bluebox

Index the world's undocumented APIs

Runssource: GitHubPythonApache-2.0commit 1021d39243f6

Python, Apache-2.0 licensed. The project labels itself: ai agents, ai web app, ai website, api, browser automation, cdp, chrome devtools protocol and llm web interface.

bluebox runs. An Argusic agent installed it in 3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 2434 unit tests pass after fixing 2 flaky async tests; pip editable install succeeds; CLI help commands work for bluebox-agent and bluebox-discover; core Python imports resolve without errors.

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
$0.02 (measured)
recorded runs
1
last tested
stars
203
forks
36
open issues
17
watchers
0
size
24 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 bluebox, 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.

  • 2 tests failed due to asyncio event loop handling: test_handle_unknown_message_returns_false in both AsyncWindowPropertyMonitorMessageHandling and AsyncInteractionMonitorMessageHandling1 minute
Install time
3 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
python -m pytest tests/ -q exited 0, 2434 passed
Model tokens used
68,398
Exact commit tested
1021d39243f6
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.

Now let me check how much time elapsed and compile the report.
exec
/bin/sh -lc 'echo "Start ~06:02, now $(date +%H:%M)"' in /work/repo
 succeeded in 0ms:
Start ~06:02, now 06:05
exec
/bin/sh -lc 'cd /work/repo && git diff --stat' in /work/repo
 succeeded in 0ms:
 tests/unit/cdp/test_monitors.py | 19 ++++++-------------
 1 file changed, 6 insertions(+), 13 deletions(-)
tokens used
68,398

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 3 minutes, faster than the median of the 123 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.
  • Ran without a GPU, so it does not need one to start.
  • Licensed Apache-2.0, 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 124 ai-agents projects Argusic has installed and timed, bluebox was the 49th fastest to reach a running state, and 96 of 124 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 3 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 Runner1/3Runs100.000.02

Topics (from GitHub)

ai-agentsai-web-appai-websiteapibrowser-automationcdpchrome-devtools-protocolllm-web-interfacemcpreverse-engineeringrobotic-process-automationweb-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/bluebox.svg)](https://argusic.com/subject/bluebox)

Questions

Does bluebox run?
Yes. bluebox runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test bluebox?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1021d39243f6. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test bluebox?
The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does bluebox take to install?
3 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 bluebox need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing bluebox?
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 bluebox compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, bluebox was the 49th fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for bluebox?
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