text-to-cad: 讓 AI 驅動的參數化 CAD 建模成為現實 / text-to-cad: Bringing AI-Driven Parametric CAD Modeling to Reality
🔎 工具速覽 / AT A GLANCE
| Category | AI-Powered CAD Tooling / AI 驅動 CAD 工具 |
| Pricing | Free (Open Source) / 免費(開源) |
| BestFor | Robotics engineers and product designers using AI coding agents / 使用 AI 程式碼代理的機器人工程師與產品設計師 |
| GitHub Stars | ⭐ 93 |
🚀 引言 / Introduction
text-to-cad 是一個強大的開源框架,旨在填補大型語言模型(LLM)與專業 3D 建模之間的鴻溝。它允許開發者利用 Claude Code 或 Codex 等 AI 代理,透過程式碼生成精確的參數化幾何模型,並提供即時預覽與迭代能力。
text-to-cad is a powerful open-source harness designed to bridge the gap between Large Language Models (LLMs) and professional 3D modeling. It enables developers to leverage AI agents like Claude Code or Codex to generate precise parametric geometry via code, providing real-time preview and iteration capabilities.🛠️ 核心功能 / Key Features
與 Codex 或 Claude Code 等代理集成,生成可版本控制的 CAD 原始碼 / Integration with agents like Codex or Claude Code to generate source-controlled CAD models.
支持 STEP, STL, DXF, GLB 以及機器人描述文件 URDF 等多種格式導出 / Support for exporting various formats including STEP, STL, DXF, GLB, and URDF robot descriptions.
內建本地查看器,無需後端伺服器即可直接檢查生成的幾何形體 / Built-in local viewer for inspecting generated geometry without needing a hosted backend.
透過 `@cad[...]` 引用機制,讓 AI 能對特定幾何部分進行精確的後續修改 / Stable `@cad[...]` references allowing agents to make precise follow-up edits.
支持快照渲染與源文件直接編輯,快速實現「生成-審查-修改」的閉環 / Rapid iteration loop with snapshot rendering and source-first editing for quick verification.
💡 技術亮點 / Tech Highlights
不同於一般的 AI 點雲生成,它基於 build123d 等參數化庫,確保模型具有工程級的精確度 / Unlike general AI point-cloud generation, it leverages parametric libraries like build123d to ensure engineering-grade precision.
內建 URDF 技能,使其不僅能設計單個零件,還能構建完整的機器人描述模型 / Bundled URDF skills enable the creation of full robot description models beyond single part design.
將 CAD 建模轉化為程式碼開發流程,完美適配 Git 版本管理與 AI 協作 / Transforms CAD modeling into a code-development workflow, perfectly fitting Git version control and AI collaboration.
📦 快速上手 / Quick Start
安裝 Python 3.11+ 並配置 build123d 與 OpenCascade 環境 / Install Python 3.11+ and configure build123d and OpenCascade environments.
部署本地 Viewer(基於 React 與 Vite)以實現即時可視化 / Deploy the local viewer (based on React and Vite) for real-time visualization.
配置你的 AI Coding Agent(如 Claude Code),使用內建的 CAD/URDF Skill 指引生成模型 / Configure your AI Coding Agent (e.g., Claude Code) and use bundled CAD/URDF skills to generate models.
準備好試試 text-to-cad: 讓 AI 驅動的參數化 CAD 建模成為現實 / text-to-cad: Bringing AI-Driven Parametric CAD Modeling to Reality 了嗎?
Ready to try text-to-cad: 讓 AI 驅動的參數化 CAD 建模成為現實 / text-to-cad: Bringing AI-Driven Parametric CAD Modeling to Reality?
前往 GitHub 頁面 →
留言
張貼留言