[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-77241":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},77241,"articraft","mattzh72\u002Farticraft","mattzh72","An Agentic System for Scalable Articulated 3D Asset Generation",null,"https:\u002F\u002Fgithub.com\u002Fmattzh72\u002Farticraft","Python",1263,160,11,3,0,27,134,513,81,19.62,false,"main","2026-06-12 02:03:42","# Articraft\n\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg)](LICENSE)\n[![Python versions](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.11%20%7C%203.12-blue)](https:\u002F\u002Fwww.python.org\u002F)\n[![CI](https:\u002F\u002Fgithub.com\u002Fmattzh72\u002Farticraft\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmattzh72\u002Farticraft\u002Factions\u002Fworkflows\u002Fci.yml)\n\n**An Agentic System for Scalable Articulated 3D Asset Generation.**\n\n[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.15187) | [Project Page](https:\u002F\u002Farticraft3d.github.io\u002F)\n\nArticraft transforms the creation of articulated 3D assets into a programmatic, code-generation workflow powered by LLMs. Engineered for large-scale dataset generation, it bypasses heavyweight manual tools to rapidly produce objects with semantic parts, robust geometry, and physical joints.\n\n![Articraft viewer showing an articulated desk lamp with joint controls and dataset metadata](docs\u002Fimages\u002Fviewer-demo.png)\n\n> **Security Note:** Articraft compiles and inspects generated records by executing their `model.py` files as Python code. Only run generated records and model scripts from trusted sources.\n\n---\n\n## Quickstart\n\n### 1. Prerequisites\n- Python 3.12 recommended (or 3.11). *Note: 3.13+ is not currently supported.*\n- [`uv`](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) for incredibly fast Python package management.\n- [`just`](https:\u002F\u002Fgithub.com\u002Fcasey\u002Fjust) as the command runner.\n- [`npm`](https:\u002F\u002Fdocs.npmjs.com\u002Fdownloading-and-installing-node-js-and-npm) (optional, but needed for local viewer frontend).\n\n### 2. Setup\nFrom the repo root, run:\n```bash\njust setup\n```\n\n### 3. Add API Keys\nOpen `.env` and set one or more provider keys (e.g. `OPENAI_API_KEY`, `GEMINI_API_KEYS`, `ANTHROPIC_API_KEYS`).\n\n> **No API Keys?** No problem! If you don't have API keys set up, you can use external AI agents like Claude Code, Codex, or Cursor. Just point them to this repository and prompt them:\n> \n> *\"Create a realistic articulated [object name] and add it to the Articraft dataset. Follow EXTERNAL_AGENT_DATA.md.\"*\n\n### 4. Create an Asset\n\nGenerate your first model directly from a prompt using `articraft generate`:\n```bash\nuv run articraft generate \"Create a realistic articulated desk lamp with a weighted base, two hinged arms, and an adjustable lamp head.\"\n```\n\nIf you specify no overrides, it defaults to `--model gpt-5.5-2026-04-23 --thinking-level high`. You can change models and caps:\n```bash\nuv run articraft generate --model gemini-3-flash-preview --max-cost-usd 1.5 \"Create a compact desk fan with adjustable tilt.\"\n```\n\n### 5. Open the Viewer\nBrowse the objects you just generated. The local viewer API and React frontend can be started with:\n```bash\njust viewer\n```\n\n### 6. Edit an Existing Asset\nFork an existing record when you want to modify it:\n```bash\nuv run articraft fork data\u002Frecords\u002F\u003Crecord_id> \"make the handle longer\"\n```\n\nForking creates a new child record and leaves the parent unchanged. See [Editing Existing Records](docs\u002Frecord_editing.md) for model options, dataset behavior, and history viewing.\n\n---\n\n## Contribute Data\n\nA huge part of Articraft's mission is crowdsourcing a diverse, massive dataset of articulated 3D models. We welcome generation via our CLI, batch processing, or through external AI agents (like Claude Code or Codex). \n\nFor full details on our data pipelines, generation guides, and opening pull requests, please read the complete **[Data Contribution Workflow in CONTRIBUTING.md](CONTRIBUTING.md)**.\n\n**Data Usage & Licensing**  \nBy contributing data to the Articraft project, you acknowledge and agree that your submissions will be used to build, evaluate, and improve machine learning models, and will be distributed publicly as part of our datasets. You explicitly agree that all contributed data is released under the **[Creative Commons Attribution 4.0 International (CC-BY 4.0)](https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby\u002F4.0\u002F)** license.\n\n---\n\n## Documentation & Advanced Usage\n\n- **[Architecture & Project Structure](docs\u002Farchitecture.md)**\n- **[Editing Existing Records](docs\u002Frecord_editing.md)**\n- **[Dataset Generation & Batch Processing](docs\u002Fdataset_generation.md)**\n- **[Contributing Standards & Workflow](CONTRIBUTING.md)**\n- **[Security Policy](SECURITY.md)**\n\n## Citation\n\n```bibtex\n@article{zhou2026articraft,\n  title     = {Articraft: An Agentic System for Scalable Articulated 3D Asset Generation},\n  author    = {Zhou, Matt and Li, Ruining and Lyu, Xiaoyang and Song, Zhaomou and Huang, Zhening and Zheng, Chuanxia and Rupprecht, Christian and Vedaldi, Andrea and Wu, Shangzhe},\n  journal   = {arXiv preprint arXiv:2605.15187},\n  year      = {2026}\n}\n```\n\nThis repository is licensed under the [Apache-2.0 License](LICENSE).\n","Articraft是一个用于生成可扩展的关节式3D资产的系统。它通过大语言模型（LLM）驱动的代码生成工作流，将关节式3D资产的创建过程程序化，特别适合大规模数据集的生成。其核心功能包括快速生成具有语义部分、坚固几何结构和物理关节的对象，无需依赖复杂的传统工具。此外，Articraft支持多种AI服务提供商，并提供了一个本地查看器来浏览生成的对象。该项目适用于需要高效创建或自定义关节式3D模型的场景，如游戏开发、虚拟现实应用以及教育领域等。",2,"2026-06-11 03:55:13","trending"]