earthtojake / text-to-cad

2026-04-22 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Software Development & Engineering · Depth: Intermediate, medium

Summary

CAD Skills, a library by earthtojake, provides agent capabilities for generating, inspecting, sourcing, slicing, and managing CAD and robot-description artifacts from local project files. It supports a wide array of formats including STEP, STL, 3MF, GLB, DXF, URDF, SRDF, and SDF. Key functionalities include creating and editing CAD models from text or image prompts, local browser previews via CAD Viewer, and sourcing off-the-shelf STEP parts. The library also facilitates generating 2D DXF drawings, writing robot structure files (URDF, SRDF), and creating simulator models (SDF). For manufacturing, it offers G-code slicing for FDM printers, pre-upload checks for SendCutSend, and direct print job management for Bambu Lab. Installation is available through the Skills CLI or as plugins for Codex and Claude Code. Benchmarks showcase its ability to generate complex designs such as a planetary gear stage and a spiral staircase.

Key takeaway

For AI Engineers or Robotics Engineers integrating generative AI into hardware design, CAD Skills offers a robust framework to automate complex tasks. You can streamline workflows by enabling agents to generate CAD models from natural language, create robot description files, and prepare designs for fabrication. This library allows you to accelerate prototyping cycles and reduce manual intervention in design-to-manufacturing processes, enhancing efficiency across your development pipeline.

Key insights

CAD Skills provides a comprehensive agent-based toolkit for automated design, fabrication, and simulation workflows in hardware and robotics.

Principles

• Agent-driven design automation.
• Broad CAD/robotics file support.
• Integrated fabrication workflows.

Method

Install CAD Skills via `npx skills install earthtojake/text-to-cad` or as a plugin for Codex/Claude Code. Agents then access focused workflows for CAD, fabrication, and robot description files.

In practice

• Generate CAD models from text.
• Slice mesh files to G-code.
• Find off-the-shelf STEP parts.

Topics

• CAD Automation
• Robotics Design
• Generative Design
• Agent-based Systems
• 3D Printing
• STEP Files

Code references

• earthtojake/text-to-cad

Best for: Machine Learning Engineer, Computer Vision Engineer, Robotics Engineer, AI Engineer, Software Engineer

Related on AIssential

• mattpocock / skills — Agent skills can automate and enhance various stages of the software development lifecycle.
• IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing — IterCAD enables closed-loop, iterative CAD generation and editing by integrating multi-modal feedback and self-correction.
• TO-Agents: A Multi-Agent AI Pipeline for Preference-Guided Topology Optimization — Multi-agent AI can autonomously translate qualitative design intent into optimized structures through iterative visual and historical feedback.
• From Text to CAD: The Future of Manufacturing — How AI is Revolutionising CAD Design — AI-driven CAD can generate 3D models and intelligent assembly/disassembly sequences from natural language prompts.
• ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation — ArtisanCAD distills expert CAD procedures into reusable skills via CAD-IR to generate production-ready B-Rep models from ambiguous prompts.
• AI is a Tool for Designers, Not a Substitute for Design — AI transforms design by automating low-level tasks, enabling designers to focus on strategic and empathetic work.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.