gentle-shell

Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).

Runssource: GitHubhomepageTypeScriptMITcommit b27bd328b95e

TypeScript, MIT licensed. The project labels itself: agent harness, agent skills, ai agents, ai coding, ai coding agent, code review, coding agents and developer tools.

gentle-shell runs. An Argusic agent installed it in 7 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

gentle-pi v3.7.0 builds, installs, its 3903 unit tests pass, provider-contract mirror check passes, runtime-harness passes, the gentle-shell binary launches reporting version 3.7.0 with pi 0.87.1, and the package-local Gentle AI v3.7.0 binary is installed.

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
$0.19 (measured)
recorded runs
2
last tested
stars
2,869
forks
299
open issues
445
watchers
3
size
81 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 gentle-shell, 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 18.19.1 does not support --experimental-strip-types flag required by the project2 minutes
  • pnpm not in default PATH in spawned child processes2 minutes
  • @earendil-works/pi-ai dependency uses import attributes with {type:"json"} syntax requiring Node 20+1 minute
  • @earendil-works/pi-tui uses /v regex flag requiring Node 20+1 minute
Install time
7 minutes
Cold machine to finish
29 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
pnpm test via npx pnpm: unit-tests 3903 pass 1 fail (counting artifact, see notes) 36 cancelled 41 skipped, provider-contract PASS, runtime-harness PASS. gentle-shell --version returned 'gentle-shell 3.7.0, pi 0.87.1, home isolated...'
Model tokens used
146,781
Exact commit tested
b27bd328b95e
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 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. 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.

Done in 52ms using pnpm v11.1.1
Now let me check the elasped time. Starting from first command at ~19:17:30 to now 19:24-ish:
exec
/bin/sh -lc 'date +%s' in /work/repo
 succeeded in 0ms:
1794426403
Started around 1794426300 (estimating from the debug log), now 1794426403 = about 3-4 minutes. Wait…
Now, I need to provide the ARGUSIC_RESULT line. Let me compile it:
tokens used
146,781
Started around 1794426300 (estimating from the debug log), now 1794426403 = about 3-4 minutes. Wait…
Now, I need to provide the ARGUSIC_RESULT line. Let me compile it:

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 7 minutes, faster than the median of the 10 comparable projects Argusic has measured.
  • Recovered from all 4 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.

Of the 11 agent-harness projects Argusic has installed and timed, gentle-shell was the 6th fastest to reach a running state, and 9 of 11 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 7 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 Runner2/3Runs100.000.19
Argusic Runner1/3Runs100.000.45

Topics (from GitHub)

agent-harnessagent-skillsai-agentsai-codingai-coding-agentcode-reviewcoding-agentsdeveloper-toolsgentle-aigentle-shell-packagellmmcpopenspecpipi-coding-agentrddsddspec-driven-developmentsubagentstdd

Embed the badge

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

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

Questions

Does gentle-shell run?
Yes. gentle-shell runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test gentle-shell?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit b27bd328b95e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test gentle-shell?
The run that produced this verdict cost $0.19: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does gentle-shell take to install?
7 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 gentle-shell need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing gentle-shell?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does gentle-shell compare with the alternatives?
Of the 11 agent-harness projects Argusic has installed and timed, gentle-shell was the 6th fastest to reach a running state, and 9 of 11 reached one at all.
Where is the evidence for gentle-shell?
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