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。
Runs with mockssource: GitHubhomepageJavaScriptMITcommit a2ba9b531332
JavaScript, MIT licensed. The project labels itself: anthropic compatible, api gateway, claude, claude code, cline, codeium, cursor and deepseek.
WindsurfAPI runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The Node.js HTTP server starts on port 3003 and all 4317 tests pass; the Language Server binary is unavailable in this container (requires Windsurf IDE binary), so the proxy functions as a Devin Connect gateway rather than a full Cascade/LanguageServer bridge, which is the expected state when DEVIN_CONNECT is not configured.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 56 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- test/devin-connect.test.js: deadlineMs timer with .unref() did not fire (event loop resolved) on Node 22, cascading 88 cancelled tests5 minutes
- test/restart.test.js: Docker detection via /.dockerenv caused 2 test failures in container2 minutes
- Node.js v18.19.1 in container — project requires >=201 minute
- test/default-on-switch-registry.test.js: WINDSURFAPI_RESTART_SUPERVISED not in default-on LEDGER1 minute
- Install time
- 10 minutes
- Cold machine to finish
- 36 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- Model tokens used
- 320,436
- Exact commit tested
- a2ba9b531332
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec /bin/sh -lc 'export PATH=/tmp/node-v22.13.1-linux-x64/bin:$PATH && cd /work/repo && node --import .… succeeded in 30778ms: # tests 4317 # pass 4317 # fail 0 # cancelled 0 # duration_ms 30893.648466 All 4317 tests pass with 0 failures. tokens used 320,436 All 4317 tests pass with 0 failures.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 10 minutes.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Did not run | 20.00 | 0.04 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.27 |
Topics (from GitHub)
anthropic-compatibleapi-gatewayclaudeclaude-codeclinecodeiumcursordeepseekdevindevin-apigeminigemini-compatiblegptllmopenaiopenai-compatiblereverse-proxyself-hostedswe-1-5windsurf
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/windsurfapi)Questions
- Does WindsurfAPI run?
- WindsurfAPI runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test WindsurfAPI?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a2ba9b531332. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test WindsurfAPI?
- The run that produced this verdict cost $0.27: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does WindsurfAPI take to install?
- 10 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does WindsurfAPI need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing WindsurfAPI?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for WindsurfAPI?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.