auto-browser

Give your AI agent a real browser, with a human in the loop. Open-source MCP-native browser agent.

Runssource: GitHubhomepagePythonMITcommit 6b2c196bb517

Python, MIT licensed. The project labels itself: ai agent, ai agents, browser automation, claude, docker, fastapi, llm and local first.

auto-browser runs. An Argusic agent installed it in 2 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 controller package installed, all 1189 host-side tests pass, lint is clean, and the app starts and serves a real browser session over MCP+CDP, successfully navigating to 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 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.06 (measured)
recorded runs
2
last tested
stars
929
forks
154
open issues
2
watchers
5
size
8 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 auto-browser, 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.

  • Test test_not_configured_without_api_key failed because the container had OPENROUTER_API_KEY env var set, which pydantic-settings picks up from os.environ, making the adapter report as configured3 minutes
  • Non-critical: harness extension init failed — /data directory not writable1 minute
Install time
2 minutes
Cold machine to finish
10 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
pip install succeeded; pytest tests/ passed 1189/1189 with 4 skipped; uvicorn app.main:app answered HTTP 200 on /healthz; MCP /mcp/tools returned 20 tools; browser.create_session with start_url=https://example.com returned status=active, current_url=https://example.com/, title='Example Domain', live=True, proving end-to-end browser control works
Model tokens used
176,041
Exact commit tested
6b2c196bb517
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.

    },
    {
      "msg": "Non-critical: harness extension init failed — /data directory not writable",
      "fix": "Set env vars to point at /tmp/auto-browser-data; harness init needs vars or /data to …
      "minutes": 1
    }
  ],
  "test_depth": "tier1_real",
  "verified_how": "pip install succeeded; pytest tests/ passed 1189/1189 with 4 skipped; uvicorn ap…
  "final_state": "The controller package installed, all 1189 host-side tests pass, lint is clean, a…
}
```

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 2 minutes, faster than the median of the 83 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 2 times, so the result is not a one-off.

Of the 84 ai-agent projects Argusic has installed and timed, auto-browser was the 24th fastest to reach a running state, and 58 of 84 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 2 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.06
Argusic Runner1/3Runs with mocks92.000.08

Topics (from GitHub)

ai-agentai-agentsbrowser-automationclaudedockerfastapillmlocal-firstmcpnovncplaywrightself-hosted

Embed the badge

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

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

Questions

Does auto-browser run?
Yes. auto-browser runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test auto-browser?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6b2c196bb517. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test auto-browser?
The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does auto-browser take to install?
2 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 auto-browser need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing auto-browser?
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 auto-browser compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, auto-browser was the 24th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for auto-browser?
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