Open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven workflows (Flows).
Adam-CAD/CADAM
Open-source web app that generates parametric OpenSCAD 3D CAD models from natural language prompts and images, running in the browser.
Open-source alternative to:Autodesk Fusion 360
- Stars
- 5,300
- Forks
- 655
- Open issues
- 26
- Last commit
- 6 days ago
What is it?
CADAM is a web application that turns plain-language descriptions and reference images into 3D CAD models. The generated models are written as parametric OpenSCAD code, so the main dimensions show up as adjustable controls. Users can change a value with a slider and see the model update without regenerating it through the AI.
The OpenSCAD engine runs as WebAssembly inside the browser, so the editing and rendering workflow needs no local installation. Finished models can be exported as STL, SCAD, or DXF files. The project also bundles the BOSL, BOSL2, and MCAD OpenSCAD libraries and uses Three.js for the live preview.
The stack is React 19, TypeScript, TanStack Start, and Supabase for auth, storage, and PostgreSQL, with Anthropic Claude as the AI backend. Running it locally requires Node.js, the Supabase CLI, and API keys for the model providers.
Key features
- 01Generates 3D models from natural language and reference images.
- 02Exposes model dimensions as interactive parametric sliders.
- 03Runs OpenSCAD in the browser via WebAssembly.
- 04Exports models as STL, SCAD, or DXF files.
- 05Includes BOSL, BOSL2, and MCAD libraries.
Use cases
- Quickly prototyping mechanical parts such as knobs, brackets, or threaded fittings.
- Creating a parametric starting point that can be tweaked for 3D printing.
- Learning how OpenSCAD code maps to geometry without installing desktop software.
Quick start
- 1
Clone the repository
git clone https://github.com/Adam-CAD/CADAM.git - 2
Enter the project folder
cd CADAM - 3
Install dependencies
npm install - 4
Start Supabase, then run the development server
npx supabase start && npm run dev
Things to know
- Needs Supabase CLI, Node.js 20.19+ or 22.12+, and API keys for AI providers such as Anthropic to generate models.
- Local setup also requires ngrok for webhook development.
- Licensed under GPL-3.0, a copyleft license that requires derivative works to remain open source.
Topics
FAQ
- What is CADAM?
- Open-source web app that generates parametric OpenSCAD 3D CAD models from natural language prompts and images, running in the browser. CADAM is a web application that turns plain-language descriptions and reference images into 3D CAD models. The generated models are written as parametric OpenSCAD code, so the main dimensions show up as adjustable controls. Users can change a value with a slider and see the model update without regenerating it through the AI.
- Is CADAM free to use? What license does it have?
- CADAM is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is CADAM still maintained?
- Actively maintained. The last commit to CADAM was on Oct 15, 2026.
- What can I use CADAM for?
- Quickly prototyping mechanical parts such as knobs, brackets, or threaded fittings. Creating a parametric starting point that can be tweaked for 3D printing. Learning how OpenSCAD code maps to geometry without installing desktop software.
- How do I install CADAM?
- Clone the repository: git clone https://github.com/Adam-CAD/CADAM.git Enter the project folder: cd CADAM Install dependencies: npm install Start Supabase, then run the development server: npx supabase start && npm run dev
- Where can I get CADAM?
- The source code and installation instructions are on GitHub: https://github.com/Adam-CAD/CADAM
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
An open-source Next.js demo that recreates ChatGPT's Intelligent UI, streaming model answers as interactive maps, charts, forms and working tools built on OpenUI.
A Python framework for building LLM-powered applications and agents, with standard interfaces for models, embeddings, vector stores and third-party integrations.
A low-level Python framework for building stateful, long-running agents with durable execution, human-in-the-loop and memory.
Open-source embedding database for AI apps, storing documents and vectors to power semantic, hybrid and full-text search.
TypeScript, Python and Go SDK for browser agents that drives Chrome with natural-language act, observe and extract calls alongside Playwright-style APIs.