MCPInstall

openclaw-wechat-integration

Connect OpenClaw AI agents to personal WeChat accounts for messaging, group chats, and automation

Installs
180
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-wechat-integration
  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 openclaw-wechat-integration 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.

openclaw-wechat-integration

Skill by ara.so — Hermes Skills collection.

This skill provides expertise in using the openclaw-wechat plugin to connect OpenClaw AI agents to personal WeChat accounts, enabling automated messaging, group chat interactions, and multi-account management.

What It Does

openclaw-wechat is a WeChat channel plugin for OpenClaw that enables:

  • Direct messages and group chat support
  • Text and image message handling
  • QR code login authentication
  • Multi-account WeChat bot management
  • Webhook-based message receiving
  • Cloud server deployment compatibility

Installation

Install the Plugin

openclaw plugins install @canghe/openclaw-wechat

Update Existing Installation

openclaw plugins update wechat

Core Configuration

Required Configuration Steps

  1. Set API Key (obtain from project community):
openclaw config set channels.wechat.apiKey "wc_live_xxxxxxxxxxxxxxxx"
  1. Set Proxy URL (required for WeChat protocol handling):
openclaw config set channels.wechat.proxyUrl "http://your-proxy-server:3000"
  1. Set Webhook Host (required for cloud deployment):
openclaw config set channels.wechat.webhookHost "your-server-ip"
  1. Enable the Channel:
openclaw config set channels.wechat.enabled true

Configuration File Structure

The configuration is stored in ~/.openclaw/openclaw.json:

{
  "channels": {
    "wechat": {
      "enabled": true,
      "apiKey": "wc_live_xxxxxxxxxxxxxxxx",
      "proxyUrl": "http://your-proxy:3000",
      "webhookHost": "1.2.3.4",
      "webhookPort": 18790,
      "webhookPath": "/webhook/wechat",
      "deviceType": "ipad"
    }
  }
}

Configuration Options Reference

OptionRequiredDefaultDescription
enabledYesfalseEnable/disable the WeChat channel
apiKeyYes-API key from service provider
proxyUrlYes-Proxy service URL for WeChat protocol
webhookHostCloud only-Public IP or domain for webhooks
webhookPortNo18790Port for webhook listener
webhookPathNo/webhook/wechatWebhook endpoint path
deviceTypeNo"ipad"Device type: "ipad" or "mac"

First-Time Login

QR Code Authentication

Start the gateway to initiate login:

openclaw gateway start

The terminal will display a QR code. Scan it with your WeChat mobile app to authenticate.

Verify Connection

openclaw gateway status

Check logs for connection status:

openclaw gateway logs

Multi-Account Configuration

Managing Multiple WeChat Accounts

Configure multiple accounts with distinct API keys:

{
  "channels": {
    "wechat": {
      "accounts": {
        "work": {
          "apiKey": "wc_live_work_xxx",
          "webhookHost": "1.2.3.4",
          "webhookPort": 18790,
          "deviceType": "ipad"
        },
        "personal": {
          "apiKey": "wc_live_personal_xxx",
          "webhookHost": "1.2.3.4",
          "webhookPort": 18791,
          "deviceType": "mac"
        }
      }
    }
  }
}

Important: Each account must use a unique webhookPort to avoid conflicts.

Message Handling Patterns

Receiving Messages

The plugin automatically receives messages via webhooks. Ensure your webhook endpoint is accessible:

// OpenClaw automatically handles incoming messages
// Configure message handlers in your OpenClaw skills

// Example skill handler (conceptual)
export async function onMessage(context: MessageContext) {
  const { message, channel } = context;
  
  if (channel === 'wechat') {
    console.log('WeChat message:', message.text);
    console.log('From:', message.sender);
    console.log('Chat type:', message.isGroup ? 'group' : 'private');
  }
}

Sending Messages

When building OpenClaw skills that send WeChat messages:

// Example: Sending a text message
await context.send({
  channel: 'wechat',
  to: 'wxid_xxxxxxxxxx',
  text: 'Hello from OpenClaw!'
});

// Example: Sending to a group
await context.send({
  channel: 'wechat',
  to: 'group_id',
  text: 'Message to group',
  isGroup: true
});

Image Message Handling

// Receiving images
export async function onMessage(context: MessageContext) {
  if (context.message.type === 'image') {
    const imageUrl = context.message.imageUrl;
    // Process image
  }
}

// Sending images
await context.send({
  channel: 'wechat',
  to: 'wxid_xxxxxxxxxx',
  type: 'image',
  imageUrl: 'https://example.com/image.png'
});

Cloud Server Deployment

Network Requirements

  1. Open Webhook Port: Ensure firewall allows incoming connections:
# Example: UFW on Ubuntu
sudo ufw allow 18790/tcp
  1. Verify Public Accessibility:
# Test from external machine
curl http://YOUR_SERVER_IP:18790/webhook/wechat

Systemd Service Setup

Create /etc/systemd/system/openclaw-gateway.service:

[Unit]
Description=OpenClaw Gateway Service
After=network.target

[Service]
Type=simple
User=YOUR_USER
WorkingDirectory=/home/YOUR_USER
ExecStart=/usr/local/bin/openclaw gateway start
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target

Enable and start:

sudo systemctl enable openclaw-gateway
sudo systemctl start openclaw-gateway
sudo systemctl status openclaw-gateway

Docker Deployment

FROM node:18-alpine

WORKDIR /app

# Install OpenClaw
RUN npm install -g openclaw

# Install plugin
RUN openclaw plugins install @canghe/openclaw-wechat

# Expose webhook port
EXPOSE 18790

# Configure via environment
ENV OPENCLAW_CONFIG_PATH=/app/config/openclaw.json

CMD ["openclaw", "gateway", "start"]

Troubleshooting

Bot Cannot Receive Messages

Symptoms: Gateway starts but no messages arrive.

Solutions:

  1. Verify webhook host configuration:
openclaw config get channels.wechat.webhookHost
# Should return your public IP
  1. Check port accessibility:
# From external network
telnet YOUR_SERVER_IP 18790
  1. Verify gateway is running:
openclaw gateway status
  1. Check webhook logs:
openclaw gateway logs --tail 100
  1. Test webhook endpoint:
curl -X POST http://YOUR_SERVER_IP:18790/webhook/wechat \
  -H "Content-Type: application/json" \
  -d '{"test": true}'

QR Code Not Displaying

Symptoms: Gateway starts but no QR code appears.

Solutions:

  1. Check proxy URL connectivity:
curl http://your-proxy-server:3000/health
  1. Verify API key is valid:
openclaw config get channels.wechat.apiKey
  1. Clear session cache:
rm -rf ~/.openclaw/sessions/wechat
openclaw gateway restart

Login Expired

Symptoms: Bot stops responding, shows login errors.

Solutions:

  1. Restart gateway to get new QR code:
openclaw gateway restart
  1. Scan QR code again with WeChat

  2. Check WeChat account status (ensure not blocked)

Multiple Accounts Port Conflict

Symptoms: Second account fails to start.

Solution: Ensure each account has a unique webhookPort:

{
  "channels": {
    "wechat": {
      "accounts": {
        "account1": {
          "webhookPort": 18790
        },
        "account2": {
          "webhookPort": 18791
        }
      }
    }
  }
}

Proxy Connection Issues

Symptoms: Cannot connect to proxy server.

Solutions:

  1. Verify proxy is running:
curl http://your-proxy-server:3000
  1. Check network connectivity:
ping your-proxy-server
  1. Update proxy URL:
openclaw config set channels.wechat.proxyUrl "http://new-proxy:3000"

Common Commands

# View current configuration
openclaw config list

# Start gateway in foreground
openclaw gateway start

# Start gateway in background
openclaw gateway start --daemon

# Stop gateway
openclaw gateway stop

# Restart gateway
openclaw gateway restart

# View logs
openclaw gateway logs

# View real-time logs
openclaw gateway logs --follow

# Check gateway status
openclaw gateway status

# Uninstall plugin
openclaw plugins uninstall wechat

Best Practices

  1. Security: Store API keys in environment variables:
export WECHAT_API_KEY="wc_live_xxxxxxxxxxxxxxxx"
openclaw config set channels.wechat.apiKey "$WECHAT_API_KEY"
  1. Monitoring: Set up log rotation for production:
openclaw config set logging.rotation.enabled true
openclaw config set logging.rotation.maxSize "100M"
  1. Backup: Regularly backup session data:
tar -czf openclaw-backup-$(date +%Y%m%d).tar.gz ~/.openclaw/sessions
  1. Firewall: Only expose webhook port, not entire server:
sudo ufw default deny incoming
sudo ufw allow 18790/tcp
sudo ufw enable
  1. Health Checks: Implement automated restarts on failure when using systemd (see service configuration above).

FAQ

What does the openclaw-wechat-integration skill do?

Connect OpenClaw AI agents to personal WeChat accounts for messaging, group chats, and automation

How do I install openclaw-wechat-integration?

Run npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-wechat-integration 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/openclaw-wechat-integration/ (personal) or .claude/skills/openclaw-wechat-integration/ (project).

Which AI agents can use openclaw-wechat-integration?

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 openclaw-wechat-integration 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 openclaw-wechat-integration?

It is published by reason-machines in reason-machines/hermes-skills. It has 180 recorded installs.

More from reason-machines/hermes-skills

View all →

hermes-agent-self-evolution

reason-machines/hermes-skills

Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code

AI & Agents323 installs

hermes-webui-agent

reason-machines/hermes-skills

Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.

267 installs

awesome-hermes-agent-ecosystem

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

232 installs

hermes-agent-framework

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

219 installs

hermes-workspace-ai-agent-ui

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

Frontend & Design213 installs

hermes-desktop-companion

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

206 installs

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