MCPInstall

weclaw-wechat-ai-bridge

Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.

Installs
954
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/trending-skills --skill weclaw-wechat-ai-bridge
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads weclaw-wechat-ai-bridge automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

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


Configuration

{
  "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

VariablePurpose
WECLAW_DEFAULT_AGENTOverride default agent at runtime
WECLAW_API_ADDRChange local HTTP API address (default 127.0.0.1:18011)
OPENCLAW_GATEWAY_URLHTTP agent endpoint
OPENCLAW_GATEWAY_TOKENHTTP agent API token

Agent Modes

ModeProcess modelBest for
acpLong-running subprocess, JSON-RPC over stdioClaude, Codex, Kimi, Gemini — fastest, session reuse
cliNew process per message, --resume for sessionsclaude -p, codex exec
httpOpenAI-compatible /v1/chat/completionsAny REST-accessible model

Auto-detection prefers acp over cli when both binaries exist.


Chat Commands (send as WeChat messages)

CommandAction
helloSend to default agent
/codex write a sort functionRoute to named agent
/cc explain this codeUse alias (/cc → claude)
/claudeSwitch default agent to Claude (persisted)
/statusShow active agent info
/helpList available commands

Built-in Aliases

AliasAgent
/ccclaude
/cxcodex
/cscursor
/kmkimi
/gmgemini
/ocdopencode
/ocopenclaw

Proactive Messaging — CLI

# 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 a file
weclaw send --to "user_id@im.wechat" --media "https://example.com/report.pdf"

Proactive Messaging — HTTP API

The local API listens on 127.0.0.1:18011 while weclaw start is running.

# Send text
curl -X POST http://127.0.0.1:18011/api/send \
  -H "Content-Type: application/json" \
  -d '{"to": "user_id@im.wechat", "text": "Hello from WeClaw"}'

# Send image
curl -X POST http://127.0.0.1:18011/api/send \
  -H "Content-Type: application/json" \
  -d '{"to": "user_id@im.wechat", "media_url": "https://example.com/photo.png"}'

# Send text + media
curl -X POST http://127.0.0.1:18011/api/send \
  -H "Content-Type: application/json" \
  -d '{"to": "user_id@im.wechat", "text": "See this", "media_url": "https://example.com/photo.png"}'

Supported media types: png, jpg, gif, webp, mp4, mov, pdf, doc, zip.

Change listen address:

WECLAW_API_ADDR=0.0.0.0:18011 weclaw start

Go Integration Example

Call the WeClaw HTTP API from a Go service to send notifications:

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
	"os"
)

type SendRequest struct {
	To       string `json:"to"`
	Text     string `json:"text,omitempty"`
	MediaURL string `json:"media_url,omitempty"`
}

type SendResponse struct {
	OK      bool   `json:"ok"`
	Message string `json:"message,omitempty"`
}

func sendToWeChat(to, text, mediaURL string) error {
	apiAddr := os.Getenv("WECLAW_API_ADDR")
	if apiAddr == "" {
		apiAddr = "127.0.0.1:18011"
	}

	req := SendRequest{To: to, Text: text, MediaURL: mediaURL}
	body, err := json.Marshal(req)
	if err != nil {
		return fmt.Errorf("marshal: %w", err)
	}

	resp, err := http.Post(
		fmt.Sprintf("http://%s/api/send", apiAddr),
		"application/json",
		bytes.NewReader(body),
	)
	if err != nil {
		return fmt.Errorf("post: %w", err)
	}
	defer resp.Body.Close()

	var result SendResponse
	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
		return fmt.Errorf("decode: %w", err)
	}
	if !result.OK {
		return fmt.Errorf("weclaw error: %s", result.Message)
	}
	return nil
}

func main() {
	recipient := os.Getenv("WECHAT_RECIPIENT_ID") // e.g. "user_id@im.wechat"
	if err := sendToWeChat(recipient, "Build succeeded ✅", ""); err != nil {
		fmt.Fprintf(os.Stderr, "failed: %v\n", err)
		os.Exit(1)
	}
	fmt.Println("Message sent.")
}

Docker Setup

# Build image
docker build -t weclaw .

# Step 1: Interactive login (scan QR code)
docker run -it -v ~/.weclaw:/root/.weclaw weclaw login

# Step 2: Run daemon with HTTP agent
docker run -d --name weclaw \
  -v ~/.weclaw:/root/.weclaw \
  -e OPENCLAW_GATEWAY_URL=https://api.example.com \
  -e OPENCLAW_GATEWAY_TOKEN="$OPENCLAW_GATEWAY_TOKEN" \
  weclaw

# Expose the local API externally (bind carefully — no auth by default)
docker run -d --name weclaw \
  -v ~/.weclaw:/root/.weclaw \
  -e WECLAW_API_ADDR=0.0.0.0:18011 \
  -p 18011:18011 \
  -e OPENCLAW_GATEWAY_TOKEN="$OPENCLAW_GATEWAY_TOKEN" \
  weclaw

docker logs -f weclaw

ACP/CLI agents require the agent binary inside the container. Mount the binary or build a custom image. HTTP agents work out of the box.


System Service (Auto-start)

macOS (launchd):

cp service/com.fastclaw.weclaw.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.fastclaw.weclaw.plist

Linux (systemd):

sudo cp service/weclaw.service /etc/systemd/system/
sudo systemctl enable --now weclaw
journalctl -u weclaw -f

Development

make dev                        # Hot reload
go build -o weclaw .            # Build binary
./weclaw start -f               # Run in foreground

Releasing:

git tag v0.1.0
git push origin v0.1.0
# GitHub Actions builds darwin/linux × amd64/arm64 and uploads release artifacts

Common Patterns

Pattern: Per-user agent routing

Send /claude or /codex as a WeChat message to switch the default agent. The choice persists in ~/.weclaw/config.json across restarts.

Pattern: CI/CD build notifications

After a build, call weclaw send or POST to the HTTP API to push results to a WeChat contact or group.

Pattern: Media from agent

If an agent reply contains ![alt](https://...), WeClaw auto-downloads, AES-128-ECB encrypts, uploads to WeChat CDN, and delivers as a native image message — no extra config needed.

Pattern: Disable permission prompts for headless use

{
  "claude": { "type": "cli", "command": "/usr/local/bin/claude",
               "args": ["--dangerously-skip-permissions"] },
  "codex":  { "type": "cli", "command": "/usr/local/bin/codex",
               "args": ["--skip-git-repo-check"] }
}

ACP agents handle permissions automatically and do not need these flags.


Troubleshooting

SymptomFix
QR code not appearingRun weclaw login explicitly; ensure terminal supports UTF-8
Agent not auto-detectedCheck binary is on $PATH; run weclaw status
connection refused on HTTP APIConfirm weclaw start is running; check WECLAW_API_ADDR
Agent permission prompts block responsesAdd --dangerously-skip-permissions (Claude) or --skip-git-repo-check (Codex) to args; or use ACP mode
Docker — no agent binaryMount binary: -v /usr/local/bin/claude:/usr/local/bin/claude; or use HTTP mode
Markdown not renderingWeClaw strips markdown automatically for WeChat plain-text display; this is expected
Logstail -f ~/.weclaw/weclaw.log or docker logs -f weclaw

FAQ

What does the weclaw-wechat-ai-bridge skill do?

Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.

How do I install weclaw-wechat-ai-bridge?

Run npx skills add https://github.com/reason-machines/trending-skills --skill weclaw-wechat-ai-bridge in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/weclaw-wechat-ai-bridge/ (personal) or .claude/skills/weclaw-wechat-ai-bridge/ (project).

Which AI agents can use weclaw-wechat-ai-bridge?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is weclaw-wechat-ai-bridge safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains weclaw-wechat-ai-bridge?

It is published by reason-machines in reason-machines/trending-skills. It has 954 recorded installs.

More from reason-machines/trending-skills

View all →

openclaw-control-center

reason-machines/trending-skills

Local-first, security-first control center for OpenClaw agents — visibility dashboard with readonly defaults, token attribution, collaboration tracing, and safe write operations.

Data & Databases4.4K installs

inkos-multi-agent-novel-writing

reason-machines/trending-skills

Multi-agent CLI system for autonomous novel writing, auditing, and revision with human review gates

Docs & Writing2.8K installs

claude-hud-statusline

reason-machines/trending-skills

A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.

understand-anything-knowledge-graph

reason-machines/trending-skills

Turn any codebase into an interactive knowledge graph using Claude Code skills — explore, search, and ask questions about any project visually.

agency-agents-ai-specialists

reason-machines/trending-skills

A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.

AI & Agents2.1K installs

agent-browser-automation

reason-machines/trending-skills

Headless browser automation CLI for AI agents using native Rust binary with Chrome DevTools Protocol

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs