aurora-develop/aurora

What it solves

Aurora converts the internal backend capabilities of the ChatGPT Web interface into a standard, OpenAI-compatible API. This allows developers to use ChatGPT's web-based features—including chat, image generation, and voice services—within applications that expect an OpenAI API format, without needing official API keys for every feature.

How it works

The project acts as a proxy layer that translates OpenAI-style API requests into the specific requests required by the ChatGPT Web backend. It manages a pool of authentication tokens (access, refresh, session, and free UUID tokens) and handles the complexities of maintaining sessions. To avoid detection and ensure stability, it assigns each account its own TLS client, proxy IP, browser fingerprint, and WebSocket connection.

Who it’s for

It is designed for developers who want to integrate ChatGPT Web's full suite of capabilities (like file Q&A, image editing, and TTS) into their own software using a familiar API structure.

Highlights

• Broad Feature Support: Supports chat completions, image generation/editing, speech-to-text, text-to-speech, and file uploads for Q&A.
• Tool Calling Simulation: Simulates function calling by using a text-based protocol (<tool_call>) and automatically parsing it into the standard OpenAI format.
• Advanced Account Management: Features a robust system for token deduplication, automatic token renewal every 10 minutes, and support for external access tokens.
• Infrastructure Control: Includes built-in support for proxy pools, TLS configuration, and custom browser fingerprints to maintain account isolation.