herdr-browser

Render a real Chromium view inside a Herdr pane and drive it over CDP.

Runs with mockssource: GitHubTypeScriptMITcommit ab5c60b1e155

TypeScript, MIT licensed. The project labels itself: browser, browser automation, cdp, chromium, herdr plugin, kitty graphics and terminal.

herdr-browser runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Project builds, typechecks clean, all 140 tests pass, CLI help displays, and test HTTP server starts on localhost

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
$0.40 (measured)
recorded runs
1
last tested
stars
360
forks
24
open issues
8
watchers
0
size
0 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 herdr-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.

  • PaneGraphicsStream.open test: timeout promise rejection not caught; server close event missed4 minutes
  • staleChrome test: Bun.spawn with bash exec -a returns before exec completes3 minutes
Install time
1 minutes
Cold machine to finish
33 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
bun test exited 0, 140 passed, 306 expect calls; tsc --noEmit clean; bun run src/cli.ts --help prints usage; test server starts serving
Model tokens used
340,618
Exact commit tested
ab5c60b1e155
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.

 succeeded in 0ms:
{"install_succeeded":true,"launch_succeeded":true,"install_minutes":1,"errors":[{"msg":"PaneGraphic…
All 140 tests pass (306 expect calls), typecheck is clean, CLI help displays, test HTTP server star…
1. **herdrGraphics timeout test**: A race where Bun's test runner observed the rejected promise bet…
2. **staleChrome test**: `Bun.spawn` with `bash -c "exec -a ..."` returns before the target `exec` …
2026-10-23T14:49:14.144639Z ERROR codex_core::session: failed to record rollout items: thread 01a16…
2026-10-23T14:49:14.144674Z ERROR codex_core::session: failed to record rollout items: thread 01a16…
tokens used
340,618
All 140 tests pass (306 expect calls), typecheck is clean, CLI help displays, test HTTP server star…
1. **herdrGraphics timeout test**: A race where Bun's test runner observed the rejected promise bet…
2. **staleChrome test**: `Bun.spawn` with `bash -c "exec -a ..."` returns before the target `exec` …

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 1 minute, faster than the median of the 9 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.
  • 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 10 browser projects Argusic has installed and timed, herdr-browser was the 4th fastest to reach a running state, and 8 of 10 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 mocks92.000.40

Topics (from GitHub)

browserbrowser-automationcdpchromiumherdr-pluginkitty-graphicsterminal

Embed the badge

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

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

Questions

Does herdr-browser run?
herdr-browser runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test herdr-browser?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ab5c60b1e155. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test herdr-browser?
The run that produced this verdict cost $0.40: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does herdr-browser take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does herdr-browser need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing herdr-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 herdr-browser compare with the alternatives?
Of the 10 browser projects Argusic has installed and timed, herdr-browser was the 4th fastest to reach a running state, and 8 of 10 reached one at all.
Where is the evidence for herdr-browser?
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