npcsh
the composable multi-agent shell
Runs with mockssource: GitHubRustMITcommit e8d3cdd697d4
Rust, MIT licensed. The project labels itself: agentic coding, bash, bash shell, multi agent systems, super intelligence and superintelligence.
npcsh runs, with stand-ins for the services it depends on. An Argusic agent installed it in 15 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python test suite passes (72/72), Rust test suite passes (8/8), Rust release binaries compile and respond to version and help, Python backend serves health endpoint, npcsh shell initializes and connects to the backend after a one-line migration SQL fix
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
Subject data from GitHub, linked at the top of this page. 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.
- Missing Rust toolchain (no cargo/rustc)3 minutes
- npcpy backend listens on port 5337 but npcsh expects 52372 minutes
- Database migration fails because conversation_history table doesn't exist yet2 minutes
- Install time
- 15 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- cargo test: 8 passed; pytest: 72 passed, 2 skipped; python3 -m npcpy.serve answers /api/health with 200; npcsh --version prints 'npcsh 2.1.24 7e61bac9'; npc --version prints 'npc 2.1.24'
- Model tokens used
- 260,843
- Exact commit tested
- e8d3cdd697d4
- 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
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 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.
**Python backend** — responds `{"error":null,"status":"ok"}` on `GET /api/health`
**npcsh -c "hello"** — starts, connects to backend, runs migrations; can't complete an agent turn w…
One bug fixed: migration SQL was missing `CREATE TABLE IF NOT EXISTS conversation_history (...)` be…
tokens used
260,843
Here's the complete verification summary:
**Python tests** — 72 passed, 2 skipped
**Rust tests (cargo test)** — 8 passed
**Rust build** — release binaries compiled (`npcsh 2.1.24`, `npc 2.1.24`)
**Python backend** — responds `{"error":null,"status":"ok"}` on `GET /api/health`
**npcsh -c "hello"** — starts, connects to backend, runs migrations; can't complete an agent turn w…
One bug fixed: migration SQL was missing `CREATE TABLE IF NOT EXISTS conversation_history (...)` be…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.
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 15 minutes to install, slower than the median of the 19 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 20 agentic-coding projects Argusic has installed and timed, npcsh was the 17th fastest to reach a running state, and 14 of 20 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.17 |
Topics (from GitHub)
agentic-codingbashbash-shellmulti-agent-systemssuper-intelligencesuperintelligence
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/npcsh)Questions
- Does npcsh run?
- npcsh runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 15 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test npcsh?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e8d3cdd697d4. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test npcsh?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does npcsh take to install?
- 15 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 npcsh need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing npcsh?
- 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 npcsh compare with the alternatives?
- Of the 20 agentic-coding projects Argusic has installed and timed, npcsh was the 17th fastest to reach a running state, and 14 of 20 reached one at all.
- Where is the evidence for npcsh?
- 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.