giselle
Giselle: AI App Builder. Open Source.
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit 7dca22434e3d
TypeScript, Apache-2.0 licensed. The project labels itself: agent, agent builder, agentic ai, ai, ai agent, ai agents, anthropic and gemini.
giselle runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
Giselle monorepo installs, all SDK packages build, 653 tests pass, types check, and the Next.js dev server starts and responds with HTTP 307 at localhost:3456.
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 88 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 v18.19.1 installed but project requires >=243 minutes
- Production build OOM-killed (exit 137) during page data collection3 minutes
- pnpm binary not found on PATH2 minutes
- Studio build failed due to missing Supabase env vars2 minutes
- npm install -g failed with EACCES1 minute
- Install time
- 1 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 5 hit, 4 fixed with no human help
- How the result was proved
- pnpm test exited 0 (653 passed, 6 skipped); curl -s -o /dev/null -w %{http_code} localhost:3456 returned 307
- Model tokens used
- 109,878
- Exact commit tested
- 7dca22434e3d
- 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.
6. **Formatting** -- `pnpm format`: 1529 files checked, no fixes needed. 7. **Tidy** -- `pnpm tidy` (knip): no unused files or deps found. 8. **Studio build** -- Compiled successfully (Turbopack + TypeScript passed), but was **OOM-killed*… 9. **Dev server** -- Started and served: `curl http://localhost:3456` returned **HTTP 307** (redire… ### Errors encountered and fixed | Error | Fix | |---|---| | `node v18.19.1` (too old; project requires `>=24`) | Installed `n`, used it to install and activa… | `pnpm: not found` | Installed `pnpm@10` via `npm install -g` with `--prefix=$HOME/.npm-global` | | `EACCES` on `npm install -g` | Used `--prefix=$HOME/.npm-global` (no root access) | | `Missing Supabase credentials` during build | Created `.env.local` with mock Supabase/Postgres/Ar… | Production build OOM (exit 137) | Container memory limit; dev server works fine |
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
- Installed in 1 minute, faster than the median of the 140 comparable projects Argusic has measured.
- Licensed Apache-2.0, 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.
- Hit 5 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 141 agent projects Argusic has installed and timed, giselle was the 18th fastest to reach a running state, and 94 of 141 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 88.00 | 0.03 |
Topics (from GitHub)
agentagent-builderagentic-aiaiai-agentai-agentsanthropicgeminigenaigenerative-aimultiagentnextjsno-codeopen-sourceopenaipnpmragtypescriptvercelworkflow
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/giselle)Questions
- Does giselle run?
- giselle runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test giselle?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7dca22434e3d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test giselle?
- 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 giselle 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 giselle need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing giselle?
- 5 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 giselle compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, giselle was the 18th fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for giselle?
- 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.