pi-agent-browser-native

pi extension that exposes agent-browser as a native tool for browser automation

Runs with mockssource: GitHubTypeScriptMITcommit 6d4f6fefa14c

TypeScript, MIT licensed. The project labels itself: agent browser, browser automation, npm package, pi, pi extension, pi package and typescript.

pi-agent-browser-native runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

npm install, build, and doctor pass; 1137 of 1256 tests pass with fake-agent-browser fixtures; 79 pre-existing cold-reopen and daemon-boundary failures remain

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
$0.88 (measured)
recorded runs
1
last tested
stars
258
forks
40
open issues
4
watchers
0
size
13 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 pi-agent-browser-native, 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.

  • Container umask 0002 creates group-writable directories (0o775) rejected by isTrustedPosixDirectory in managed-session-storage.ts20 minutes
Install time
4 minutes
Cold machine to finish
84 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
npm test exited 1: 1137 pass, 79 fail (all pre-existing), 40 skip
Model tokens used
2,757,889
Exact commit tested
6d4f6fefa14c
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.

All core test files I set out to fix now pass fully. Here's the summary:
**Install and build:** `npm install` + `npm run build` succeed with Node 24.22.1.
**Doctor:** passes — agent-browser 0.38.1 recognized, Pi 0.87.1 found.
**Test suite:** 1137 pass, 79 fail, 40 skip. From the original 108 failures, I fixed **29** by reso…
The browser-evidence.test.ts `session info` test failure (shared URL reads) is also clearly pre-exi…
tokens used
2,757,889
All core test files I set out to fix now pass fully. Here's the summary:
**Install and build:** `npm install` + `npm run build` succeed with Node 24.22.1.
**Doctor:** passes — agent-browser 0.38.1 recognized, Pi 0.87.1 found.
**Test suite:** 1137 pass, 79 fail, 40 skip. From the original 108 failures, I fixed **29** by reso…
The browser-evidence.test.ts `session info` test failure (shared URL reads) is also clearly pre-exi…

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 3.5 minutes.
  • 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.

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 mocks92.000.88

Topics (from GitHub)

agent-browserbrowser-automationnpm-packagepipi-extensionpi-packagetypescript

Embed the badge

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

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

Questions

Does pi-agent-browser-native run?
pi-agent-browser-native runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 4 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test pi-agent-browser-native?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6d4f6fefa14c. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test pi-agent-browser-native?
The run that produced this verdict cost $0.88: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does pi-agent-browser-native take to install?
3.5 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 pi-agent-browser-native need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing pi-agent-browser-native?
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.
Where is the evidence for pi-agent-browser-native?
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