wechat-bot
🤖 Multi-platform IM AI Agent for Telegram, WhatsApp, Lark, and WeChat. Connects ChatGPT / Claude / Kimi / DeepSeek / Ollama / Pi for auto-replies, community an
What is wechat-bot?
🤖 Multi-platform IM AI Agent for Telegram, WhatsApp, Lark, and WeChat. Connects ChatGPT / Claude / Kimi / DeepSeek / Ollama / Pi for auto-replies, community analysis, contact management, and inactive-friend detection.
Overview of wechat-bot
What it is
wechat-bot is an open source multi-platform IM AI agent project written in Node.js. It uses the Wechaty library to connect WeChat (via QR code login), Lark, Telegram, and WhatsApp, and can route received messages to AI services such as ChatGPT, Claude, Kimi, DeepSeek, Ollama, and Pi for automatic replies. It also includes a command-line interface (CLI) called wb that can access local WeChat data (chats, contacts, group members, Moments cache) and perform statistical or AI analysis on group chats or specific friends. The project is licensed under MIT and hosted at https://github.com/wangrongding/wechat-bot.
Key features
- Supports WeChat QR-code IM login (via Wechaty), Lark IM events, Telegram Bot API polling, and WhatsApp Cloud API webhooks.
- Agents: Pi, ChatGPT, DeepSeek, Doubao, Kimi, Xunfei, tongyi, claude, ollama, 302.AI, dify, and gpt4free.
- CLI (
wb) to read local WeChat sessions, history, contacts, group members, Moments feed, and search Moments. - Group and friend analysis command (
wb analyze) provides local statistics and AI deep analysis. - Multi-model replies can be selected by the
--serveflag. - Allowlist-based triggers for private and group chats to control which contacts or groups can invoke the agent.
Use cases
The project is suitable for individuals who want to connect an AI agent to multiple IM platforms for automated replies, community analysis, contact management, and detection of inactive friends. It can be used to analyze group chat activity, summarize conversations, or automatically respond to whitelisted friends and groups. The integrated WeChat data access also allows offline analysis of local chat history and Moments.
Getting started
sh npm i cp .env.example .env npm link Configure the required environment variables in .env (BOT_NAME, ALIAS_WHITELIST, ROOM_WHITELIST, and the credentials for the chosen AI service). Then start the agent for a specific IM, for example: sh wb agent --im wechat --agent pi See the repository README for detailed instructions on each supported AI service and IM platform.
License and pricing
The project is released under the MIT license. No pricing information is stated in the repository.
Based on the project's public README and repository metadata.
