An AI-powered, multi-platform customer service robot designed to automate responses and manage interactions across e-commerce and social media channels. It targets businesses seeking to streamline customer support, offering intelligent replies powered by various large language models (LLMs) and a centralized management interface. The system aims to improve efficiency and customer engagement through automated communication and targeted content delivery.

How It Works

The system employs a hybrid integration strategy: MITM proxy injection and JavaScript runtime injection for platforms like Taobao/Qianniu, and browser automation via headless browsers for others like Pinduoduo. A message processing pipeline dispatches incoming messages through sensitive word filtering and keyword handling before generating responses using pluggable LLMs (e.g., GPT, Qwen, Llama). Communication is secured via SSL-encrypted WebSockets, and a modern PySide6 GUI provides a user-friendly interface for management and real-time message synchronization.

Quick Start & Requirements

• Primary install/run command:

  git clone https://github.com/kunkeji/chatGPT_auto_msg_multiPlat.git
  pip install -r requirements.txt
  python app.py
  

• Non-default prerequisites: Python 3.8+, Windows 10/11. PySide6 is required for the GUI.
• Setup: Initial setup involves cloning the repository, installing dependencies, and running the main script. A test account (admin/123456) is provided, but user registration is recommended.

Highlighted Details

• Extensive Platform Support: Designed for integration with numerous platforms including WeChat, Pinduoduo, Qianniu, JD, Enterprise WeChat, Weibo, Xiaohongshu, and Zhihu.
• LLM Agnostic: Capable of integrating with a wide array of LLMs such as GPT, GLM, Qwen, Gemma, Llama, Phi, and Yi.
• Advanced Features: Includes real-time message synchronization across clients, built-in sensitive word filtering, automated product information pushing, and comprehensive data/message statistics.
• Technical Implementation: Leverages MITM proxy techniques, JavaScript injection, and headless browser control for platform-specific message interception and automation.

Maintenance & Community

The project explicitly states it cannot guarantee regular maintenance due to the developer's work commitments. Support and inquiries can be directed via GitHub Issues, email (kunkeji@qq.com), or through the official website (kunkeji.com).

Licensing & Compatibility

The project is released under the MIT License, which permits commercial use, modification, and distribution. No specific compatibility restrictions for closed-source linking or commercial applications are noted.

Limitations & Caveats

Only the Qianniu platform is fully implemented; other platforms are provided with core methods requiring further user development. The project's maintenance status may impact long-term support and bug fixes. The system enforces single-account login, limiting concurrent usage by multiple individuals on the same account.