browser-harness
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Runssource: GitHubhomepagePythonMITcommit afbcc381b963
Python, MIT licensed. The project labels itself: ai agent, browser agent, browser automation, browser use, browser use box, browser use cloud, cdp and cloud browser.
browser-harness runs. An Argusic agent installed it in 7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The package installs, builds, passes all 283 tests, and the CLI drives a real headless Chrome via CDP (navigate, page_info) when pointed at a running browser with BU_CDP_WS.
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.
- No Chrome browser installed in container — daemon refused to start10 minutes
- Chrome needs --no-sandbox in unprivileged container2 minutes
- Install time
- 7 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- py.test tests/unit passed 266/1; py.test tests/integration passed 17/0; browser-harness <<'PY' print(page_info()) returned correct page data after navigating to example.com; browser-harness --version returned 0.1.13
- Model tokens used
- 150,378
- Exact commit tested
- afbcc381b963
- 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.
- **Integration tests**: `python -m pytest tests/integration -v` → **17 passed**. - **Real browser end-to-end**: Launched Playwright's headless Chrome with `--remote-debugging-port=… One issue encountered: the daemon's `supported_browser_running()` only scans standard profile direc… tokens used 150,378 Here's the final report: - **Install**: `uv` installed the project and dependencies with zero errors. The `./browser-harness… - **Launcher**: `./browser-harness --doctor`, `--version`, `skill`, `recordings`, `telemetry status… - **Unit tests**: `python -m pytest tests/unit -q` → **266 passed, 1 skipped**. - **Integration tests**: `python -m pytest tests/integration -v` → **17 passed**. - **Real browser end-to-end**: Launched Playwright's headless Chrome with `--remote-debugging-port=… One issue encountered: the daemon's `supported_browser_running()` only scans standard profile direc…
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 7 minutes, faster than the median of the 12 comparable projects Argusic has measured.
- Recovered from all 2 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 13 ai-agent projects Argusic has installed and timed, browser-harness was the 7th fastest to reach a running state, and 10 of 13 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 7 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)
ai-agentbrowser-agentbrowser-automationbrowser-usebrowser-use-boxbrowser-use-cloudcdpcloud-browserllmpersistent-browserplaywrighttelegram-agentvps-agentweb-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/browser-harness)Questions
- Does browser-harness run?
- Yes. browser-harness runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test browser-harness?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit afbcc381b963. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test browser-harness?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does browser-harness take to install?
- 7 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-harness need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing browser-harness?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does browser-harness compare with the alternatives?
- Of the 13 ai-agent projects Argusic has installed and timed, browser-harness was the 7th fastest to reach a running state, and 10 of 13 reached one at all.
- Where is the evidence for browser-harness?
- 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.