Show HN: Loböle, open-source parametric CAD that AI agents can drive
I could never get used to FreeCAD, so I built my own. It turns out Claude is really good at using it. Loböle is a parametric B-Rep CAD built on OpenCASCADE and Vulkan, with sketches, assemblies, drawings, FEM and CAM. The GUI, Python scripts and AI agents all go through the same commands, so an agent can do anything you can in the GUI. The engine, watch and bicycle in the README were each built by Claude writing a script against it.
Read original source
Source record
Recorded metrics
points · 1 votes
2026-10-25 17:15:28.260Z
cumulative since publication
Research analysis
Project record
Repository: eliasaronson/lobole. Source account: I could never get used to FreeCAD, so I built my own. It turns out Claude is really good at using it. Loböle is a parametric B-Rep CAD built on OpenCASCADE and Vulkan, with sketches, assemblies, drawings, FEM and CAM. The GUI, Python scripts and AI agents all go through the same commands, so an agent can do anything you can in the GUI. The engine, watch and bicycle in the README were each built by Claude writing a script against it.
Observed adoption & comparisons
Source votes: 1 votes (Oct 25, 2026 UTC; cumulative since publication); previous same-scope observation: 1 (Oct 25, 2026 UTC). These observations do not establish demand growth. Recent records to compare: “google/skills” (GitHub Trending, Nov 6, 2026); “mattpocock/skills” (GitHub Trending, Nov 6, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.