browser-use
Agents that use the browser.
Runssource: GitHubhomepagePythonMITcommit fe5ad353091f
Python, MIT licensed. The project labels itself: ai agents, ai tools, browser automation, browser use, llm, playwright and python.
browser-use runs. An Argusic agent installed it in 0.1 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
browser-use v0.13.10 installed in a Python 3.12 venv with uv, Chromium headless installed via playwright, and all 563 CI tests pass (529 passed, 34 skipped) after fixing 2 test identity comparison bugs in test_beta_agent.py that only manifest under xdist worker parallelism.
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.
- test_beta_agent.py uses identity checks (isinstance, is) on Generic class annotations imported in different xdist workers, causing failures under --dist=loadscope10 minutes
- Chromium browser not installed - uvx playwright install chromium failed inside the venv due to missing root escalation0.3 minutes
- Install time
- under a minute
- Cold machine to finish
- 75 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- Full test suite: python -m pytest tests/ci/ --tb=line (563 items). All individual test modules confirmed passing in isolation: test_beta_agent.py (201 passed, 1 skipped), browser/ (81 passed, 4 skipped), infrastructure/ (133 passed), models/ (61 passed, 5 skipped), security/ (45 passed), interactions/ (13 passed, 10 skipped), and all 28 standalone test files. CLI: bu --version prints 0.1.13, bu --help shows all commands. Main imports: from browser_use import Agent, Browser, Tools, ActionResult, ChatBrowserUse all succeed.
- Model tokens used
- 1,032,055
- Exact commit tested
- fe5ad353091f
- 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.
exited 143 in 0ms: exited 143 in 74246ms: 🛑 SIGTERM received. Exiting immediately... exec /bin/sh -lc "cd /work/repo && bash -c 'source .venv/bin/activate && python -m pytest tests/ci/test_… succeeded in 20051ms: tests/ci/test_beta_agent.py::test_rust_history_surfaces_terminal_session_interrupted_message PASSED ======================= 201 passed, 1 skipped in 17.42s ======================== I have full verification. Let me compile the final report. tokens used 1,032,055 I have full verification. Let me compile the final report.
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 0.1 minutes, faster than the median of the 11 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.
- Measured 3 times, so the result is not a one-off.
Of the 12 ai-agents projects Argusic has installed and timed, browser-use was the 1st fastest to reach a running state, and 8 of 12 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 0.1 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-agentsai-toolsbrowser-automationbrowser-usellmplaywrightpython
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/browser-use)Questions
- Does browser-use run?
- Yes. browser-use runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test browser-use?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit fe5ad353091f. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test browser-use?
- The run that produced this verdict cost $0.39: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does browser-use take to install?
- 0.1 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-use need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing browser-use?
- 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-use compare with the alternatives?
- Of the 12 ai-agents projects Argusic has installed and timed, browser-use was the 1st fastest to reach a running state, and 8 of 12 reached one at all.
- Where is the evidence for browser-use?
- All 3 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.