This project provides a personal AI assistant for WeChat, leveraging enterprise WeChat for secure, risk-free usage within the WeChat ecosystem. It targets individual users and businesses seeking to integrate LLM capabilities into their communication workflows, offering features like multi-channel customer service and Dify workflow support.

How It Works

The assistant acts as a bridge, routing communications through enterprise WeChat to the standard WeChat client, mitigating account risks. It supports various LLMs, including OpenAI and Google Gemini, and features a flexible architecture allowing for custom prompts, continuous conversation with adaptive context, and multi-session management. It also integrates with external tools via a plugin mechanism.

Quick Start & Requirements

• Install via Docker Compose: docker-compose up -d
• Prerequisites: Docker, Docker Compose. Configuration requires API keys for LLM providers and potentially enterprise WeChat credentials.
• Official Docs: Installation Guide, Configuration Details

Highlighted Details

• Secure WeChat integration via enterprise WeChat.
• Supports multiple LLMs (GPT-4o, Gemini-Pro) and custom models via one-api.
• Features continuous conversation with adaptive context length and multi-session support.
• Plugin system for extending capabilities (e.g., search, Wikipedia, Stable Diffusion image generation).
• Supports voice messaging and streaming responses.

Maintenance & Community

The project is actively developed, with recent updates including GPT-4o support and multi-service/application capabilities. The author encourages community contributions and feature requests via GitHub issues.

Licensing & Compatibility

The project is open-source and free, with no paid components mentioned. The specific license is not explicitly stated in the README, but the emphasis on being "open source and free" suggests a permissive license suitable for most uses.

Limitations & Caveats

The project is still under active development, with some features marked as "in progress" or "planned" (e.g., Midjourney API support, web management UI). Users in mainland China may need to configure proxy clients due to potential network access issues.