opensrc
Fetch source code for npm packages to give AI coding agents deeper context
Runssource: GitHubhomepageRustApache-2.0commit f96078ac0a7c
Rust, Apache-2.0 licensed. The project labels itself: ai, ai coding, cli, coding agents, developer tools, llm, nodejs and npm.
opensrc runs. An Argusic agent installed it in 1 minute and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The opensrc CLI and docs site both install, build, and run. CLI fetches source from npm, PyPI, and crates.io and provides cached paths for grep/search. Docs site builds and serves on port 3456 returning HTTP 200. Rust compilation tests fail due to missing cargo (no root), but the pre-built native binary is downloaded during install and works fully.
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.
- Node.js v18 present but project requires >=24; pnpm not available2 minutes
- Rust toolchain missing: 'cargo test' failed in opensrc#test1 minute
- GitHub API rate limit exceeded when fetching vercel/next.js
- Install time
- 1 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pnpm install exited 0; 'next build' completed successfully (12 static pages); 'next start -p 3456' returned HTTP 200; 'opensrc fetch zod' fetched source; 'opensrc list' showed 3 cached packages; CLI --help and --version returned correct output
- Model tokens used
- 82,782
- Exact commit tested
- f96078ac0a7c
- 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.
→ Also removed repo (no other packages use it) Removed 1 source(s) Everything works. Let me calculate the time from start exec /bin/sh -lc 'echo "Started at roughly 17:25, now is:" && date' in /work/repo succeeded in 0ms: Started at roughly 17:25, now is: Mon Sep 7 17:36:07 UTC 2026 About 11 minutes total. Now I'll compile my final report. tokens used 82,782 About 11 minutes total. Now I'll compile my final 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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 1 minute, faster than the median of the 36 comparable projects Argusic has measured.
- 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 37 ai projects Argusic has installed and timed, opensrc was the 3rd fastest to reach a running state, and 30 of 37 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 1 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
Topics (from GitHub)
aiai-codingclicoding-agentsdeveloper-toolsllmnodejsnpmsource-codetypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opensrc)Questions
- Does opensrc run?
- Yes. opensrc runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test opensrc?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f96078ac0a7c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test opensrc?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does opensrc take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does opensrc need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing opensrc?
- 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 opensrc compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, opensrc was the 3rd fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for opensrc?
- 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.