happyhands
Open-source, AI-assisted UI design review for coding agents. Inspect screenshots, scope code changes and compare results in a local workbench. Alpha.
Runssource: GitHubJavaScriptMITcommit 4010bdb8400b
JavaScript, MIT licensed. The project labels itself: ai assisted development, coding agents, design review, design systems, developer tools and ui review.
happyhands runs. An Argusic agent installed it in 6.7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
HappyHands workbench installs, builds, serves on port 4190, passes all 641 tests and 28 regression cases with Node 22.15.0 via portable binary
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. 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 v18.19.1 too old, requires >=22.150.5 minutes
- pnpm not in PATH, lockfile updated by older pnpm0.3 minutes
- Install time
- 7 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pnpm test exited 0, 641 passed; pnpm regression 28/28 passed; curl localhost:4190/apps/designer returned 200
- Model tokens used
- 101,659
- Exact commit tested
- 4010bdb8400b
- 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
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.
1. **Node.js version mismatch** (18.19.1 vs >=22.15) — Fixed by downloading and using `/tmp/node-v2… 2. **pnpm version too old** — Fixed by using `npx [email protected]` (the version specified in `package.… 3. **Lockfile config mismatch** after first install with pnpm 9 — Fixed by running `pnpm install --… **Verification results:** - `pnpm install` — success, 200 packages - `pnpm design:check` — passes, 4 pinned source files, 18 declared tokens - `pnpm build` — success, vite 8.3.5 production build in 1.26s - `pnpm test` — **641 pass, 0 fail** (602 top-level + subtests) in ~89s - `pnpm regression` — **28/28 cases pass** - `pnpm dev` — Vite server starts, HTTP 200 on `localhost:4173` - `pnpm workbench` — Vite server starts on port 4190, HTTP 200 on `/apps/designer/` One recommendation: bundle a portable Node.js binary in the repo or document the dependency on Node…
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 6.7 minutes.
- 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 6.7 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)
ai-assisted-developmentcoding-agentsdesign-reviewdesign-systemsdeveloper-toolsui-review
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/happyhands)Questions
- Does happyhands run?
- Yes. happyhands runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test happyhands?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4010bdb8400b. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test happyhands?
- 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 happyhands take to install?
- 6.7 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 happyhands need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing happyhands?
- 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.
- Where is the evidence for happyhands?
- 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.