bb-browser
Your browser is the API. CLI + MCP server for AI agents to control Chrome with your login state.
Runssource: GitHubTypeScriptMITcommit 7975dc74b3f6
TypeScript, MIT licensed.
bb-browser runs. An Argusic agent installed it in 12 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
bb-browser pnpm install and build succeed; CLI version 0.14.2 prints help; daemon auto-downloads and launches Chrome 149 headed on Xvfb; HTTP API on port 19826 responds 200 to /status, tab_list, eval, snap, open commands; 129 of 143 tests pass, 13 skipped (need Chrome), 1 flaky timing failure.
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.
- unzip not installed in container - Chrome auto-download fails to extract2 minutes
- Chrome 149 crashpad_handler segfault - Chrome fails to start (Permission denied on spawn)2 minutes
- Node.js 18 lacks import.meta.dirname (added in Node 20) - CLI daemon-startup tests crash1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- tsx --test ran 143 tests (129 pass, 13 skip, 1 flaky fail); node dist/daemon.js started Chrome 149, HTTP /status returned 200 with Chrome connected; CLI tab list/eval/snap/open commands returned correct JSON via real Chrome CDP
- Model tokens used
- 136,028
- Exact commit tested
- 7975dc74b3f6
- 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.
],
'test_depth': 'tier1_real',
'notes': 'Flaky test: daemon discovers CDP via managed port file (timing-sensitive, 8s timeout)…
'verified_how': 'tsx --test ran 143 tests (129 pass, 13 skip, 1 flaky fail); node dist/daemon.j…
'final_state': 'bb-browser pnpm install and build succeed; CLI version 0.14.2 prints help; daem…
}
print(json.dumps(result))
\"" in /work/repo
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 12, "errors": [{"msg": "No…
tokens used
136,028Replay 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.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 18 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 19 TypeScript projects Argusic has installed and timed, bb-browser was the 15th fastest to reach a running state, and 16 of 19 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.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/bb-browser)Questions
- Does bb-browser run?
- Yes. bb-browser runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test bb-browser?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7975dc74b3f6. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test bb-browser?
- The run that produced this verdict cost $0.25: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does bb-browser take to install?
- 12 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 bb-browser need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing bb-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 bb-browser compare with the alternatives?
- Of the 19 TypeScript projects Argusic has installed and timed, bb-browser was the 15th fastest to reach a running state, and 16 of 19 reached one at all.
- Where is the evidence for bb-browser?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.