@GitTrend0x: Blender 里直接喊话生成 3D 模型 https://github.com/Adam-CAD/CADAM 这就是 CADAM,把 ChatGPT / Claude / Gemini 直接变成 Blender 内置 CAD 智能助手的…
Summary
CADAM 是一个开源工具,通过自然语言在 Blender 中利用 ChatGPT、Claude 或 Gemini 生成 3D CAD 模型,支持参数化控制和多种导出格式。
View Cached Full Text
Cached at: 05/24/26, 10:27 AM
Blender 里直接喊话生成 3D 模型
https://t.co/MfA4T7BbhE
这就是 CADAM,把 ChatGPT / Claude / Gemini 直接变成 Blender 内置 CAD 智能助手的神器! https://t.co/Iu1ridhU8W
Adam-CAD/CADAM
Source: https://github.com/Adam-CAD/CADAM
⛮ The Open Source Text to CAD Web App ⛮
✨ Features
- 🤖 AI-Powered Generation - Transform natural language and images into 3D models
- 🎛️ Parametric Controls - Interactive sliders for instant dimension adjustments
- 📦 Multiple Export Formats - Export as .STL, .SCAD, or .DXF files
- 🌐 Browser-Based - Runs entirely in your browser using WebAssembly
- 📚 Library Support - Includes BOSL, BOSL2, and MCAD libraries
🎯 Key Capabilities
| Feature | Description |
|---|---|
| Natural Language Input | Describe your 3D model in plain English |
| Image References | Upload images to guide model generation |
| Real-time Preview | See your model update instantly with Three.js |
| Parameter Extraction | Automatically identifies adjustable dimensions |
| Smart Updates | Efficient parameter changes without AI re-generation |
| Custom Fonts | Built-in Geist font support for text in models |
📸 Demo
🎬 Try it live: https://adam.new/cadam
📺 Screenshots
More screenshots
🚀 Quick Start
# Clone the repository
git clone https://github.com/Adam-CAD/CADAM.git
cd CADAM
# Install dependencies
npm install
# Start Supabase
npx supabase start
npx supabase functions serve --no-verify-jwt
# Start the development server
npm run dev
📋 Prerequisites
- Node.js ^20.19.0 or >=22.12.0, with npm 10+
- Supabase CLI
- ngrok (for local webhook development)
🔧 Setting Up Environment Variables
1. Frontend Environment:
- Copy
.env.local.templateto.env.local - Update all required keys in
.env.local:VITE_SUPABASE_ANON_KEY="<Test Anon Key>" VITE_SUPABASE_URL='http://127.0.0.1:54321'
2. Server Environment:
- Add server-side keys to
.env.local, including:ANTHROPIC_API_KEY="<Test Anthropic API Key>" OPENROUTER_API_KEY="<Test OpenRouter API Key>" OPENAI_API_KEY="<Test OpenAI API Key>" GOOGLE_API_KEY="<Test Google API Key>" FAL_KEY="<Test FAL API Key>" SUPABASE_SERVICE_ROLE_KEY="<Test Service Role Key>" BILLING_SERVICE_URL="<Test Billing Service URL>" BILLING_SERVICE_KEY="<Test Billing Service Key>" ENVIRONMENT="local" ADAM_URL="<Adam URL or dev URL>" # Checkout and portal redirect target WEBHOOK_BASE_URL="<Public TanStack App URL>" # Your app URL for /cadam/api callbacks NGROK_URL="<NGROK URL>" # Optional local Supabase Storage tunnel for provider-readable signed URLs
🌐 Setting Up ngrok for Local Development
CADAM uses public URLs for provider callbacks and local signed storage URLs:
-
Install ngrok if you haven’t already:
npm install -g ngrok # or brew install ngrok -
Start an ngrok tunnel pointing to your TanStack Start dev server:
ngrok http 3000 -
Copy the generated ngrok URL (e.g., https://xxxx-xx-xx-xxx-xx.ngrok.io) and add it to your
.env.localfile:WEBHOOK_BASE_URL="https://xxxx-xx-xx-xxx-xx.ngrok.io" -
If a provider must fetch local Supabase Storage signed URLs, run a second tunnel to Supabase and set
NGROK_URLto that URL. -
Ensure
ENVIRONMENT="local"is set in the same file.
💻 Development Workflow
Install Dependencies
npm i
Start Supabase Services
npx supabase start
npm run dev
🛠️ Built With
- Frontend: React 19 + TypeScript + TanStack Start + Vite
- 3D Rendering: Three.js + React Three Fiber
- CAD Engine: OpenSCAD WebAssembly
- Backend: TanStack Start server routes + Supabase PostgreSQL/Auth/Storage
- AI: Anthropic Claude API
- Styling: Tailwind CSS + shadcn/ui
- Libraries: BOSL, BOSL2, MCAD
🤝 Contributing
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also open an issue.
See the CONTRIBUTING.md for instructions and code of conduct.
🙏 Credits
This app wouldn’t be possible without the work of:
📄 License
This distribution is licensed under the GNU General Public License v3.0 (GPLv3). See LICENSE.
Components and attributions:
- Portions of this project are derived from
openscad-web-gui(GPLv3). - This distribution includes unmodified binaries from OpenSCAD WASM under
GPL v2 or later; distributed here under GPLv3 as part of the combined work.
See
src/vendor/openscad-wasm/SOURCE-OFFER.txt.
🌟 Star History
Live chart by RepoStars — click for the interactive version.
⭐ If you find CADAM useful, please consider giving it a star!
Made with 💙 for the 3D printing and CAD community
GitTrend (@GitTrend0x): 用 Seedance2-skill 创建高质量视频,看到都拍手叫好!
https://t.co/LsvfKADMSQ 电影级提示词 + 自动生成外挂。专为字节 Seedance 2.0(Jimeng)视频模型打造的提示词技能,教 AI 怎么写带镜头语言、结构、@引用素材的高质量 prompt。 直接塞进 Cursor / Claude Code 等 AI
Similar Articles
@QingQ77: Open-source framework enables Codex, Claude Code and other coding agents to generate CAD models from text descriptions, export to STEP/STL/3MF and more. https://github.com/earthtojake/text-to-cad… text-to-…
The open-source framework text-to-cad enables Codex, Claude Code and other coding agents to generate CAD models from text descriptions, supporting export to STEP, STL, 3MF, DXF, GLB, URDF and more. It comes with three built-in Skills (CAD, URDF, and Robot Motion) and runs locally without requiring a backend.
@oragnes: Wow, just dug up this amazing tool map3d on GitHub! Based on OpenStreetMap, you select an area on the web page, and it automatically fetches real building and road data, rendering a 3D city model with heights in one click! The craziest part is it can directly export GLB files for use in Blender or game engines…
Introduces two open-source tools on GitHub: map3d, which automatically generates 3D city models from OpenStreetMap and exports GLB files; and Voice-Pro, a local tool integrating video download, voice separation, subtitle recognition, translation, voice cloning dubbing, and video synthesis.
@LufzzLiz: Wow, this is amazing. A 3D biological structure page generated by GPT Image 2 + Gemini 3.1 Pro is great for AI education. I'm going to replicate it~
The user shares an impressive example of a 3D biological structure page generated using GPT Image 2 and Gemini 3.1 Pro, noting its potential for AI education and expressing intent to replicate it.
GenCAD
GenCAD introduces an image-conditional model that generates full parametric CAD command histories using transformers and diffusion priors, enabling precise and modifiable 3D modeling from images.
@VincentLogic: Open-source alternative to Claude Code is here! OpenClaude is a real game-changer. I always felt that the official Claude Code was too limited by only using its own model. This open-source version breaks through that barrier: supports any model like DeepSeek, GPT-4, GLM, etc. Usage is exactly the same as the original...
Introduces OpenClaude, an open-source alternative that supports multiple models like DeepSeek, GPT-4, etc., and uses Agent Routing to intelligently assign tasks, saving money and improving efficiency.