BrowserKitten
A Chrome side-panel agent for your signed-in browser. Read pages, take action, create files, and run local follow-ups. Bring your own models.
Runssource: GitHubJavaScriptMITcommit 6ec7d9cc8411
JavaScript, MIT licensed. The project labels itself: ai agent, browser agent, browser automation, byok, chrome extension, javascript, llm and local first.
BrowserKitten runs. An Argusic agent installed it in 11.4 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
813 regression tests pass with Node.js 22.11.0. Pack script generates correct extension/ with 273 files, passing all CI shape assertions (no dev .md leak, TSV fix present, manifest/src/fflate/THIRD_PARTY_NOTICES present). Verify script confirms sourceParity=true.
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. 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 18.19.1 (default) lacks global crypto.randomUUID, Promise.withResolvers, and MockTimers object-format config required by this project. Tests fail with ESM import errors, crypto is not defined, and MockTimers API incompatibility.5 minutes
- Install time
- 11 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- /home/runner/node22/bin/node --test tests/*.test.mjs exited 0, 813 passed, 0 failed. python3 scripts/pack_extension.py succeeded (273 files). python3 scripts/verify_extension.py extension --source . returned status passed, sourceParity true.
- Model tokens used
- 199,364
- Exact commit tested
- 6ec7d9cc8411
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
3. **MockTimers API incompatibility**: Node 18's `t.mock.timers.enable()` only accepts an Array of … **Fix applied**: Downloaded Node.js 22.11.0 to `/home/runner/node22/bin/node`. All 813 tests pass w… Nothing else needed changing — no `package.json`, no npm installs, no code modifications. tokens used 199,364 ## Summary **The project works.** The only issue was the default Node.js 18.19.1 being too old — the project r… 1. **Missing global `crypto`**: `crypto.randomUUID()`, `crypto.subtle.digest()`, and `crypto.getRan… 2. **No `Promise.withResolvers()`**: Used in `tests/local-task-runtime.test.mjs`. 3. **MockTimers API incompatibility**: Node 18's `t.mock.timers.enable()` only accepts an Array of … **Fix applied**: Downloaded Node.js 22.11.0 to `/home/runner/node22/bin/node`. All 813 tests pass w… Nothing else needed changing — no `package.json`, no npm installs, no code modifications.
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 1 error 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 11.4 minutes to install, slower than the median of the 72 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 73 ai-agent projects Argusic has installed and timed, BrowserKitten was the 47th fastest to reach a running state, and 46 of 73 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.
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)
ai-agentbrowser-agentbrowser-automationbyokchrome-extensionjavascriptllmlocal-firstmanifest-v3
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/browserkitten)Questions
- Does BrowserKitten run?
- Yes. BrowserKitten runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test BrowserKitten?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6ec7d9cc8411. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test BrowserKitten?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does BrowserKitten take to install?
- 11.4 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 BrowserKitten need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing BrowserKitten?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does BrowserKitten compare with the alternatives?
- Of the 73 ai-agent projects Argusic has installed and timed, BrowserKitten was the 47th fastest to reach a running state, and 46 of 73 reached one at all.
- Where is the evidence for BrowserKitten?
- 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.