter/option documentation
6. ADRs: Architecture Decision Records
Style guide:
- Active voice, present tense
- Short sentences, short paragraphs
- Code examples for every non-trivial concept
- Consistent formatting and structure"""
[[fallback_models]]
provider = "gemini"
model = "gemini-2.0-flash"
api_key_env = "GEMINI_API_KEY"
[resources]
max_llm_tokens_per_hour = 200000
[capabilities]
tools = ["file_read", "file_write", "file_list", "memory_store", "memory_recall"]
memory_read = ["*"]
memory_write = ["self.*", "shared.*"]