3D & graphics
3D and graphics turn text prompts or reference images into 3D models and CAD geometry, and they also drive existing tools. Text-to-cad generates physical product designs from descriptions, while img2threejs rebuilds an object from a photo as a code-only Three.js model.
293 agents · most starred first
Top 100 of 293
Design physical products with AI
Open-source 3D architecture software for AECO, scan-to-BIM. Agent-friendly, browser-first, MCP, CLI.
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
CADAM is the open source text-to-CAD web application
Professional Blender 5.3 workflows as Agent Skills for Claude Code, Codex, Gemini CLI, Copilot and Cursor: modeling, UVs, PBR, baking, rigging, animation, export and QA.
DSH × Blender 直连插件 v3.0.6:15 个模型工具让 AI 驱动 GUI Blender(视口 / 自定义视角 / 无头 worker / 作业层 / 事务回滚 / 配方库),34 family / 228 op 契约层;npm 安装 + addon zip,GUI 优先、无头备用;dsh-TUI 选中 chip / @ 提及 / /blender,随包建模 skill,支持 WSL / Windows / macOS。
Agent skill for creative 3D visualization: turn an idea into a Three.js/Blender scene worth exploring. Claude Code + Codex plugin, 223 recipes, 440 knowledge records, 22 proved kits, 37 runnable studies.
AI-first 3D & AR SDK for Android (Jetpack Compose + Filament), Apple (SwiftUI + RealityKit) and the web. Opens glTF/GLB, 3MF, STL, OBJ and PLY on Android and USDZ on Apple, at real size in AR. An assistant reads llms.txt and writes code that compiles first try; also an MCP server and a ChatGPT/Codex plugin.
Bridge between LLM-Agent and Cadence Virtuoso. A new infrastructure for Agentic Analog and Mixed-Signal Design.
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds
Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.
Use AI Agents directly in Blender.
Design workspace for programmable 3D. Nova builds assets and worlds as editable, versioned programs: parametric, articulated and simulation-ready, compiled to CAD tools, 3D applications and robotics simulators.
Playbook and Three.js code kit for detailed dioramas: classic pixel art, stroked toon or pixel + stroke; two intake gates for look and model sourcing; free orbit, palette snap and ink; animated toy-scale cast; per-entity frame QA.
AI-powered assistant workbench for FreeCAD — generate 3D models from natural language
Agent tooling for generative LEGO models building, built with Astra and Opus 5.5, powered by Jev
worlds via code, from fable 5.1
MapStage: a narrative map stage for historical videos. MapLibre engine + agent skill, antique parchment look, routes, place names, seek(t) frame capture.
Agentic CAD for 3D printing
Desktop app for designing parametric 3D models in CadQuery together with the coding agent of your choice
Agentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with optional per-part materials and articulation.
Turn any video into a Mixamo-rig animation - GVHMR estimator, spec-driven retarget, FK apply in Blender via MCP. Works with any Mixamo character; built to be operated end-to-end by an AI agent.
Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
Open-source, local-first 3D parametric CAD that runs in the browser for people and permissioned typed agents, powered by OpenCascade WASM.
全息闪卡通用 Agent Skill:多模态模型都能用,不挑宿主——一句话生成可拖转、会流光、带层次景深的 3D 闪卡网页,附可编辑 Blender 工程
Photoreal Blender scenes from a one-paragraph brief, built by AI agents: image→3D props on fal, scripted layout, lighting, camera and grade.
Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight
LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction
The AI-powered 3D CAD IDE — edit code, visualize in 3D, and reshape your designs with natural language.
An Agent Skill for building interactive, self-assembling 3D architecture with Three.js. 一个用 Three.js 生成可交互、可动态建造 3D 建筑的 Agent Skill。
Houdini Agent - DCC Asset Manager with AI capabilities
Character Animation Creator Skill for Codex and GPT Web Agent — generates game-ready animations and sprites from reference images or text prompts
Curated Blender + Seedance workflows for AI filmmaking: previs, camera control, Blender MCP, reference video, and agent-guided use cases.
Build and revise procedural 3D assets with your coding agent. Local MCP server, CLI and TypeScript engine with rendered review, editable source and GLB export.
[IJCV 2024] InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions
The AI-powered 3D CAD IDE — edit code, visualize in 3D, and reshape your designs with natural language.
Give your AI agent a 3D body: rigged GLB avatars from text or a photo, an LLM brain, a Solana wallet, a one-tag embed.
Bambu Lab AI (Bambu Studio AI): agent skill for 3D printing on Bambu Lab. Finds models on MakerWorld & Printables, generates or designs them in CAD, checks printability, hands them to Bambu Studio and reads printer/AMS status. For Claude Code, Codex, Cursor, Gemini CLI and any SKILL.md agent. Featured in 我的拓竹 Skill 大赏.
Maintenance mode: bug fixes only, no new features. Lighter option, no app to install: forgent3d/forgent3d-skills
AI-powered 3D suite built on Blender, with an integrated agent, moodboard, generation tools and layer-based painting
Text-To-VRMA — VRM特化型Text-To-Motionツール
HiCAD,一款AI驱动的CAD建模平台
Using AI to generate 3D models
Amazon Sumerian Hosts (Hosts) is an experimental open source project that aims to make it easy to create interactive animated 3D characters for Babylon.js, three.js, and other web 3D frameworks. It leverages AWS services including Amazon Polly (text-to-speech) and Amazon Lex (chatbot).
Clarvis - 3D Printing Made Easy
An agent-native CAD SDK for language models to create, inspect, and reconstruct complex, editable 3D models.
An open toolkit that equips a coding agent to design buildings as executable CAD code. It supplies skills, Python modelling tools, a six-agent team definition and summaries of construction manuals.
Open-source home design and floor plan editor in Rust (a Sweet Home 3D alternative) with a built-in MCP server: your AI agent draws walls, furnishes rooms, checks lighting and ergonomics, and renders photos — live, on your own machine.
从 Vibe Coding 到 Vibe World:AI原生的可编程三维世界,面向元宇宙、Science、世界模型的开源底座
Loopcut: an AI agent that works inside Blender. A fork of Blender (GPL).
Persistent, editable objects for AI agents: researched part by part, honest about what is known, and carried into worlds, film, web, games, CAD and print.
Loopcut: an AI agent that works inside Blender. A fork of Blender (GPL).
CAD in TypeScript with exact solids (B-Rep). AI agents can write parts with it and check them on OpenCascade.
Tame3D research framework: evidence-grounded multi-agent 3D reasoning with scene-level conformal uncertainty alignment
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark
Blender Add-on: OpenAI Bridge (Bridge between Blender and OpenAI API)
A Claude Code-powered 3D modeling agent environment for creating 3D printable designs using OpenSCAD.
[ICLR 2025] Official repo of "Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs"
DeepSeek Harness Desktop 插件,让 AI Agent 用自然语言构建、检查和维护可编辑的 SideFX Houdini 工程,支持程序化建模、HDA、场景诊断与渲染。 | A DeepSeek Harness Desktop plugin that lets AI agents build, inspect, and maintain editable SideFX Houdini projects with natural language, including procedural modeling, HDAs, scene diagnostics, and rendering.
Free, open-source Blender AI plugin for the tools you already use. Codex and Claude Code installers, local MCP tools, editable .blend files and Python source.
AI agent operating system for Blender 5.2: bpy knowledge base, AGENT_OK execution contract, 3D-print production gate, worked keyboard and desktop-robot builds.
Implementation of Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework
An agent-native CAD SDK for language models to create, inspect, and reconstruct complex, editable 3D models.
First 3D AI Agent Platform, allowing users to recreate and display Bynce Agent. Using 3D Motion Capture & MMD Model Technology to interact with Bynce.
[ARCHIVED] Superseded by XenolithGraph — modern TypeScript/WebGL successor with React/Vue adapters and MCP for AI agents. See: github.com/XenolithEngine/xenolith-graph
Create and refine Blender product scenes in DSH: editable recipes, model imports, real previews, saved revisions and PNG/MP4 delivery.
Turn a reference video, image or idea into an editable procedural Blender node system: a coding-agent skill with a tested Geometry/Shader/compositor node-group library
Benchmarking Agentic Procedural 3D Modeling Via Code
Local-first raster-to-vector desktop app. PNG/JPEG/BMP to SVG/EPS/DXF/PDF/PNG. No account, no credits, no subscription — offline by default, with one clearly-labeled opt-in exception (bring-your-own-key AI Enhance).
In-process Revit AI agent with dynamic C# code execution, multi-provider LLM support, and a guardrail system for safe BIM automation.
CAD/CAE Copilot — an AI-native CAD/CAE/CAX workbench for AI agents. Text-to-CAD, text-to-CAE, real build123d/OpenCASCADE geometry, editable parameters, stable topology pointers, deterministic critique, and MCP server tools.
ZW3D CAD automation bridge and iterative drafting agent for mechanical drawing generation.
AI agent skills for Meshy AI 3D generation platform
CAD 自动化设计技能包 — 让 AI Agent 真正学会用 AutoCAD
Automated optical design agent skill for Ansys Zemax OpticStudio via ZOS-API — AI-driven requirements parsing, lens modeling, staged optimization, and design reporting.
Create GTA-style 3D models and scenes with your AI and Blender, using models and textures from your game. Early alpha.
Build interactive 3D worlds with high-quality assets from Thrixel and your AI agent of choice.
🤖 Intelligent AI-powered PCB design automation tool using machine learning for component placement, routing optimization, and signal integrity analysis. Supports KiCad, Altium Designer, and Eagle CAD integration.
A simple AI agent that turns prompts into articulated 3D objects.
ANIMAT is the first AI platform to integrate MMD and facial tracking for dynamic 3D Model, enabling realistic customization and upgrade of AgentAI.
SolidWorks 自动化设计技能包 — 让 AI Agent 真正学会用 SolidWorks
A multi-agent KiCad PCB design workspace: 9 skills driving a Phase 0-5 pipeline from topology discussion to Gerber shipout. Noncommercial.
Agent skill and toolkit for reconstructing Gaussian splats as editable Blender Geometry Nodes meshes and Shader Node materials.
Agent skill (Claude Code / Codex) for building an MMD-ready 3D character from one illustration: Tripo generation, component texturing, rigging, expressions, Houdini cloth, rendering
The agentic node editor for live visual effects
DSH skill v1.0 · Blender 建模与装配流程:多 Agent 分工范式(冻结 spec/写作用域/接口表)、参考图形体还原、六条必踩的坑、十道数值门装配审计;23 条配方;配套插件 dsh-blender-plugin v1.0.0
鲸语:自然语言编排 Live2D 动作,支持 OpenAI/DSH、网页/VTube Studio、预设保存与 GIF/MP4 导出。
AI Image to 3D Mesh Rigging and Roblox Asset API Cost Tracker 2026
Custom 3D TShirt designer. Design your own T-shirts from scratch, customize its colors, logo etc. Made using ThreeJS, ReactJS and Custom Hooks.
AI-Powered 3D-model customization app (DALL-E 2) on React, Framer Motion, ThreeJS and TailwindCSS
modular, service-oriented CAD
AI CAD 建模 Agent:一句话需求进来,调研、提问、出 BOM,逐件完成真实 CAD 建模并导出装配 STEP(参数化 BRep,不是图片或网格);几何与碰撞检查不过关就不交付。Windows 封闭 Beta。An AI CAD modeling agent: real parametric geometry from a one-line brief, gated by geometry and interference checks.
担心AI在SW上面画的好看,实际组装又是另外一个事故?有这个项目在!材料、力学、规范三重校核,凭可追溯证据交付工图。让AI画的图真正能进入工程世界,而不是只是一个漂亮的玩具
Agent skill (Claude Code) that turns one character illustration into a half-body Live2D avatar for VTube Studio. 一张立绘做出 VTube Studio 半身 Live2D 皮套。
🧊 300+ source-backed GPT-6 Astra 3D prompts with WebP/WebM results, X sources, and creator attribution—for Blender, Three.js, games, CAD, and agents.
NVIDIA Omniverse NuRec agent skills automate neural reconstruction for autonomous vehicle and robotics simulation, running the reconstruction and rendering workflow end to end.
SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation
The mechanical CAD generation agent capable for recording and learning your own design skill and product features, it can grow like your own mechanical design specialist