This project is an AI API gateway and proxy that translates and normalizes requests between different AI model formats to ensure compatibility across client applications. It functions as a middleware service that can transform local command-line binaries into web services, allowing them to be triggered via HTTP requests.
The system is distinguished by its ability to route multimodal text and image inputs and extract internal reasoning chains from model outputs to separate the chain of thought from the final answer. It includes an authentication manager that automatically cycles through multiple OAuth tokens to distribute request load and bypass rate limits.
The capability surface covers credential health tracking, real-time log streaming via WebSockets, and a web administration console for bulk credential management. Data persistence is handled through a pluggable backend supporting either local SQLite or distributed MongoDB instances.
The application can be deployed using Docker container images or through automation for mobile terminal environments via Termux.
