steel-browser
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
Runssource: GitHubhomepageTypeScriptApache-2.0commit 2b41124d8e29
TypeScript, Apache-2.0 licensed. The project labels itself: ai, ai agents, ai tools, browser automation and llm.
steel-browser 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.
Steel Browser API builds, runs, passes all 79 unit tests, serves the health endpoint, creates live Chrome sessions, scrapes web pages into clean HTML, and captures screenshots as JPEGs on a headless desktop with Chrome 156 and Node 22.
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 100 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 v18.19.1 too old (package engines require >=22)2 minutes
- Chrome binary not found in container1 minute
- Chrome crash due to missing sandbox support (no root for suid sandbox, user namespace restrictions)
- Install time
- 4 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm run test -w api exited 0, 11 test files, 79 passed, 2 skipped; curl http://localhost:3000/v1/health returned 200 with 'ok'; POST /v1/sessions created a live browser session; POST /v1/scrape extracted real HTML from example.com; POST /v1/screenshot returned a 42833-byte valid JPEG; session release succeeded
- Model tokens used
- 65,670
- Exact commit tested
- 2b41124d8e29
- 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.
✓ src/services/cdp/instrumentation/browser-interaction-events.test.ts (5 tests) 8ms
Test Files 11 passed (11)
Tests 79 passed | 2 skipped (81)
Start at 05:29:22
Duration 5.94s (transform 547ms, setup 0ms, collect 3.22s, tests 9.77s, environment 3ms, prepar…
exec
/bin/sh -lc 'pkill -f "node api/build/index.js" 2>/dev/null || true; echo "done"' in /work/repo
exited 143 in 0ms:
Let me compile the final report. Here's everything I did and found:
tokens used
65,670
Let me compile the final report. Here's everything I did and found: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.
- Installed in 4 minutes, faster than the median of the 36 comparable projects Argusic has measured.
- 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 37 ai projects Argusic has installed and timed, steel-browser was the 16th fastest to reach a running state, and 30 of 37 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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/steel-browser)Questions
- Does steel-browser run?
- Yes. steel-browser 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 steel-browser?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2b41124d8e29. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test steel-browser?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does steel-browser 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 steel-browser need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing steel-browser?
- 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 steel-browser compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, steel-browser was the 16th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for steel-browser?
- 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.