bux

Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Telegram, and a real browser on any box you own.

Runs with mockssource: GitHubhomepagePythonMITcommit f17c1b31d668

Python, MIT licensed. The project labels itself: ai agent, ai automation, automation, browser agent, browser automation, browser use, browser use box and browser use cloud.

bux runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.1 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Python venv at /tmp/bux-venv with websockets, httpx, Pillow installed. All 84 agent tests pass (telegram_bot: 63, mini_app: 16, bux_miniapp_tunnel: 3, login_flow: 2). The project can't fully launch without BROWSER_USE_API_KEY, TG_BOT_TOKEN, and systemd, those are real third-party services, but the full test suite exercises all components with mocked external dependencies.

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
1
last tested
stars
465
forks
59
open issues
22
watchers
1
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 bux, 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_login_flow.py::test_forced_claude_login_restarts_existing_shell failed: save_state tries to write to /etc/bux/tg-state.tmp which doesn't exist in the container2 minutes
Install time
under a minute
Cold machine to finish
4 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
PYTHONPATH=agent /tmp/bux-venv/bin/python -m pytest agent/test_telegram_bot.py agent/test_mini_app.py agent/test_bux_miniapp_tunnel.py agent/test_login_flow.py -v exited 0, 84 passed
Model tokens used
222,682
Exact commit tested
f17c1b31d668
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

# --- base packages ---------------------------------------------------------
say 'installing system packages'
export DEBIAN_FRONTEND=noninteractive
apt-get update -qq
apt-get install -y -qq \
  curl git build-essential python3 python3-pip python3-venv \
  unzip ca-certificates jq gnupg \
  ripgrep fd-find python3-dev make gcc g++ pkg-config libssl-dev zlib1g-dev \
All 84 tests pass — no errors remain. Here's the verified result:
tokens used
222,682
All 84 tests pass — no errors remain. Here's the verified result:

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

  • Installed in 0.1 minutes, faster than the median of the 83 comparable projects Argusic has measured.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 84 ai-agent projects Argusic has installed and timed, bux was the 4th fastest to reach a running state, and 58 of 84 reached one at all.

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 Runner1/3Runs with mocks92.000.04

Topics (from GitHub)

ai-agentai-automationautomationbrowser-agentbrowser-automationbrowser-usebrowser-use-boxbrowser-use-cloudclaude-codeclaude-code-agentcloud-browserpersistent-browserplaywrightplaywright-automationtelegram-agenttelegram-automationtelegram-botvpsvps-agentweb-automation

Embed the badge

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

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

Questions

Does bux run?
bux runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test bux?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit f17c1b31d668. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test bux?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does bux 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 bux need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing bux?
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 bux compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, bux was the 4th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for bux?
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.

Discussion