percho

Percho: Minimalist desktop GUI for the Pi coding agent, the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals, and custom themes.

Runssource: GitHubhomepageTypeScriptMITcommit 2db9bec6e483

TypeScript, MIT licensed. The project labels itself: agent, ai agent, coding agent, desktop app, gui, minimalist, pi and pi agent.

percho runs. An Argusic agent installed it in 8 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 538 tests pass across 49 test files in both packages/backend and packages/desktop; typecheck passes in all 3 workspaces; the production Electron build succeeds; the app launches and reports app ready v43.3.0

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

At a glance

verdict
Runs
Argusic Score
60 / 100
cost of the verifying run
$0.07 (measured)
recorded runs
2
last tested
stars
545
forks
50
open issues
18
watchers
2
size
39 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 percho, 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.

  • Node.js 18.19.1 installed but project requires >=22.191 minute
  • electron-vite build OOM (JavaScript heap out of memory)1 minute
  • Electron SUID sandbox helper not configured
Install time
8 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
npm test passed: 49 test files, 538 tests passed; npx electron --no-sandbox --version returned v43.3.0; npx electron --no-sandbox out/main/index.js printed [main] app ready version 43.3.0 then ran until timeout
Model tokens used
52,623
Exact commit tested
2db9bec6e483
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

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

Here's the summary of everything I did:
- **Error 1**: Node.js v18 in container, project requires >=22.19. Fixed by installing nvm and Node…
- **Error 2**: Build OOM (client bundle too large for default heap). Fixed by running with `NODE_OP…
- **Error 3**: Electron SUID sandbox fails in container. Worked around with `--no-sandbox`.
- The Electron app launched successfully (observed `[main] app ready {"version":"43.3.0"}`) and ran…
tokens used
52,623
Here's the summary of everything I did:
- **Error 1**: Node.js v18 in container, project requires >=22.19. Fixed by installing nvm and Node…
- **Error 2**: Build OOM (client bundle too large for default heap). Fixed by running with `NODE_OP…
- **Error 3**: Electron SUID sandbox fails in container. Worked around with `--no-sandbox`.
- The Electron app launched successfully (observed `[main] app ready {"version":"43.3.0"}`) and ran…

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.
  • Recovered from all 3 errors 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 MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 8 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, percho was the 81st fastest to reach a running state, and 94 of 141 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 8 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 Runner2/3Runs100.000.07
Argusic Runner1/3Did not run20.000.07

Topics (from GitHub)

agentai-agentcoding-agentdesktop-appguiminimalistpipi-agentpi-desktop

Embed the badge

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

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

Questions

Does percho run?
Yes. percho runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test percho?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2db9bec6e483. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test percho?
The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does percho take to install?
8 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 percho need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing percho?
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 percho compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, percho was the 81st fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for percho?
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