Does open-codesign run?

Yes. open-codesign runs. Argusic installed and launched it on a clean machine in 60 minutes, hitting 4 errors on the way, and recorded the session.

How did Argusic test open-codesign?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 26c84984809b. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test open-codesign?

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 open-codesign take to install?

60 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 open-codesign need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing open-codesign?

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.

Where is the evidence for open-codesign?

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.

open-codesign

Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.

Runssource: GitHub homepageTypeScriptMITcommit 26c84984809b

TypeScript, MIT licensed. The project labels itself: ai design, anthropic, byok, claude, claude code, claude design, claude design alternative and deepseek.

open-codesign runs. An Argusic agent installed it in 60 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Dependencies installed, project builds, all 9 workspace packages pass tests independently (1418+ tests), and the Electron app main process launches on Xvfb, logs its version, and seeds templates.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.16 (measured)
recorded runs: 1
last tested: 2026-09-28
stars: 7,975
forks: 834
open issues: 91
watchers: 32
size: 67 MB
created: 2026-04-18
last push: 2026-09-28

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-28. 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 open-codesign, 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.

Node.js 18 installed but project requires 22+5 minutes
Build scripts blocked for esbuild, koffi, protobufjs, @google/genai, electron-winstaller3 minutes
3 web-research tests failed: System Chrome not found3 minutes
pnpm not found1 minute

Install time: 60 minutes
Cold machine to finish: 60 minutes
Errors hit and fixed: 4 hit, 4 fixed with no human help
How the result was proved: pnpm build exited 0 (built apps/desktop/out/main/index.js 6.7MB). Individual packages: core 551 passed, shared 292 passed, runtime 172 passed, providers 214 passed, exporters 90 passed/3 skipped, templates 12 passed, i18n 15 passed, ui 11 passed, script tests 61 passed. Desktop sampled: onboarding-ipc 69 passed, connection-ipc+codex-oauth-ipc+session-chat+workspace-reader+design-workspace+resolve-api-key+keychain+generation-ipc+preferences-ipc+diagnostics-ipc = 313 passed, web-research 14 passed. Electron app launched: open-codesign starting { version: 39.8.10, platform: linux } logged, templates seeded.
Model tokens used: 372,677
Exact commit tested: 26c84984809b
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.

Templates: 12 passed
i18n: 15 passed
UI: 11 passed
Desktop (sampled): 313+14+69=396 passed
=== App launch ===
Electron main process started with version and template seeding
Now let me compile the final report based on everything I've verified.
exec
/bin/sh -lc "echo 'ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"inst…
 succeeded in 0ms:
tokens used
372,677

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 60 minutes.
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 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.

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	100.00	0.16	2026-09-28 11:31 UTC

Embed the badge

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

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

Questions

Does open-codesign run?: Yes. open-codesign runs. Argusic installed and launched it on a clean machine in 60 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test open-codesign?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 26c84984809b. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test open-codesign?: 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 open-codesign take to install?: 60 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 open-codesign need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing open-codesign?: 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.
Where is the evidence for open-codesign?: 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.