SoL-Pi
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
Runssource: GitHubhomepageTypeScriptMITcommit 06b3ee358ddc
TypeScript, MIT licensed.
SoL-Pi runs. An Argusic agent installed it in 12 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
SoL-Pi installs on Node v22.23.3 as a project-local Pi 0.85.1 extension with all four mechanisms enabled, passes its complete test suite (21 files, 195 tests), and boots Pi offline cleanly (no extension load error).
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
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.
- Container's system Node is v18.19.1, below the project's required >=22.19.0.3 minutes
- npm audit --audit-level=high exits 1 with 6 vulnerabilities (3 moderate, 3 high) in the pinned Pi 0.85.1 dev toolchain (undici, brace-expansion, source-map-js, vitest).2 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npx vitest run -> 21 files passed, 195 tests passed; node scripts/check-sol-pi-config.mjs --config /work/repo/.pi/sol-pi.json --require-all-enabled -> exit 0, all_enabled true; pi --offline --approve --print --no-session 'say ok' -> exit 0, printed 'ok'; pi --version -> 0.85.1
- Model tokens used
- 86,422
- Exact commit tested
- 06b3ee358ddc
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
.gitignore:13:.pi/ .pi/settings.json ignore_exit=0 All checks done — `.pi/` is gitignored, repo otherwise clean. Final status: everything installed, t… exec /bin/sh -lc 'export PATH=$HOME/node22/bin:$PATH && export NPM_CONFIG_PREFIX=$HOME/.npm-global && $N… succeeded in 100ms: 0.85.1 exec /bin/sh -lc true in /work/repo succeeded in 0ms: tokens used 86,422
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 2 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.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 33 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 34 TypeScript projects Argusic has installed and timed, SoL-Pi was the 24th fastest to reach a running state, and 25 of 34 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.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/sol-pi)Questions
- Does SoL-Pi run?
- Yes. SoL-Pi runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test SoL-Pi?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 06b3ee358ddc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test SoL-Pi?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does SoL-Pi take to install?
- 12 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 SoL-Pi need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing SoL-Pi?
- 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 SoL-Pi compare with the alternatives?
- Of the 34 TypeScript projects Argusic has installed and timed, SoL-Pi was the 24th fastest to reach a running state, and 25 of 34 reached one at all.
- Where is the evidence for SoL-Pi?
- 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.