cloudflare-os
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
Runssource: GitHubhomepageTypeScriptApache-2.0commit 004ab773fad6
TypeScript, Apache-2.0 licensed.
cloudflare-os runs. An Argusic agent installed it in 1 minute and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pnpm 11.17.0 installed, Node upgraded to v23.11.0 with --experimental-strip-types, all 38 test tasks pass with 0 failures across all packages, and the dev server serves HTTP 200 on port 8787.
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.
- URLPattern is not a global in Node 23 (it's in node:url); 5 test files/ configs failed with 'URLPattern is not defined'3 minutes
- System had Node v18.19.1, but pnpm 11.17.0 requires >=22.130.5 minutes
- Node without --experimental-strip-types cannot run .ts files; vite-plus spawns subprocesses that don't inherit the flag0.5 minutes
- portal-boundaries test expected error text /native connector/ but code now produces a different message0.5 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 33 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm test via 'node scripts/vp/run.ts --filter=!cloudflare-os --cache test', 38 tasks, 0 failures; curl -s -o /dev/null -w %{http_code} localhost:8787 returned 200
- Model tokens used
- 771,550
- Exact commit tested
- 004ab773fad6
- 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.
Test Files 3 passed (3)
Tests 158 passed (158)
Test Files 2 passed (2)
Tests 125 passed (125)
Test Files 17 passed (17)
Tests 75 passed (75)
Test Files 9 passed (9)
Tests 69 passed (69)
All tests pass with zero failures across all 38 test tasks. Let me present the final result.
tokens used
771,550
All tests pass with zero failures across all 38 test tasks. Let me present the final result.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 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 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 11 TypeScript projects Argusic has installed and timed, cloudflare-os was the 1st 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 1 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cloudflare-os)Questions
- Does cloudflare-os run?
- Yes. cloudflare-os runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test cloudflare-os?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 004ab773fad6. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test cloudflare-os?
- The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does cloudflare-os 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 cloudflare-os need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing cloudflare-os?
- 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 cloudflare-os compare with the alternatives?
- Of the 11 TypeScript projects Argusic has installed and timed, cloudflare-os was the 1st fastest to reach a running state, and 9 of 11 reached one at all.
- Where is the evidence for cloudflare-os?
- 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.