Weclaw Wechat Ai Bridge
Bridge WeChat messaging to Claude, Codex, Gemini, Kimi, or OpenAI-compatible agents via the WeClaw Go daemon.
Overview
WeClaw WeChat AI Bridge is an agent skill for the Build phase that connects WeChat to AI agents via a Go bridge with QR login, routing, and ACP, CLI, or HTTP agent modes.
Install
npx skills add https://github.com/aradotso/trending-skills --skill weclaw-wechat-ai-bridgeWhat is this skill?
- Go-based WeClaw bridge: QR WeChat login, daemon lifecycle (start/stop/status/login)
- Three agent modes: ACP JSON-RPC subprocess, CLI per message, HTTP OpenAI-compatible REST
- Install via curl script, go install, or Docker with ~/.weclaw config volume
- Supports Claude, Codex, Gemini, Kimi, OpenClaw, and OpenAI-compatible APIs
- Foreground debug via weclaw start -f; config and logs under ~/.weclaw
- 3 agent modes: ACP, CLI, HTTP
Adoption & trust: 841 installs on skills.sh; 31 GitHub stars; 0/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need customers or teammates on WeChat to talk to your AI agent but lack a maintained bridge for login, routing, and media.
Who is it for?
Solo builders shipping China-facing or WeChat-native workflows who already use Claude, Codex, or OpenAI-compatible APIs.
Skip if: Teams with no WeChat requirement, or products that cannot run a local daemon or container with network access to WeChat.
When should I use this skill?
connect wechat to claude, weclaw setup, send messages from wechat to ai, or bridge wechat with openai compatible api.
What do I get? / Deliverables
WeClaw runs as a configured daemon, WeChat is linked via QR login, and messages flow to your selected agent backend using the documented mode.
- Running weclaw daemon with saved ~/.weclaw config
- Authenticated WeChat session via weclaw login
- Documented agent mode binding (ACP, CLI, or HTTP)
Recommended Skills
Journey fit
WeClaw is shelved in Build integrations because it wires an external chat channel to your AI backend during product construction. QR login, message routing, media conversion, and agent modes are channel-integration work, not SEO or production monitoring.
How it compares
Channel bridge skill and Go CLI, not an in-app MCP server or hosted SaaS inbox.
Common Questions / FAQ
Who is weclaw-wechat-ai-bridge for?
Indie developers and small teams integrating WeChat with Claude, Codex, Gemini, Kimi, or custom OpenAI-compatible agents on their own infrastructure.
When should I use WeClaw?
During Build integrations when wiring chat to agents, or Validate prototype when demoing WeChat-driven AI support before full product launch.
Is weclaw-wechat-ai-bridge safe to install?
It runs shell installs, network, and a long-lived daemon with WeChat credentials in ~/.weclaw; review the Security Audits panel on this page and harden secrets and host access.
SKILL.md
READMESKILL.md - Weclaw Wechat Ai Bridge
# WeClaw — WeChat AI Agent Bridge > Skill by [ara.so](https://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 ```bash # 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 ```bash 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` --- ## Configuration ```json { "default_agent": "claude", "agents": { "claude": { "type": "acp", "command": "/usr/local/bin/claude-agent-acp", "model": "sonnet" }, "codex": { "type": "acp", "command": "/usr/local/bin/codex-acp" }, "claude-cli": { "type": "cli", "command": "/usr/local/bin/claude", "args": ["--dangerously-skip-permissions"] }, "codex-cli": { "type": "cli", "command": "/usr/local/bin/codex", "args": ["--skip-git-repo-check"] }, "openclaw": { "type": "http", "endpoint": "https://api.example.com/v1/chat/completions", "api_key": "$OPENCLAW_GATEWAY_TOKEN", "model": "openclaw:main" } } } ``` ### Environment Variables | Variable | Purpose | |----------|---------| | `WECLAW_DEFAULT_AGENT` | Override default agent at runtime | | `WECLAW_API_ADDR` | Change local HTTP API address (default `127.0.0.1:18011`) | | `OPENCLAW_GATEWAY_URL` | HTTP agent endpoint | | `OPENCLAW_GATEWAY_TOKEN` | HTTP agent API token | --- ## Agent Modes | Mode | Process model | Best for | |------|--------------|----------| | `acp` | Long-running subprocess, JSON-RPC over stdio | Claude, Codex, Kimi, Gemini — fastest, session reuse | | `cli` | New process per message, `--resume` for sessions | `claude -p`, `codex exec` | | `http` | OpenAI-compatible `/v1/chat/completions` | Any REST-accessible model | Auto-detection prefers `acp` over `cli` when both binaries exist. --- ## Chat Commands (send as WeChat messages) | Command | Action | |---------|--------| | `hello` | Send to default agent | | `/codex write a sort function` | Route to named agent | | `/cc explain this code` | Use alias (`/cc` → claude) | | `/claude` | Switch default agent to Claude (persisted) | | `/status` | Show active agent info | | `/help` | List available commands | ### Built-in Aliases | Alias | Agent | |-------|-------| | `/cc` | claude | | `/cx` | codex | | `/cs` | cursor | | `/km` | kimi | | `/gm` | gemini | | `/ocd` | opencode | | `/oc` | openclaw | --- ## Proactive Messaging — CLI ```bash # Send plain text weclaw send --to "user_id@im.wechat" --text "Hello from WeClaw" # Send an image weclaw send --to "user_id@im.wechat" --media "https://example.com/photo.png" # Send text + media together weclaw send --to "user_id@im.wechat" \ --text "Check this out" \ --media "https://example.com/photo.png" # Send