earthtojake/text-to-cad: AI tool review & score

Score8.0

Popularity1.0

Risklow

TierGold

Score breakdown

Usefulness8.0

Novelty8.0

Momentum8.0

Maturity6.3

Open-source/build8.4

Evidence7.2

Workflow potential9.1

Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for mechanical engineers, hardware designers, robotics engineers, fabrication engineers, AI-curious readers, technical writers, and any developer building a CAD/robotics/hardware design workflow with an AI agent -- and who can pair text-to-cad with an Anthropic / OpenAI / DeepSeek / Xiaomi Mimo / Claude / GPT API key for the model surface, an SKILL.md-compatible agent (Claude Code, Codex, C

Who should use it

Mechanical engineers, hardware designers, robotics engineers, fabrication engineers, AI-curious readers, technical writers, and any developer building a CAD/robotics/hardware design workflow with an AI agent -- and who can pair text-to-cad with an Anthropic / OpenAI / DeepSeek / Xiaomi Mimo / Claude / GPT API key for the model surface, an SKILL.md-compatible agent (Claude Code, Codex, Cursor, OpenCode, etc.) for the install surface, a real browser for the local 3D viewer surface, build123d for the Python CAD source surface, the cadpy-step-artifact CLI for the artifact surface, and an FDM 3D printer + Bambu Labs printer for the G-code + Bambu Labs output surfaceEngineering teams that want a STEP-first CAD artifact pipeline for AI agents -- STEP is the primary CAD artifact, STL/3MF/GLB are secondary export workflows that branch from a STEP-first process; the cadpy package generates STEP files via build123d, validates them, extracts topology, hashes sources, and the AssemblyHelper wraps native build123d labels + joints + compoundsEngineering teams that want to bridge AI agents to physical fabrication -- the G-code skill (FDM slicing via real slicer CLIs) + Bambu Labs skill (dry-run + validated .gcode upload to Bambu Lab printers) form the bridge from CAD output to physical 3D-printed object; the SendCutSend skill (DXF + STEP file check before upload) bridges to 2D fabrication servicesEngineering teams that want a CAD Viewer local browser primitive -- the viewer/ directory ships a real local browser 3D viewer with `npm run agent:start` (port selection + compatible-server reuse + directory activation + `?dir=` query parameter); the agent returns review links for the consumer's .step / .stp / .glb / .stl / .3mf / .dxf / .urdf / .srdf / .sdf filesRobotics teams that want AI agents to generate URDF / SRDF / SDF robot files -- the urdf skill writes robot structure files with links + joints + limits + inertials + meshes; the srdf skill adds MoveIt planning groups + end effectors + poses + collision rules; the sdf skill creates simulator models and worlds with frames + physics + sensors + lights; together they bridge to robotics simulation (Gazebo, MuJoCo, etc.)

Who should skip it

Consider earthtojake/text-to-cad lower priority if you already have a working solution in this category.

About this signal

earthtojake/text-to-cad is tracked by RepoRadar as a cad / robotics / hardware design in the AI CAD / Robotics / Hardware Design section. It was first seen on 2026-07-06 and last updated on 2026-07-06. The current verdict is 'try now' with a Gold tier and easy setup difficulty. earthtojake/text-to-cad leads on workflow potential (9.1) and setup ease (8.8); its lowest signal is maturity (6.3), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned earthtojake/text-to-cad a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

The 7; 704* / 90 MB repo is at active maintenance but the maintainer is a single individual (earthtojake) -- treat the first evaluation cycle as a smoke test (install via `npx skills install earthtojake/text-to-cad` + generate a simple CAD bracket + confirm the STEP file is valid + open the local 3D viewer + confirm the G-code slicing works) before relying on the 11 skills in production; the cadpy package wraps build123d for source-level CAD generation -- the consumer SHOULD be familiar with build123d's Python API for advanced use; the cadpy-step-artifact CLI is the canonical entry point for STEP artifact generation but the consumer SHOULD validate the STEP output against the consumer's CAD interchange standards.

Evidence links

github.com

Closest alternatives / related signals

open-sourcemittext-to-cadearthtojakecad-skill-librarycad-robotics-hardware-design11-installable-skills11-skills