According to AlphaMoat, as of 2026-09, OpenClaw WeCom Channel has 4,210 downloads and 5 stars — ranked #2,371 of 5,078 AI skills overall, and #462 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 134 | 3.9K | 5 | - |
| SkillHub ↗ | 702 | 4.2K | 5 | — |
Platforms count differently and update at different times.
As a native OpenClaw channel it replies automatically to text sent by WeCom users and can also push messages through the API on its own. Messages are encrypted and decrypted with AES-256-CBC per the WXBizMsgCrypt standard, access_token is cached and refreshed ahead of expiry, and access control policies are included.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 4.2K | — | 5 |
| 2026-08 | 3.8K | +2.4% | 5 |
| 2026-07 | 3.7K | — | 5 |
| 2026-05 | 3.3K | — | 5 |
| 2026-03 | 2.2K | — | 5 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
---
name: openclaw-wecom-channel
description: "企业微信 (WeCom) Channel 插件 — 让 OpenClaw AI Agent 通过企业微信收发消息。支持消息加解密、Token 自动管理、访问控制策略。"
homepage: https://github.com/darrryZ/openclaw-wecom-channel
metadata: { "openclaw": { "emoji": "💬", "requires": { "bins": ["node"], "network": true } } }
---
# OpenClaw 企业微信 Channel 插件
企业微信 (WeCom/WxWork) 消息通道插件,让 OpenClaw AI Agent 通过企业微信收发消息,与 Telegram、Discord、Signal 等并列为原生 Channel。
## 功能
- **📩 接收消息** — 企业微信用户发送文本,Agent 自动回复
- **📤 主动推送** — Agent 通过企业微信 API 主动发送消息
- **🔐 消息加解密** — 完整实现企业微信 AES-256-CBC 消息加解密(WXBizMsgCrypt 标准)
- **🔑 Token 管理** — access_token 自动缓存 + 提前 5 分钟刷新
- **🛡️ 访问控制** — open / pairing / allowlist 三种策略
- **⚡ 智能回复** — 5 秒内被动回复,超时自动降级为主动推送
## 前置条件
- OpenClaw 已安装并运行
- 企业微信管理员权限(创建自建应用)
- 公网可达的回调 URL(推荐 Cloudflare Tunnel)
## 快速开始
### 1. 安装插件
```bash
# 克隆到 OpenClaw extensions 目录
git clone https://github.com/darrryZ/openclaw-wecom-channel.git ~/.openclaw/extensions/wecom
```
### 2. 配置 OpenClaw
编辑 `~/.openclaw/openclaw.json`:
```json
{
"channels": {
"wecom": {
"enabled": true,
"corpId": "你的企业ID",
"agentId": 1000003,
"secret": "应用Secret",
"token": "回调Token",
"encodingAESKey": "回调EncodingAESKey",
"port": 18800,
"dmPolicy": "open"
}
},
"plugins": {
"entries": {
"wecom": { "enabled": true }
}
}
}
```
### 3. 配置公网回调(Cloudflare Tunnel)
```bash
cloudflared tunnel create wecom-tunnel
cloudflared tunnel route dns wecom-tunnel wecom.yourdomain.com
cloudflared tunnel run --edge-ip-version 4 --url http://localhost:18800 wecom-tunnel
```
企业微信后台回调 URL 设置为:`https://wecom.yourdomain.com/wecom/callback`
### 4. 重启 Gateway
```bash
openclaw gateway restart
```
## 详细文档
完整的配置指南、企业微信后台设置步骤、故障排查请参考 README.md。
## 链接
- **GitHub**: https://github.com/darrryZ/openclaw-wecom-channel
- **OpenClaw**: https://github.com/openclaw/openclaw
- **企业微信开发文档**: https://developer.work.weixin.qq.com/document/
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Stores agent memory and cross-skill state as a typed, constraint-checked knowledge graph.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.