parchi

Your AI friend right in your browser

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 0678f72a3e16

TypeScript, MIT licensed. The project labels itself: agent, ai, browser automation, browser extension, model agnostic and workflow.

parchi runs, with stand-ins for the services it depends on. An Argusic agent installed it in 35 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

npm install completed 771 packages with warnings about node version requirements; npm run build produces dist/ with manifest.json, background.js, sidepanel/panel.{js,css,html}, and content scripts; npm test passes 233 checks; integration tests pass 19; orchestrator harness passes 7; tsc typechecks without errors; repo-standards passes; 12/21 E2E tests pass in headless mode; biome reports 20 formatting/lint issues.

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

At a glance

verdict
Runs with mocks
Argusic Score
56 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
549
forks
58
open issues
15
watchers
2
size
9 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.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • npm WARN EBADENGINE: 20+ packages require node >=20 but node v18.19.1 is installed
  • npm test: 9/21 E2E tests timed out in headless virtual display (panel loading, quick actions, new session, theme, look-and-feel, tool renders)
  • biome lint: 20 formatting/lint errors (mostly unused template literal, formatting diffs in 3 source files)
Install time
35 minutes
Cold machine to finish
12 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
npm test exited 0 (233 checks passed: 27 validate + 206 unit); npm run test:integration exited 0 (19 passed); orchestrator fixture executor exited 0 (7 passed); tsc --noEmit typecheck exited 0; repo-standards check passed
Model tokens used
59,599
Exact commit tested
0678f72a3e16
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 388ms:
Tests Passed: 206
Now I have all the data. Let me compile the final report.
exec
/bin/sh -lc 'cd /work/repo && node dist/tests/orchestrator/run-fixture-executor.js 2>&1 | grep -E "…
 succeeded in 273ms:
All orchestrator fixtures passed.
All data collected. Here is my report:
2026-10-18T10:47:47.686200Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
tokens used
59,599
All data collected. Here is my report:

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

  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

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.
  • Took 35 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.

Of the 141 agent projects Argusic has installed and timed, parchi was the 133rd fastest to reach a running state, and 94 of 141 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 Runner2/3Runs with mocks92.000.03
Argusic Runner1/3Did not run20.000.03

Topics (from GitHub)

agentaibrowser-automationbrowser-extensionmodel-agnosticworkflow

Embed the badge

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

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

Questions

Does parchi run?
parchi runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 35 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test parchi?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0678f72a3e16. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test parchi?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does parchi take to install?
35 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 parchi need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing parchi?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does parchi compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, parchi was the 133rd fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for parchi?
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