Amm1rr/WebAI-to-API

Webchat to API

What it solves

WebAI-to-API allows users to access browser-based AI services (like Google Gemini) as if they were standard API endpoints. It solves the problem of using AI web interfaces that lack official, accessible APIs by wrapping them in an OpenAI-compatible API layer.

How it works

The project uses a combination of browser-native automation (via Playwright) and WebAPI-based provider integrations. It routes requests from an OpenAI-compatible /v1/chat/completions endpoint to the underlying browser-based AI service. It handles authentication via browser login workflows or manual cookie injection, ensuring the session remains active for the AI service.

Who it’s for

Developers who want to integrate browser-based AI models into their own applications or tools without needing a official API key, or those who want to integrate multiple AI providers (including Atlas Cloud) through a single, unified API interface.

Highlights

  • OpenAI-Compatible API: Provides a standard /v1/chat/completions endpoint for easy integration with existing AI tools.
  • Multi-Provider Support: Supports Gemini (via WebAPI or Playwright) and Atlas Cloud.
  • Browser Automation: Includes a built-in login helper (verify_login.py) to manage Google sessions.
  • Integrated Dashboard: Features a visual UI for monitoring runtime status, managing authentication, and testing requests.
  • Streaming Support: Supports Server-Sent Events (SSE) for streaming responses.
  • File Support: Allows file attachments via the Gemini WebAPI backend.

Related

  • Project
    zhiyu1998/Gemi2Api-Server

    Gemi2Api‑Server is a self‑hosted FastAPI proxy that forwards OpenAI‑style requests to Google Gemini’s unofficial web API. By supplying your own Gemini login cookies, you get `/v1/models` and `/v1/chat/completions` endpoints, an admin UI, optional model overrides, and an image‑proxy feature—all runnable via Docker or directly with Python.

  • Project
    foxhui/WebAI2API

    A tool that converts web-based AI services into OpenAI-compatible APIs by simulating human browser interactions to bypass bot detection.

  • Project
    Nativu5/Gemini-FastAPI

    An OpenAI-compatible API wrapper for web-based Gemini models that allows free access using session cookies instead of an API key.

  • Project
    Sophomoresty/gemini-web2api

    gemini‑web2api is a Python server that proxies Google Gemini’s private web API and presents it as an OpenAI‑compatible endpoint (`/v1/chat/completions`, `/v1/models`, etc.). It supports optional API‑key auth, streaming, function calling, image input, multiple Gemini model aliases, adjustable reasoning depth, and can run directly or inside Docker.

  • Project
    yeahhe365/AMC-WebUI

    A local-first, all-in-one model console for Google Gemini and OpenAI-compatible APIs, featuring real-time audio/video interaction, a WASM-based Python sandbox, and chain-of-thought visualization.