Built an agent loop where the LLM writes Python code to generate articulated 3D CAD models. You can pin a part to edit it
Summary
Built an agent loop where an LLM writes Python code to generate articulated 3D CAD models, with the ability to pin a part for editing.
Similar Articles
A tool I built to generate 3D objects with functional, articulated parts. It's on github, and is mostly LLM-agnostic.
A developer built a pipeline that uses an LLM as a structured code compiler to generate Blender Python code, producing 3D objects with functional, articulated parts instead of monolithic meshes. The tool is open-source and LLM-agnostic.
Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling
Presents Embodied CAD, a closed-loop framework that grounds LLM agents in a CAD execution environment for parametric B-Rep assembly modeling, using solver feedback for planning and refinement.
Built an agent workstation where the environment does the structural reasoning so the LLM doesn't have to
Atlarix is a desktop environment that pre-parses codebases into a node/edge graph, allowing coding agents to navigate architecture via queries instead of reading raw text, which improves performance of smaller local models.
built an agent where the LLM is structurally forbidden from writing the final output. looking for feedback + people willing to break it
The author describes an AI agent designed to reproduce production Python crashes using LangGraph, featuring a unique architecture where the LLM plans actions but deterministic Python functions generate the final test code to ensure reliability.
Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
This paper proposes an agentic LLM framework for automated structural analysis of 3D frame systems from natural language inputs, achieving 90% accuracy on ten representative 3D frames through a multi-agent pipeline.