Commit Graph
3 Commits
Author SHA1 Message Date
Tsukimaru Oshawott 40bdf4316b feat(agents): add LangChain code review agent with A2A protocol
Add a Python-based code review agent powered by LangChain that
integrates with OpenFang via the A2A (Agent-to-Agent) protocol.

- agent.py: Core review logic with structured Chinese SYSTEM_PROMPT
  covering 6 dimensions (correctness, security, performance,
  maintainability, testing, style) and 4 severity levels
- server.py: FastAPI server exposing A2A-compatible endpoints
  (/.well-known/agent.json and /a2a JSON-RPC)
- workflow.json: OpenFang workflow definition for the review pipeline
- config.example.toml: Example A2A config for ~/.openfang/config.toml
- Supports OpenAI, DeepSeek, and Ollama backends

Made-with: Cursor
2026-03-16 14:33:41 +08:00
jaberjaber23 a4a83b1699 bugfixes batch 2026-03-03 16:54:30 +03:00
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