whirl

The AI chat app that sweats the details. Every top model, real memory, living documents, and your own tools.

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 1fb4754706c3

TypeScript, MIT licensed. The project labels itself: ai, ai chat, chat, convex, llm, nextjs, openrouter and react.

whirl runs, with stand-ins for the services it depends on. An Argusic agent installed it in 6 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 3 test suites pass (239 tests total): 106 app unit tests, 67 backend unit tests, and 66 backend integration tests. The Next.js production build compiles successfully with all 26 static pages pre-rendered. The dev server starts and serves a 200 response on / with 91KB of app HTML. Pages through Clerk's middleware require real Clerk credentials (a genuine third-party dependency).

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.16 (measured)
recorded runs
1
last tested
stars
514
forks
50
open issues
3
watchers
4
size
5 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 whirl, 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.

  • clerk middleware rejects mock keys at server-side auth boundary2 minutes
  • bun not found1 minute
  • unzip not found for bun installer1 minute
  • node 18 too old for next.js 16 (requires >=20.9.0)1 minute
  • build failed: missing NEXT_PUBLIC_CONVEX_URL env var1 minute
  • vitest's rolldown dep requires node:util.styleText (node 21+)
Install time
6 minutes
Cold machine to finish
23 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
bun test in apps/v2: 106 passed, 0 failed. npx vitest run in packages/backend (with node 22): 66 passed, 0 failed. bun run build in apps/v2: compiled successfully, all 26 static pages generated. curl http://localhost:3000/ returned HTTP 200 with 90878 bytes of HTML. curl http://localhost:3000/debug returned HTTP 500: Publishable key not valid (clerk middleware needs real api keys).
Model tokens used
114,106
Exact commit tested
1fb4754706c3
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.

- `packages/backend` (bun:test): 67 pass, 3 slot tests skipped by bun (use vitest features)
- `packages/backend` (vitest with Node 22): 66 pass, 0 fail
**Build**: `bun run build` in `apps/v2` → compiled successfully, all 26 static pages generated (inc…
**Launch**: Dev server starts on port 3000. The home page returned HTTP 200 (91KB) after initial co…
| Error | Fix | Time |
|-------|-----|------|
| `bun: not found` | Downloaded prebuilt Bun binary | 1m |
| `unzip: not found` | Used Python zipfile to extract Bun | 1m |
| Node 18 too old for Next.js 16 | Installed Node 22.14.0 locally | 1m |
| Node 18 too old for vitest's rolldown dep (`node:util.styleText`) | Same Node 22 fix | 0m |
| Build fails: `Missing NEXT_PUBLIC_CONVEX_URL` | Created `apps/v2/.env.local` | 1m |
| 500 on pages: Clerk `Publishable key not valid` | Used properly-formatted key (passes parsing, Cl…

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 6 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 6 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 237 ai projects Argusic has installed and timed, whirl was the 138th fastest to reach a running state, and 168 of 237 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.16

Topics (from GitHub)

aiai-chatchatconvexllmnextjsopenrouterreactself-hostedtypescript

Embed the badge

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

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

Questions

Does whirl run?
whirl runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 6 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test whirl?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1fb4754706c3. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test whirl?
The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does whirl take to install?
6 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 whirl need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing whirl?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does whirl compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, whirl was the 138th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for whirl?
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.

Discussion