This project provides a WeChat robot powered by large language models like ChatGPT, designed for stable and secure operation. It targets WeChat users who want to integrate AI chat and image generation capabilities into their messaging without risking account restrictions.

How It Works

The bot operates via a Windows hook mechanism, avoiding the account risks associated with QR code scanning logins used by other WeChat bots. It supports multiple LLM providers (OpenAI, Anthropic, Google) through litellm and offers features like multi-turn conversation memory, image generation (DALL-E), and a plugin system for extensibility.

Quick Start & Requirements

• Install: pip install -r requirements.txt
• Prerequisites: Windows OS, Python 3.8-3.10 (3.10 recommended). Requires a specific WeChat version (3.2.1.121) and a DLL injector tool (wechat-dll-injectorV1.0.3.exe with 3.2.1.121-LTS.dll).
• Setup: Clone repo, install dependencies, copy config.template.json to config.json and fill in API keys and settings. Inject the DLL into the WeChat process.
• Run: python app.py
• Docs: English, 中文文档

Highlighted Details

• Implemented using Windows hook for account security.
• Supports multiple LLMs via litellm (GPT-3.5/4, Claude, PaLM).
• Includes image generation capabilities (DALL-E).
• Features a plugin system for custom extensions.

Maintenance & Community

The project acknowledges contributions from wechat-windows-versions and wechat-bot. Further community links are not explicitly provided in the README.

Licensing & Compatibility

The README does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The bot is strictly Windows-dependent due to its hook-based implementation. It requires a specific, older version of WeChat and manual DLL injection, which may be complex or unstable across different Windows updates.