text-to-cad
Design physical products with AI
Runssource: GitHubhomepagePythonMITcommit 4eaf7459a95c
Python, MIT licensed. The project labels itself: agents, ai agents, cad, mechanical engineering, robotics, step, stl and stp.
text-to-cad runs. An Argusic agent installed it in 30 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
cadgen 0.6.6 installed from source: OCP kernel loads, CLI responds, Python test suites for cadgen CLI/store/memo and all eight tested skill packages pass, cross-language JS runtime bundle and Playwright snapshot browser present.
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 60 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.
- pytest collection collision: multiple test files named test_cli.py and test_skill_structure.py across different skill test directories3 minutes
- cadgen-js node_modules missing, causing 'three' import failure in tessellation cache cross-language test1 minute
- cadgen-js test suite requires Node 22, container has Node 18
- rsync missing — viewer client bundle step skipped in bundle.sh
- Install time
- 30 minutes
- Cold machine to finish
- 32 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pytest --tb=short tests/python/global/ returned 135 passed/1 skipped/699 subtests; pytest tests/python/skills/dfam-check/ tests/python/skills/gcode/ tests/python/skills/bambu-labs/ tests/python/skills/sendcutsend/ tests/python/skills/cad-viewer/ tests/python/skills/dxf/ returned 140 passed/81 subtests; python -m cadgen.cli doctor reports kernel OK; python -m cadgen.cli --version returns 0.6.6
- Model tokens used
- 696,081
- Exact commit tested
- 4eaf7459a95c
- 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.
/bin/sh -lc 'cd /work/repo && echo "=== Verified summary ===" && echo "cadgen-js tests require Node… succeeded in 44562ms: tests/python/skills/dxf/test_drawing_checks.py::DrawingChecksTests::test_open_polyline_on_cut_layer… tests/python/skills/dxf/test_drawing_checks.py::DrawingChecksTests::test_raise_on_error_findings PA… tests/python/skills/dxf/test_drawing_checks.py::DrawingChecksTests::test_zero_length_and_duplicate_… tests/python/skills/dxf/test_snapshot_cli.py::DxfSnapshotCliTests::test_a_mesh_failure_is_an_error_… ============ 140 passed, 73 warnings, 81 subtests passed in 43.13s ============= Now I have all the data I need. Here's the final report: 2026-09-26T10:24:13.093117Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… tokens used 696,081 Now I have all the data I need. Here's the final report:
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 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 30 minutes to install, slower than the median of the 37 comparable projects Argusic has measured.
Of the 38 agents projects Argusic has installed and timed, text-to-cad was the 35th fastest to reach a running state, and 28 of 38 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.
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 | 2/3 | Runs | 100.00 | 0.14 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.13 |
Topics (from GitHub)
agentsai-agentscadmechanical-engineeringroboticsstepstlstptext-to-cad
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/text-to-cad)Questions
- Does text-to-cad run?
- Yes. text-to-cad runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test text-to-cad?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4eaf7459a95c. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test text-to-cad?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does text-to-cad take to install?
- 30 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 text-to-cad need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing text-to-cad?
- 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.
- How does text-to-cad compare with the alternatives?
- Of the 38 agents projects Argusic has installed and timed, text-to-cad was the 35th fastest to reach a running state, and 28 of 38 reached one at all.
- Where is the evidence for text-to-cad?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.