DigestAI news desk

Cut through the AI noise.

Robotics & Physical AI3 min read

Open-source tool uses AI to generate LEGO builds with 2,175 pieces

An open-source project called LDraw Nova lets AI models like GPT-6 Astra and Claude Opus 5.5 design LEGO builds by writing Python programs that output CAD files. Developer Carlos Antelo demonstrated a 2,175-piece Sakura Garden model created by Claude Opus 5.5 from a prompt asking for the most beautiful design. The tool avoids manual brick placement by using AI to generate and refine models…

1 source

Key points

  • LDraw Nova uses AI models like Claude Opus 5.5 to generate LEGO builds with up to 2,175 pieces via Python programs
  • Token costs for generating large builds with Astra are estimated at $5, per developer Carlos Antelo
  • Project lacks physics checks for stability and collisions, unlike Carnegie Mellon’s BrickGPT tool

LDraw Nova runs as a Docker web app and supports multiple AI providers, including OpenAI and Anthropic. Token costs for generating large builds are estimated at around $5 for Astra. The project differs from Carnegie Mellon’s BrickGPT, which validates designs for physical stability. Antelo plans to add minifigures, Technic parts, and VR support for Meta Quest 3, though the latter has performance issues. The tool could bridge AI-generated designs and physical production via 3D printing integrations like Kiln and OctoEverywhere.

Model pages: GPT-6 Astra → · Claude Opus 5.5 →

The story so far

3 episodes →
  1. Open-source tool uses AI to generate LEGO builds with 2,175 piecesthis story
Full story from Tom's Hardware · by Shane DowningOpen source ↗

Open-source tool designs LEGO builds with more than 2,000 real pieces

Tom's Hardware · 4 October 2026

Loading the full article…

This text was published by Tom's Hardware and written by Shane Downing. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Robotics & Physical AI

All →

Related stories