Claude Skill
fastclaw-ai/weclaw
WeClaw is an open-source Go SDK that connects WeChat to any AI agent via ClawBot. Enable automated conversations, task execution, and seamless integration with intelligent agents on WeChat.
Overview
Repository
Install this Skill
docker run -it -v ~/.weclaw:/root/.weclaw ghcr.io/fastclaw-ai/weclaw startRegistry
docker run -it -v ~/.weclaw:/root/.weclaw ghcr.io/fastclaw-ai/weclaw startdocker run -it -v ~/.weclaw:/root/.weclaw weclaw logindocker run -d --name weclaw \
Summary
WeClaw is an open-source Go SDK that connects WeChat to any AI agent via ClawBot, enabling seamless integration of WeChat with intelligent agents for automated conversations and task execution.
通过微信ClawBot连接任意智能体。
Key features
- Seamless WeChat-to-agent integration via ClawBot
- Lightweight Go SDK for fast deployment
- Supports any AI agent or backend service
- Open-source with active community maintenance
- Designed for real-time message handling
Use cases
- Build WeChat-based AI customer service bots
- Connect WeChat to custom AI agents for automation
- Create personal assistant bots on WeChat
- Integrate WeChat with enterprise AI workflows
- Prototype and test AI agent interactions via WeChat
README excerpt
# WeClaw [中文文档](README_CN.md) WeChat AI Agent Bridge — connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.). > This project is inspired by [@tencent-weixin/openclaw-weixin](https://npmx.dev/package/@tencent-weixin/openclaw-weixin). For personal learning only, not for commercial use. | | | | |:---:|:---:|:---:| | <img src="previews/preview1.png" width="280" /> | <img src="previews/preview2.png" width="280" /> | <img src="previews/preview3.png" width="280" /> | ## Quick Start ```bash # One-line install curl -sSL https://raw.githubusercontent.com/fastclaw-ai/weclaw/main/install.sh | sh # Start (first run will prompt QR code login) weclaw start ``` That's it. On first start, WeClaw will: 1. Show a QR code — scan with WeChat to login 2. Auto-detect installed AI agents (Claude, Codex, Gemini, etc.) 3. Save config to `~/.weclaw/config.json` 4. Start receiving and replying to WeChat messages Use `weclaw login` to add additional WeChat accounts. ### Other install methods ```bash # Via Go go install github.com/fastclaw-ai/weclaw@latest # Via Docker docker run -it -v ~/.weclaw:/root/.weclaw ghcr.io/fastclaw-ai/weclaw start ``` ## How It Works <p align="center"> <img src="previews/architecture.png" width="600" /> </p> **Agent modes:** | Mode | How it works | Examples | |------|-------------|----------| | ACP | Long-running subprocess, JSON-RPC over stdio. Fastest — reuses process and sessions. | Claude, Codex, Kimi, Gemini, Cursor, OpenCode, OpenClaw | | CLI | Spawns a new process per message. Supports session resume via `--resume`. | Claude (`claude -p`), Codex (`codex exec`) | | HTTP | OpenAI-compatible chat completions API. | OpenClaw (HTTP fallback) | Auto-detection picks ACP over CLI when both are available. ## Chat Commands Send these as WeCh