wangrongding/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.

What it solves

This project provides a unified interface to turn various instant messaging (IM) platforms into AI-powered agents. It allows users to route messages from WeChat, Lark, Telegram, and WhatsApp to a wide variety of LLM providers, enabling automated replies and deep analysis of chat histories.

How it works

The system acts as a bridge between IM platforms and AI services. It uses Wechaty for WeChat integration and official APIs for Telegram and WhatsApp. It can be configured to use a specific AI agent (like Pi) or a general LLM service (such as ChatGPT, DeepSeek, Claude, or Ollama) to generate responses.

Additionally, it integrates with wx-cli to access local WeChat data, allowing the AI to perform statistics and deep analysis on specific friends or group chats based on cached local data.

Who it’s for

  • Individual users who want an AI assistant integrated into their daily chat apps.
  • Developers looking to deploy LLM-powered bots on multiple IM platforms without writing separate integration code for each.
  • Users who want to analyze their social interaction data from WeChat.

Highlights

  • Multi-Platform Support: Integrated with WeChat, Lark, Telegram, and WhatsApp.
  • Extensive Model Support: Compatible with ChatGPT, DeepSeek, Claude, Pi, Ollama (local), and several other providers.
  • Local Data Analysis: Ability to run AI-driven deep analysis and statistics on local WeChat chat histories and Moments cache.
  • Trigger Control: Fine-grained control over bot responses via allowlists for friends and groups, and specific trigger prefixes to avoid spamming.

Related

  • Project
    yincongcyincong/MuseBot

    MuseBot is an open‑source Go bot that connects Telegram, Discord, Slack, Lark, DingTalk, Enterprise WeChat, QQ and WeChat to a wide range of LLM APIs (OpenAI, DeepSeek, Gemini, OpenRouter, etc.). It streams AI replies, supports image/voice input, function calls, RAG, admin UI, metrics and cron jobs, and can be run locally or via Docker.

  • Project
    langbot-app/LangBot

    LangBot is an open‑source, production‑grade platform that lets you attach LLMs to dozens of instant‑messaging services (Discord, Slack, Telegram, WeChat, etc.). It provides a web dashboard, built‑in RAG/tool‑calling, a plugin marketplace, and a Model Context Protocol (MCP) server so other AI agents can manage bots programmatically. Quick start options include a one‑line `uvx langbot` launch, Docker Compose, or hosted LangBot Cloud. The project targets use cases like AI‑driven customer support, internal workflow automation, and cross‑platform community bots.

  • Project
    countbot-ai/CountBot

    An open-source AI Agent framework and hub that connects LLMs, multiple IM channels, and external tools for long-term local deployment and task execution.

  • Project
    AstrBotDevs/AstrBot

    An all-in-one Agent chatbot platform that integrates LLMs and AI agents into mainstream instant messaging apps like Telegram, Slack, and Discord.

  • Project
    photon-hq/spectrum-ts

    A multi-channel agent framework that enables AI agents to communicate over real conversation surfaces like iMessage, SMS, and Slack instead of web chat.