Skip to content
Back to search

WorldFoundry

Unified World Model Inference & Evaluation Infrastructure

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/openenvision--worldfoundry/badge.svg)](/listings/openenvision--worldfoundry)

HTML

<a href="/listings/openenvision--worldfoundry"><img src="/api/listings/openenvision--worldfoundry/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 157 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # WorldFoundry
  2. [![Python](https://img.shields.io/badge/python-3.10%20--%203.13-blue)](pyproject.toml)
  3. [![License](https://img.shields.io/badge/license-Apache--2.0-green)](LICENSE)
  4. [![Docs](https://img.shields.io/badge/docs-Fumadocs-orange)](https://openenvision.github.io/WorldFoundry/docs)
  5. [![arXiv](https://img.shields.io/badge/arXiv-2611.10771-b31b1b)](https://arxiv.org/abs/2611.10771)
  6. [![Hugging Face](https://img.shields.io/badge/Hugging%20Face-Paper-yellow)](https://huggingface.co/papers/2611.10771)
  7. [Documentation](https://openenvision.github.io/WorldFoundry/docs) · [中文文档](https://openenvision.github.io/WorldFoundry/zh/docs) · [Contributing](CONTRIBUTING.md)
  8. WorldFoundry is an open-source framework for world-model inference and evaluation.
  9. It brings video generation, interactive worlds, 3D/4D reconstruction, and embodied action into a shared workflow.
  10. ![WorldFoundry teaser](docs/fumadocs/public/teaser.png)
  11. ## 📰 News
  12. - **[2026-11-10]** 🔥 **The WorldFoundry technical report is now available on [arXiv](https://arxiv.org/abs/2611.10771)!** We welcome your support with a GitHub Star and a [Hugging Face Upvote](https://huggingface.co/papers/2611.10771). Thank you for your support!
  13. - **[2026-07-12]** 🔥 **WorldFoundry reached 100+ stars on its very first day!** Thanks to the community for the incredible support and encouragement. More exciting updates are coming!
  14. - **[2026-07-11]** 🎉 **WorldFoundry is officially open-sourced.** We welcome ⭐ stars, bug reports, feature requests, and pull requests from the community!
  15. ## 🤝 Community
  16. Join the **WorldFoundry Community** on Slack, [Discord](https://discord.gg/ybUQMDA4x), or WeChat for discussions, announcements, technical support, and the latest project updates.
  17. <p align="center">
  18. <a href="https://join.slack.com/t/worldfoundrycommunity/shared_invite/zt-43nbi9fw4-okYiELzZHp0_1UPa3dh3bQ">
  19. <img src="https://img.shields.io/badge/Slack-Join%20Workspace-4A154B?logo=slack&logoColor=white" alt="Join Slack">
  20. </a>
  21. <a href="https://github.com/OpenEnvision/WorldFoundry/issues">
  22. <img src="https://img.shields.io/badge/GitHub-Issues-181717?logo=github" alt="GitHub Issues">
  23. </a>
  24. </p>
  25. <p align="center">
  26. <strong>WeChat Community</strong>
  27. </p>
  28. <table align="center">
  29. <tr>
  30. <td align="center"><strong>Group 1 — Full</strong></td>
  31. <td align="center"><strong>Group 2 — Full</strong></td>
  32. <td align="center"><strong>Group 3 — Open</strong></td>
  33. </tr>
  34. <tr>
  35. <td align="center"><img src="docs/fumadocs/public/wechat_qr.png" alt="WorldFoundry WeChat Group 1" width="280"></td>
  36. <td align="center"><img src="docs/fumadocs/public/wechat_qr_2.png" alt="WorldFoundry WeChat Group 2" width="280"></td>
  37. <td align="center"><img src="docs/fumadocs/public/wechat_qr_3.png" alt="WorldFoundry WeChat Group 3" width="280"></td>
  38. </tr>
  39. </table>
  40. <p align="center">
  41. <em>Groups 1 and 2 are full. Scan the Group 3 QR code to join.<br>
  42. QR codes are updated periodically if they expire.</em>
  43. </p>
  44. ## Highlights
  45. - **Model and benchmark catalogs** — discover models, checkpoint sources, runtime requirements, and benchmark protocols.
  46. - **Unified inference** — run in-tree pipelines through the CLI, terminal UI, or browser-based Studio.
  47. - **Artifact inspection** — review job status, generated media, and geometry through Studio and its visualizers.
  48. - **Benchmark evaluation** — run model × benchmark cells and inspect normalized metrics, readiness, and eligibility scorecards.
  49. ## System Requirements
  50. - **Platform:** Linux with an NVIDIA CUDA-capable GPU.
  51. - **Driver:** CUDA 12.8+ support for the default unified environment.
  52. - **GPU architecture / VRAM:** model-specific; check the selected model's page.
  53. - **Tools:** Git and Conda.
  54. Inference, Studio, evaluation, and development use the same unified CUDA environment.
  55. Model-specific environments for ABI or simulator requirements are documented in the
  56. [environment guide](https://openenvision.github.io/WorldFoundry/docs/reference/environments).
  57. ## Quickstart
  58. Clone the repository, create the GPU environment, and launch Studio:
  59. ```bash
  60. GIT_LFS_SKIP_SMUDGE=1 git clone https://github.com/OpenEnvision/WorldFoundry.git
  61. cd WorldFoundry
  62. bash scripts/setup/bootstrap_worldfoundry.sh
  63. source tmp/worldfoundry_unified_env.sh
  64. conda activate "${WORLDFOUNDRY_UNIFIED_ENV_PREFIX}"
  65. bash scripts/workspace/run_workspace.sh --host 127.0.0.1 --port 7870
  66. ```
  67. Open **http://127.0.0.1:7870/** to configure inference jobs and inspect their outputs.
  68. On a remote GPU machine, forward port `7870`; additional viewer ports are listed in the
  69. [Studio guide](https://openenvision.github.io/WorldFoundry/docs/guides/studio).
  70. Checkpoints, datasets, API keys, and generated artifacts stay outside git.
  71. Before running a model, prepare its assets using the
  72. [model page](https://openenvision.github.io/WorldFoundry/docs/guides/supported-models) and
  73. [local asset guide](https://openenvision.github.io/WorldFoundry/docs/guides/local-assets).
  74. Prefer the terminal? Run `worldfoundry-eval tui` in the same environment to build a runnable command.
  75. The [full Quickstart](https://openenvision.github.io/WorldFoundry/docs/quickstart) walks through assets,
  76. inference, and evaluation.
  77. ## Documentation
  78. Browse the documentation in [English](https://openenvision.github.io/WorldFoundry/docs)
  79. or [中文](https://openenvision.github.io/WorldFoundry/zh/docs).
  80. | Task | Guide |
  81. | --- | --- |
  82. | Choose a model or benchmark | [Models](https://openenvision.github.io/WorldFoundry/docs/guides/supported-models) · [Benchmark Hub](https://openenvision.github.io/WorldFoundry/docs/evaluation/benchmark-hub) |
  83. | Prepare environments and assets | [Environments](https://openenvision.github.io/WorldFoundry/docs/reference/environments) · [Local assets](https://openenvision.github.io/WorldFoundry/docs/guides/local-assets) |
  84. | Run inference from the terminal | [Inference](https://openenvision.github.io/WorldFoundry/docs/guides/inference) · [CLI](https://openenvision.github.io/WorldFoundry/docs/reference/cli) |
  85. | Use the browser workspace | [Studio](https://openenvision.github.io/WorldFoundry/docs/guides/studio) |
  86. | Tune inference | [Inference optimization](https://openenvision.github.io/WorldFoundry/docs/guides/inference-optimization) |
  87. | Score generated outputs | [Evaluation](https://openenvision.github.io/WorldFoundry/docs/evaluation) |
  88. | Validate changes and understand internals | [Validation](https://openenvision.github.io/WorldFoundry/docs/reference/validation) · [Architecture](https://openenvision.github.io/WorldFoundry/docs/maintainers/architecture) |
  89. ## Contributing
  90. See [CONTRIBUTING.md](CONTRIBUTING.md) for GPU development setup, coding conventions,
  91. tests, DCO sign-off, and the PR workflow.
  92. Repository [Agent Skills](skills/index.md) provide opt-in workflows for model and
  93. benchmark integration, inference optimization, numerical validation, and maintenance.
  94. Use these checks before opening a PR or marking a model/benchmark ready:
  95. Community standards and private vulnerability reporting are covered by the
  96. [Code of Conduct](CODE_OF_CONDUCT.md) and [Security Policy](SECURITY.md).
  97. ## Citation
  98. If you use WorldFoundry in research, cite this repository and the upstream methods,
  99. checkpoints, datasets, and benchmarks that your work depends on.
  100. ## Community Policies
  101. Contributions follow the [Code of Conduct](CODE_OF_CONDUCT.md). Use the
  102. [Security Policy](SECURITY.md) for private vulnerability reports.
  103. ## License
  104. WorldFoundry-authored code is licensed under the [Apache License 2.0](LICENSE), except where a file or component carries a different license notice. Vendored and adapted upstream components remain subject to their original licenses, collected in [THIRD-PARTY-NOTICES](THIRD-PARTY-NOTICES).
  105. ## Acknowledgment
  106. WorldFoundry builds on upstream world-model, video-generation, reconstruction, and embodied-action projects.
  107. See the model pages and [upstream license guide](https://openenvision.github.io/WorldFoundry/docs/reference/vendored-licenses) for attribution.
  108. We also thank:
  109. - [FastVideo](https://github.com/hao-ai-lab/FastVideo) — a unified inference and post-training framework for accelerated video generation
  110. - [OpenWorldLib](https://github.com/OpenDCAI/OpenWorldLib) — a unified codebase for advanced world models
  111. - [VLA Evaluation Harness](https://github.com/allenai/vla-evaluation-harness) — one framework to evaluate VLA models on robot simulation benchmarks

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.