text-to-cad: AI Agent Skills for CAD, CAE, and CAM Workflows

Summary

text-to-cad is a comprehensive Python library developed by earthtojake, providing a rich set of agent skills for Computer-Aided Design (CAD), Computer-Aided Engineering (CAE), and Computer-Aided Manufacturing (CAM). It enables AI agents to generate, inspect, source, slice, and manage CAD and robot-description artifacts, streamlining complex engineering processes.

Use at your own risk

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.

Introduction

text-to-cad, developed by earthtojake, is an innovative Python library designed to empower AI agents with a wide array of skills for CAD, CAE, and CAM workflows. This project simplifies the creation, manipulation, and analysis of mechanical designs and robot descriptions, making advanced engineering tasks more accessible and automated. It acts as a bridge between natural language instructions and complex engineering software, facilitating rapid prototyping and design iterations.

Why Use and Key Benefits

The primary benefit of text-to-cad lies in its ability to automate and accelerate various stages of mechanical design and manufacturing. By providing specialized skills, it allows AI agents to handle tasks such as generating CAD models from text descriptions, creating detailed engineering drawings, finding off-the-shelf parts, and even slicing models for 3D printing. It supports critical industry standards like STEP, STL, 3MF, URDF, SRDF, and SDF, ensuring broad compatibility. The library's modular design, with skills for CAD creation, robot description, simulation, and fabrication checks (DfAM, DFM), makes it a versatile tool for engineers and developers looking to integrate AI into their design pipelines. This significantly reduces manual effort and potential errors in complex engineering projects.

Installation

Installing text-to-cad is straightforward, with options for both the Skills CLI and provider-native plugins. The recommended method is via the Skills CLI:

npx skills add earthtojake/text-to-cad

This command installs individual skills directly for supported agents and can also be used to update existing installations. For provider-native plugin installs, options are available for Codex, Claude Code, and Grok Build. For example, with Codex (version 0.142.0 or newer):

codex plugin marketplace add earthtojake/text-to-cad
codex plugin add cad@text-to-cad

Refer to the official documentation for detailed instructions on other plugin installations and local development.

Examples

text-to-cad offers a diverse set of capabilities through its specialized skills. For instance, the CAD skill can create and edit CAD models from plain-language requests, outputting in formats like STEP, STL, and 3MF. The URDF skill enables the writing of robot structure files complete with links, joints, and meshes, while the SRDF skill adds MoveIt planning groups for advanced robotics. For manufacturing, skills like G-code can slice mesh files into validated FDM .gcode, and DfAM Check assesses printability. The project also includes a CAD Viewer for local browser previews of designs, and skills for generating engineering drawings or finding standard parts.