Back to search
WorldFoundry
SkillGitHub
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
Markdown
[](/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.
- # WorldFoundry
- [](pyproject.toml)
- [](LICENSE)
- [](https://openenvision.github.io/WorldFoundry/docs)
- [](https://arxiv.org/abs/2611.10771)
- [](https://huggingface.co/papers/2611.10771)
- [Documentation](https://openenvision.github.io/WorldFoundry/docs) · [中文文档](https://openenvision.github.io/WorldFoundry/zh/docs) · [Contributing](CONTRIBUTING.md)
- WorldFoundry is an open-source framework for world-model inference and evaluation.
- It brings video generation, interactive worlds, 3D/4D reconstruction, and embodied action into a shared workflow.
- 
- ## 📰 News
- - **[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!
- - **[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!
- - **[2026-07-11]** 🎉 **WorldFoundry is officially open-sourced.** We welcome ⭐ stars, bug reports, feature requests, and pull requests from the community!
- ## 🤝 Community
- Join the **WorldFoundry Community** on Slack, [Discord](https://discord.gg/ybUQMDA4x), or WeChat for discussions, announcements, technical support, and the latest project updates.
- <p align="center">
- <a href="https://join.slack.com/t/worldfoundrycommunity/shared_invite/zt-43nbi9fw4-okYiELzZHp0_1UPa3dh3bQ">
- <img src="https://img.shields.io/badge/Slack-Join%20Workspace-4A154B?logo=slack&logoColor=white" alt="Join Slack">
- </a>
- <a href="https://github.com/OpenEnvision/WorldFoundry/issues">
- <img src="https://img.shields.io/badge/GitHub-Issues-181717?logo=github" alt="GitHub Issues">
- </a>
- </p>
- <p align="center">
- <strong>WeChat Community</strong>
- </p>
- <table align="center">
- <tr>
- <td align="center"><strong>Group 1 — Full</strong></td>
- <td align="center"><strong>Group 2 — Full</strong></td>
- <td align="center"><strong>Group 3 — Open</strong></td>
- </tr>
- <tr>
- <td align="center"><img src="docs/fumadocs/public/wechat_qr.png" alt="WorldFoundry WeChat Group 1" width="280"></td>
- <td align="center"><img src="docs/fumadocs/public/wechat_qr_2.png" alt="WorldFoundry WeChat Group 2" width="280"></td>
- <td align="center"><img src="docs/fumadocs/public/wechat_qr_3.png" alt="WorldFoundry WeChat Group 3" width="280"></td>
- </tr>
- </table>
- <p align="center">
- <em>Groups 1 and 2 are full. Scan the Group 3 QR code to join.<br>
- QR codes are updated periodically if they expire.</em>
- </p>
- ## Highlights
- - **Model and benchmark catalogs** — discover models, checkpoint sources, runtime requirements, and benchmark protocols.
- - **Unified inference** — run in-tree pipelines through the CLI, terminal UI, or browser-based Studio.
- - **Artifact inspection** — review job status, generated media, and geometry through Studio and its visualizers.
- - **Benchmark evaluation** — run model × benchmark cells and inspect normalized metrics, readiness, and eligibility scorecards.
- ## System Requirements
- - **Platform:** Linux with an NVIDIA CUDA-capable GPU.
- - **Driver:** CUDA 12.8+ support for the default unified environment.
- - **GPU architecture / VRAM:** model-specific; check the selected model's page.
- - **Tools:** Git and Conda.
- Inference, Studio, evaluation, and development use the same unified CUDA environment.
- Model-specific environments for ABI or simulator requirements are documented in the
- [environment guide](https://openenvision.github.io/WorldFoundry/docs/reference/environments).
- ## Quickstart
- Clone the repository, create the GPU environment, and launch Studio:
- ```bash
- GIT_LFS_SKIP_SMUDGE=1 git clone https://github.com/OpenEnvision/WorldFoundry.git
- cd WorldFoundry
- bash scripts/setup/bootstrap_worldfoundry.sh
- source tmp/worldfoundry_unified_env.sh
- conda activate "${WORLDFOUNDRY_UNIFIED_ENV_PREFIX}"
- bash scripts/workspace/run_workspace.sh --host 127.0.0.1 --port 7870
- ```
- Open **http://127.0.0.1:7870/** to configure inference jobs and inspect their outputs.
- On a remote GPU machine, forward port `7870`; additional viewer ports are listed in the
- [Studio guide](https://openenvision.github.io/WorldFoundry/docs/guides/studio).
- Checkpoints, datasets, API keys, and generated artifacts stay outside git.
- Before running a model, prepare its assets using the
- [model page](https://openenvision.github.io/WorldFoundry/docs/guides/supported-models) and
- [local asset guide](https://openenvision.github.io/WorldFoundry/docs/guides/local-assets).
- Prefer the terminal? Run `worldfoundry-eval tui` in the same environment to build a runnable command.
- The [full Quickstart](https://openenvision.github.io/WorldFoundry/docs/quickstart) walks through assets,
- inference, and evaluation.
- ## Documentation
- Browse the documentation in [English](https://openenvision.github.io/WorldFoundry/docs)
- or [中文](https://openenvision.github.io/WorldFoundry/zh/docs).
- | Task | Guide |
- | --- | --- |
- | 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) |
- | Prepare environments and assets | [Environments](https://openenvision.github.io/WorldFoundry/docs/reference/environments) · [Local assets](https://openenvision.github.io/WorldFoundry/docs/guides/local-assets) |
- | Run inference from the terminal | [Inference](https://openenvision.github.io/WorldFoundry/docs/guides/inference) · [CLI](https://openenvision.github.io/WorldFoundry/docs/reference/cli) |
- | Use the browser workspace | [Studio](https://openenvision.github.io/WorldFoundry/docs/guides/studio) |
- | Tune inference | [Inference optimization](https://openenvision.github.io/WorldFoundry/docs/guides/inference-optimization) |
- | Score generated outputs | [Evaluation](https://openenvision.github.io/WorldFoundry/docs/evaluation) |
- | Validate changes and understand internals | [Validation](https://openenvision.github.io/WorldFoundry/docs/reference/validation) · [Architecture](https://openenvision.github.io/WorldFoundry/docs/maintainers/architecture) |
- ## Contributing
- See [CONTRIBUTING.md](CONTRIBUTING.md) for GPU development setup, coding conventions,
- tests, DCO sign-off, and the PR workflow.
- Repository [Agent Skills](skills/index.md) provide opt-in workflows for model and
- benchmark integration, inference optimization, numerical validation, and maintenance.
- Use these checks before opening a PR or marking a model/benchmark ready:
- Community standards and private vulnerability reporting are covered by the
- [Code of Conduct](CODE_OF_CONDUCT.md) and [Security Policy](SECURITY.md).
- ## Citation
- If you use WorldFoundry in research, cite this repository and the upstream methods,
- checkpoints, datasets, and benchmarks that your work depends on.
- ## Community Policies
- Contributions follow the [Code of Conduct](CODE_OF_CONDUCT.md). Use the
- [Security Policy](SECURITY.md) for private vulnerability reports.
- ## License
- 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).
- ## Acknowledgment
- WorldFoundry builds on upstream world-model, video-generation, reconstruction, and embodied-action projects.
- See the model pages and [upstream license guide](https://openenvision.github.io/WorldFoundry/docs/reference/vendored-licenses) for attribution.
- We also thank:
- - [FastVideo](https://github.com/hao-ai-lab/FastVideo) — a unified inference and post-training framework for accelerated video generation
- - [OpenWorldLib](https://github.com/OpenDCAI/OpenWorldLib) — a unified codebase for advanced world models
- - [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 inFree to use. If it’s helped, pass it on.