browser-control

A tiny, fast Rust CLI that drives a real browser over the Chrome DevTools Protocol, built for coding agents.

Runssource: GitHubRustMITcommit b352a1ac0171

Rust, MIT licensed. The project labels itself: agent, browser automation, llm and rust.

browser-control runs. An Argusic agent installed it in 12 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

browser-control-cli v0.1.1 builds, all 10 unit tests pass, formatting check passes (verify.sh), and the binary launches Chrome headlessly, navigates to URLs, evaluates JS, snapshots page elements, clicks element refs, and issues raw CDP commands, all verified end-to-end with Chromium 119 against https://example.com.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.31 (measured)
recorded runs
2
last tested
stars
3,160
forks
210
open issues
1
watchers
78
size
5 MB
created
last push

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.

Time lost to each failure while testing browser-control, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • No Rust toolchain installed2 minutes
  • No Chrome/Chromium available1 minute
  • Chrome crashes with sandbox error (--no-sandbox needed)1 minute
  • Chrome 119+ HTTP CDP discovery fails without --remote-allow-origins=*1 minute
  • Formatting check failed in verify.sh1 minute
Install time
12 minutes
Cold machine to finish
15 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
browser-control launch --headless → open https://example.com → eval 'document.title' returned 'Example Domain' → snapshot showed @e1 → click @e1 navigated to iana.org (title 'Example Domains') → cdp Browser.getVersion returned Chrome/119.0.6045.105 → stop exited 0; cargo test --locked: 10 passed 0 failed
Model tokens used
102,900
Exact commit tested
b352a1ac0171
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.

  "description": ""
}
npm WARN deprecated [email protected]: < 24.15.0 is no longer supported
added 107 packages, and audited 108 packages in 10m
10 packages are looking for funding
  run `npm fund` for details
10 high severity vulnerabilities
To address all issues (including breaking changes), run:
  npm audit fix --force
Run `npm audit` for details.
tokens used
102,900

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 5 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 12 minutes to install, slower than the median of the 137 comparable projects Argusic has measured.

Of the 138 agent projects Argusic has installed and timed, browser-control was the 91st fastest to reach a running state, and 92 of 138 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.31
Argusic Runner1/3Runs100.000.06

Topics (from GitHub)

agentbrowser-automationllmrust

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/browser-control.svg)](https://argusic.com/subject/browser-control)

Questions

Does browser-control run?
Yes. browser-control runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test browser-control?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit b352a1ac0171. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test browser-control?
The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does browser-control 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 browser-control need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing browser-control?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does browser-control compare with the alternatives?
Of the 138 agent projects Argusic has installed and timed, browser-control was the 91st fastest to reach a running state, and 92 of 138 reached one at all.
Where is the evidence for browser-control?
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.

Discussion