dwgx/WindsurfAPI

Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。

What it solves

This project solves the problem of using Windsurf/Devin's cloud AI models (like Claude, GPT, Gemini, etc.) with standard client tools that expect OpenAI, Anthropic, or Gemini APIs. Instead of being locked into Windsurf's proprietary interface, users can point any existing SDK or agent (like Claude Code, Cline, Cursor) at this gateway and get access to 100+ models.

How it works

WindsurfAPI is a self-hosted Node.js HTTP service (port 3003) that listens for requests in OpenAI, Anthropic, and Gemini formats. It translates these requests into the internal gRPC protocol that Windsurf's Language Server binary understands, then forwards them to the Windsurf cloud. It maintains an account pool (you bring your own Windsurf/Devin accounts) for load balancing, failover, and rate-limit isolation. Before returning the response, it strips the upstream Windsurf identity so the model claims to be the underlying model (e.g., "Claude Opus 4.6"). The gateway also supports stateful Responses API with server-side session storage.

Who it's for

Developers and teams who already have Windsurf/Devin subscriptions and want to plug those models into their existing tooling—like using Claude Code, Cursor, or any OpenAI/Anthropic/Gemini SDK—without writing custom adapters. It's also for those who want a self-hosted, account-managed proxy with failover and isolation.

Highlights

  • Zero npm runtime dependencies, pure Node.js.
  • Exposes four API surfaces: OpenAI Chat/Completions, OpenAI Responses, Anthropic Messages, and Gemini.
  • Account pool with rotation, rate-limit isolation, and automatic failover.
  • Identifies as the underlying model (removes Windsurf branding).
  • Supports streaming (SSE) and non-streaming for multiple protocols.
  • Includes a dashboard for account management and health monitoring.
  • Docker deployment and one-click update scripts.

Related

  • Project
    Amm1rr/WebAI-to-API

    WebAI‑to‑API is a self‑hosted bridge that runs Google Gemini (via web API or a Playwright‑driven browser) and exposes it through OpenAI‑compatible endpoints, with a local dashboard and Docker support.

  • Project
    zhiyu1998/Gemi2Api-Server

    Gemi2Api‑Server is a FastAPI‑based bridge that lets you call Google Gemini via an OpenAI‑compatible REST API. It authenticates with Gemini using your browser cookies, forwards chat‑completion requests, optionally proxies generated images, and provides a simple admin UI. Deployable locally, via Docker, or on Render/HuggingFace, it’s useful for developers who want Gemini access without a formal public API.

  • 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
    iBUHub/AIStudioToAPI

    AIStudioToAPI is a self‑hosted bridge that turns Google AI Studio’s web UI into OpenAI, Gemini, and Anthropic‑compatible HTTP APIs. It automates a Camoufox browser to log in, supports multiple Google accounts, tool calls, streaming, and offers a web console. Install via npm or Docker, configure with environment variables, and call the familiar `/v1/*` or `/v1beta/*` endpoints to access Gemini’s multimodal models.

  • Project
    zexadev/gemini-web2api-go

    A self-hosted proxy that converts the free Google Gemini web interface into an OpenAI-compatible API, allowing users to access Gemini models without official API keys.