Weclaw Wechat Ai Bridge

This bridges WeChat to any AI agent through three modes: ACP for long-running JSON-RPC processes (fastest, best for Claude or Codex), CLI for spawning per-message, and HTTP for OpenAI-compatible endpoints. You scan a QR code, it auto-detects your agents, then you can route messages with `/codex write a sort function` or switch defaults mid-chat. The proactive send API is the real hook: curl a local endpoint or call from Go to push notifications, images, or files into WeChat from CI pipelines or backend services. Config is plain JSON, runs as a daemon or Docker container, and the built-in aliases save you from typing full agent names. It's glue code done right.

skills.sh installs: 911
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill weclaw-wechat-ai-bridge --agent claude-code

Installs into .claude/skills of the current project.

Files

WeClaw — WeChat AI Agent Bridge

Skill by ara.so — Daily 2026 Skills collection.

WeClaw connects WeChat to AI agents (Claude, Codex, Gemini, Kimi, OpenClaw, etc.) via a Go-based bridge. It handles QR-code login, message routing, media conversion, and agent lifecycle. Supports three agent modes: ACP (JSON-RPC subprocess, fastest), CLI (new process per message), and HTTP (OpenAI-compatible REST).

Installation

# One-line installer
curl -sSL https://raw.githubusercontent.com/fastclaw-ai/weclaw/main/install.sh | sh

# Via Go toolchain
go install github.com/fastclaw-ai/weclaw@latest

# Via Docker
docker run -it -v ~/.weclaw:/root/.weclaw ghcr.io/fastclaw-ai/weclaw start

First-Run Flow

weclaw start        # Shows QR code → scan with WeChat → auto-detects agents → saves config
weclaw login        # Add/re-authenticate a WeChat account
weclaw status       # Show running state and active agent
weclaw stop         # Stop the background daemon
weclaw start -f     # Foreground mode (debug/verbose)

Logs: ~/.weclaw/weclaw.log
Config: ~/.weclaw/config.json