text-to-cad — What is it?

earthtojake/text-to-cad is a broad library of agent skills for CAD, robotics, and hardware design, enabling the creation and manipulation of CAD models and robot descriptions through plain language or image requests.

⭐ 7,367 Stars 🍴 869 Forks JavaScript MIT Author: earthtojake
Source: Official README and linked documentation View on GitHub →

Why it matters

This project is being discussed because its unique approach to integrating CAD and robotics with plain language, filling a gap in the market for accessible CAD tools. Its use of JavaScript and integration with various platforms like Codex and Claude Code also differs, making it appealing to a wide range of users.

Source: Official README and linked documentation

Core Features

CAD Skills

A set of skills for generating, inspecting, sourcing, slicing, and handing off CAD and robot-description artifacts from local project files, with STEP as the primary output format.

Source: Official README and linked documentation
CAD Viewer

A skill that provides local browser previews for CAD, G-code, and robot files, enhancing the user's ability to review and inspect designs.

Source: Official README and linked documentation
URDF and SRDF

Skills for writing robot structure files (URDF) and adding MoveIt planning groups, end effectors, poses, and collision rules (SRDF), facilitating robot simulation and planning.

Source: Official README and linked documentation
Implicit CAD

An experimental feature that creates browser-native implicit CAD models using GLSL signed-distance fields and CAD Viewer raymarch rendering, offering a novel approach to CAD modeling.

Source: Official README and linked documentation

Architecture

The project's architecture suggests a modular design with clear separation of concerns. Skills are organized into individual modules, each with specific functionalities like CAD modeling, robot description, and simulation. The use of JavaScript and integration with various platforms like Codex and Claude Code indicates a focus on flexibility and cross-platform compatibility.

Source: Official repository tree and dependency files

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) build123d OpenCascade STEP STL 3MF CAD Skills CAD Viewer URDF and SRDF Implicit CAD text-to-cad Project Core feature Key dependency

Tech Stack

LanguageJavaScriptFrameworkNot enough information.
build123dOpenCascadeSTEPSTL3MFURDFSDFSRDFG-codeBambu Labs
Not enough information.
Source: Official repository tree and dependency files

Quick Start

```bash npx skills install earthtojake/text-to-cad ```
Source: Official README and linked documentation

Use Cases

This project is suitable for designers, engineers, and researchers in the fields of CAD, robotics, and hardware design. It is useful for creating and manipulating CAD models, robot descriptions, and simulation models, and for those who need to integrate these elements into their workflows.

Source: Official README and linked documentation

Strengths & Limitations

Strengths

  • Provides a unique and accessible way to create and manipulate CAD models and robot descriptions.
  • Offers a wide range of skills for various CAD and robotics tasks.
  • Integrates with popular platforms like Codex and Claude Code.

Limitations

  • Some features are experimental and may not be fully stable.
  • The project's documentation could be more broad.
Source: Official README and linked documentation

Latest Release

v0.6.6 was published on 2026-09-21. It adds a unified DFM skill covering sheet metal, CNC, and injection molding, plus an Engineering Drawing skill that generates PDFs from part projections.

Source: github.com/earthtojake/text-to-cad/releases/tag/v0.6.6

Verification and evidence

status: docs-only  |  checked_at: 2026-09-23  |  environment: Docs only. Reviewed the official README, CAD SKILL, requirements, license, and v0.6.6 release.  |  limitations: No skill, Python dependency, OCP, cadgen, or Viewer was installed. No STEP, engineering drawing, DXF, or robotics file was generated, no solid was measured, and no manufacturing check was run locally.  |  observed_output: v0.6.6 is the latest release, dated 2026-09-21. It adds DFM and Engineering Drawing. The current README provides Skills CLI and three plugin installation paths.

Source: github.com/earthtojake/text-to-cad/releases/tag/v0.6.6;https://github…

Comparison

CADAM is a GPLv3 browser application that uses the Anthropic API to generate OpenSCAD, previews it with WASM and Three.js, and exports STL, SCAD, and DXF. text-to-cad is a skill library installed into an agent, centered on Python, build123d, and STEP B-rep, with engineering drawing, DFM, and robotics formats. CADAM fits quick browser-based OpenSCAD prototypes. text-to-cad fits source-controlled STEP output, measurement checks, and robotics delivery workflows.

Source: github.com/Adam-CAD/CADAM/blob/main/README.md;https://github.com/eart…

Verdict

earthtojake/text-to-cad is a project for those looking to integrate CAD and robotics into their workflows. Its innovative approach to using plain language for CAD modeling and its wide range of features make it a tool for designers and engineers.

Source: Official repository

Frequently Asked Questions

What did the documentation review verify for text-to-cad on 2026-09-23?

v0.6.6 is the latest release, dated 2026-09-21. It adds DFM and Engineering Drawing. The current README provides Skills CLI and three plugin installation paths. No skill, Python dependency, OCP, cadgen, or Viewer was installed.

What evidence boundary applies to this text-to-cad review?

The review environment was: Docs only. Reviewed the official README, CAD SKILL, requirements, license, and v0.6.6 release. text-to-cad behavior outside that scope still needs a local check.

Sources and review scope
This review is based on the project's public documentation. Versions, installation commands, and feature boundaries can change upstream; check the cited sources and current release before use. Sources checked on: 2026-09-23 13:55.

Reference materials: README, GitHub API, dependency files