This project provides a unified proxy system for multi-channel AI APIs, enabling seamless conversion between OpenAI, Anthropic Claude, and Google Gemini formats. It's designed for developers and users who need to integrate with or switch between different AI providers, offering features like key management, load balancing, and comprehensive capability detection.

How It Works

The system acts as a transparent proxy, intercepting client requests and performing automatic format recognition based on request paths and parameters. It then routes the request to the appropriate AI service, converting the request and response formats as needed. Key advantages include its ability to handle advanced features like streaming responses, function calls, and visual understanding across different API specifications, abstracting away the underlying complexities of each provider.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Run the web server: python web_server.py
• Access the web interface at http://localhost:3000
• Requires Python 3.x. Configuration is managed via a .env file.

Highlighted Details

• Supports bidirectional conversion between OpenAI, Anthropic, and Gemini API formats.
• Handles advanced features including streaming, function calls, visual understanding, and structured output.
• Provides a unified API for listing models across different providers.
• Includes comprehensive capability detection for various AI features.

Maintenance & Community

The project is licensed under the MIT License.

Licensing & Compatibility

MIT License, generally permissive for commercial use and integration with closed-source applications.

Limitations & Caveats

The README does not detail specific limitations or known issues. Users may need to consult the source code or community channels for potential caveats.