Mag1cFall/AIStudio2API

将AI Studio Playground和Build反代成API | AI Studio to OpenAI, Anthropic & Gemini Compatible API

What it solves

This project acts as a high-performance proxy service that bridges Google AI Studio's web-based protocols with standard API formats. It allows developers to use Gemini models and other Google AI capabilities in applications that expect OpenAI, Anthropic, or native Gemini API compatibility.

How it works

It functions by managing the authentication and communication lifecycle between your local environment and Google AI Studio. It uses either a browser-based backend (Camoufox) or a pure Go implementation to handle the complex WAA (Web Authentication) requirements. The service provides a management dashboard to handle multiple Google accounts, load-balance requests across them, and route traffic to the appropriate AI models, including support for streaming, function calling, and media generation.

Who it’s for

This tool is designed for developers and power users who want to integrate Google's latest AI models into their existing workflows or agent-based applications (like Claude Code or Codex) without being restricted to Google's official API limitations or specific SDKs.

Highlights

  • Multi-Protocol Support: Translates Google AI Studio traffic into OpenAI, Anthropic, and native Gemini API formats.
  • Account Management: Supports high-concurrency across multiple Google accounts, including automatic load balancing and quota management.
  • Rich Feature Set: Enables advanced capabilities like TTS (Text-to-Speech), Veo video generation, image generation, and tool/function calling.
  • Agent Compatibility: Designed to work natively with popular AI agent frameworks and CLI tools.
  • Self-Hosted Control: Provides a web-based dashboard for monitoring usage, managing account authentication, and configuring service settings.

Related

  • Project
    avaturn-live/avtr-1

    AVTR‑1 is a TensorRT‑accelerated, flow‑matching autoregressive model that turns a portrait image and dual‑audio streams into a 25 fps lip‑synced talking avatar. The repo includes weights, build scripts for GPU‑specific inference engines, an interactive web demo, and a CLI for offline generation. Real‑time performance is shown for several NVIDIA GPUs. Licensing is split: a community license for the model (commercial use under $10 M revenue), and non‑commercial PolyForm licenses for the renderer and streamer, with additional research‑only restrictions from InsightFace.

  • Project
    kkokosa/dotLLM

    A high-performance LLM inference engine written natively in C#/.NET, providing native CPU/GPU support for transformer models without relying on Python or llama.cpp.

  • Project
    NVIDIA/flashdreams

    FlashDreams is an Apache‑2.0 library for ultra‑fast inference of autoregressive video and world‑model networks, targeting real‑time applications like gaming, autonomous‑vehicle simulation, and robotics. It provides ready‑made runners for several NVIDIA models, supports multi‑GPU setups on H100‑class hardware, and offers extensible guides for adding new methods.

  • Project
    modal-labs/modal-client

    Official SDKs for the Modal platform, enabling developers to deploy and high-performance serverless applications and interact with platform resources.