#5858th of 80 in Agent platformsFor image, video and design, 3d
amagine3d
LLM agent that writes editable build123d CAD for printable enclosures
- Stars
- 6.3k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Language
- Python
1 on 18 Aug 20266,282 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Amagine3D takes a product description, reference images and key dimensions, then has an LLM agent write build123d Python source for a multipart enclosure around internal components. It checks wall thickness, interference, plate fit and motion clearances on the generated geometry, and exports STEP, STL and 3MF. A React/Vite workbench previews, measures and edits parameters, then rebuilds from source.
Who it is for: Hardware makers wanting LLM-generated, editable CAD for 3D-printed enclosures
Strengths
- Outputs editable build123d source plus real STEP, STL and 3MF with color regions
- Agent checks measured wall thickness, interference and motion clearance on generated BRep geometry
- Candidates are committed only after checks pass, so the last accepted version is kept
- Each session runs in an isolated workspace with secret-like env variables stripped
Weaknesses
- Scope is limited to printable hardware enclosures and related structures
- Requires an OpenAI Responses-compatible API key or gateway; no local model path described
- Visual review needs a vision-capable model, otherwise review stays incomplete
- Tested only in desktop Chrome and Edge; no Docker setup or tagged release
What it needs
- no GPU
- Needs Node.js 22.19.0+, Python 3.10-3.13, OpenAI Responses-compatible API, Tavily (optional)
- Models: OpenAI Responses-compatible models (example: openai/gpt-5.5)
- port 6160
Quick answers
Is amagine3d open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does amagine3d need a GPU?
No, it runs without one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |