WebAI2API
WebAI2API: 基于 Camoufox 的网页 AI 转 API 工具,支持 LMArena/Gemini等,多窗口并发与账号隔离。 | Web AI to OpenAI API via Camoufox. Supports LMArena/Gemini and more, multi-window concurrency & account isolation.
Runssource: GitHubhomepageJavaScriptMITcommit beac6c979d81
JavaScript, MIT licensed. The project labels itself: ai tools, browser automation, generative ai, image generation, openai api, text generation, text to image and web scraping.
WebAI2API runs. An Argusic agent installed it in 4 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The server starts, launches a Camoufox browser instance in headful mode on Xvfb, serves the OpenAI-compatible API on port 3000 returning 200 for /v1/models and WebUI, the SQLite history database initializes, all 19 adapters load, and the browser fingerprint is generated and saved.
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 96 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.
- Node.js 18 too old for camoufox-js and @inquirer dependencies1 minute
- pnpm not available in PATH
- better-sqlite3 and sharp native builds blocked by pnpm ignoredBuiltDependencies
- Install time
- 4 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- curl -s http://localhost:3000/v1/models -H 'Authorization: Bearer sk-change-me-to-your-secure-key' returned 200 with 200+ model IDs; curl -s http://localhost:3000/ returned 200 with WebUI HTML
- Model tokens used
- 175,733
- Exact commit tested
- beac6c979d81
- 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.
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Here's the summary of everything I did and observed. **Environment:** Ubuntu 24.04 x64, Node.js 18.19.1 (upgraded to 20.20.2), Xvfb virtual display avai… **Errors encountered and fixes:** - **Node.js 18 too old** — The project requires Node.js 20+ (camoufox-js engine requirement, @inqui… - **pnpm not installed** — Installed via `npm install -g pnpm`. - **Native builds blocked by pnpm** — better-sqlite3 and sharp build scripts were in `ignoredBuiltD… - **No other errors** — `pnpm install` succeeded including postinstall patches; `npm run init` down… **Verification results:** The server launched successfully with a live Camoufox browser instance on the Xvfb virtual display,… - `GET /v1/models` with auth → **200**, returned 200+ models (lmarena/*, gemini-*, flux-*, etc.) - `GET /` (WebUI) with auth → **200**, returned HTML - `POST /v1/chat/completions` with invalid model → proper JSON error response (`INVALID_MODEL`)
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- 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
- Took 4 minutes to install, slower than the median of the 26 comparable projects Argusic has measured.
Of the 27 ai-tools projects Argusic has installed and timed, WebAI2API was the 16th fastest to reach a running state, and 19 of 27 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 4 minutes after the clone.
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 | Runs | 100.00 | 0.05 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.04 |
Topics (from GitHub)
ai-toolsbrowser-automationgenerative-aiimage-generationopenai-apitext-generationtext-to-imageweb-scraping
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/webai2api)Questions
- Does WebAI2API run?
- Yes. WebAI2API runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test WebAI2API?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit beac6c979d81. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test WebAI2API?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does WebAI2API take to install?
- 4 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 WebAI2API need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing WebAI2API?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does WebAI2API compare with the alternatives?
- Of the 27 ai-tools projects Argusic has installed and timed, WebAI2API was the 16th fastest to reach a running state, and 19 of 27 reached one at all.
- Where is the evidence for WebAI2API?
- 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.