A collection of agent skills for CAD, robotics and hardware design

CADAM is the open source text-to-CAD web application

Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD

Using AI to generate 3D models

This project uses a Large Language Model (LLM) with Retrieval-Augmented Generation (RAG) to convert natural language descriptions into executable FreeCAD Python scripts for 3D modeling.

[AAAI 2026] Official Implementation of NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling

Contract-driven, agentic system for deterministic CAD generation from natural language using headless CAD

Text to CAD using LLMs and BadCAD

An open source harness for generating CAD models [forked of https://github.com/earthtojake/text-to-cad]

Generative 3D design for gaming using Fusion 360 scripting, simulated in Godot with Bayesian optimization for AI design tuning (scikit-optimize)

🚀 Convert natural language to real CAD artifacts with Text2CAD, an agent-driven system for deterministic and validated engineering workflows.

AI-native CAD agent converting natural-language requests into validated OpenSCAD artifacts with automated geometry repair and manufacturing validation.

Generating STEP (ISO 10303) CAD files from natural language using fine-tuned LLMs — reimplementation of STEP-LLM with SFT + GRPO reinforcement learning

LLM-based CAD automation tool using KLayout API

The KittyCAD modeling app.

C# SDK for the Zoo API -- text-to-CAD generation and generated part retrieval