onlook
The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI
Runssource: GitHubhomepageTypeScriptApache-2.0commit 423e2e924366
TypeScript, Apache-2.0 licensed. The project labels itself: ai, cursor, cursor ai, design, design to code, drizzle, editor and figma.
onlook runs. An Argusic agent installed it in 7 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The Next.js app builds and starts, responds with HTTP 200 on /, and 1064 tests pass across the monorepo.
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 18.19.1 too old for Next.js (>=20.9.0 required)3 minutes
- unzip not installed; Bun installer requires it2 minutes
- 6 required env vars missing in Next.js build validation2 minutes
- Install time
- 7 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- bun test exited 0 (1064 pass, 1 skip, 0 fail); curl -s -o /dev/null -w '%{http_code}' http://localhost:3000/ returned 200
- Model tokens used
- 99,182
- Exact commit tested
- 423e2e924366
- 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.
- Node.js 18 too old for Next.js — installed nvm and Node.js 22 (3 min) - 6 required env vars missing (CSB_API_KEY, Supabase keys, Argusic key) — created `.env` with mock … tokens used 99,182 Everything works. Here's the report: **Install** — `bun install` completed (2335 packages, 8.6s), `bun run build` succeeded. **Tests** — `bun test` exited 0: 1064 pass, 1 skip, 0 fail. **Launch** — Dev server started on `http://localhost:3000` and served HTTP 200 on `/`. **Errors encountered**: - `unzip` missing for Bun installer — downloaded via `apt-get download` and extracted locally (2 mi… - Node.js 18 too old for Next.js — installed nvm and Node.js 22 (3 min) - 6 required env vars missing (CSB_API_KEY, Supabase keys, Argusic key) — created `.env` with mock …
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 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
- Took 7 minutes to install, slower than the median of the 38 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 39 ai projects Argusic has installed and timed, onlook was the 22nd fastest to reach a running state, and 32 of 39 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 7 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)
aicursorcursor-aidesigndesign-to-codedrizzleeditorfigmafrontendidelow-codenextjsreactsupabasetailwindcsstypescriptuivibe-codingvibecoding
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/onlook)Questions
- Does onlook run?
- Yes. onlook runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test onlook?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 423e2e924366. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test onlook?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does onlook take to install?
- 7 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 onlook need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing onlook?
- 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 onlook compare with the alternatives?
- Of the 39 ai projects Argusic has installed and timed, onlook was the 22nd fastest to reach a running state, and 32 of 39 reached one at all.
- Where is the evidence for onlook?
- 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.