{"id":28753238,"url":"https://github.com/google-deepmind/mujoco_warp","last_synced_at":"2026-04-29T02:01:33.067Z","repository":{"id":283508530,"uuid":"950268214","full_name":"google-deepmind/mujoco_warp","owner":"google-deepmind","description":"GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.","archived":false,"fork":false,"pushed_at":"2026-03-02T12:20:28.000Z","size":11087,"stargazers_count":1081,"open_issues_count":53,"forks_count":132,"subscribers_count":39,"default_branch":"main","last_synced_at":"2026-03-02T16:19:22.796Z","etag":null,"topics":["mujoco-warp","nvidia-warp"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/google-deepmind.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":"AUTHORS","dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-03-17T22:35:01.000Z","updated_at":"2026-03-02T15:15:01.000Z","dependencies_parsed_at":"2025-04-04T07:28:26.351Z","dependency_job_id":"01f3c881-18e9-4fa1-b117-4b3ad8ef5626","html_url":"https://github.com/google-deepmind/mujoco_warp","commit_stats":null,"previous_names":["google-deepmind/mujoco_warp"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/google-deepmind/mujoco_warp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fmujoco_warp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fmujoco_warp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fmujoco_warp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fmujoco_warp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/google-deepmind","download_url":"https://codeload.github.com/google-deepmind/mujoco_warp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Fmujoco_warp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30368664,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T21:41:54.280Z","status":"online","status_checked_at":"2026-03-11T02:00:07.027Z","response_time":84,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["mujoco-warp","nvidia-warp"],"created_at":"2025-06-17T00:39:17.725Z","updated_at":"2026-04-29T02:01:33.045Z","avatar_url":"https://github.com/google-deepmind.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![GitHub Actions](https://img.shields.io/github/actions/workflow/status/google-deepmind/mujoco_warp/ci.yml?branch=main)](https://github.com/google-deepmind/mujoco_warp/actions/workflows/ci.yml?query=branch%3Amain)\n[![Documentation](https://readthedocs.org/projects/mujoco/badge/?version=latest)](https://mujoco.readthedocs.io/en/latest/mjwarp/index.html)\n[![License](https://img.shields.io/github/license/google-deepmind/mujoco_warp)](https://github.com/google-deepmind/mujoco_warp/blob/main/LICENSE)\n[![Nightly Benchmarks](https://img.shields.io/badge/Nightly-Benchmarks-blue)](https://google-deepmind.github.io/mujoco_warp/nightly/)\n\n# MuJoCo Warp (MJWarp)\n\nMJWarp is a GPU-optimized version of the [MuJoCo](https://github.com/google-deepmind/mujoco) physics simulator, designed for NVIDIA hardware.\n\nMJWarp uses [NVIDIA Warp](https://github.com/NVIDIA/warp) to circumvent many of the [sharp bits](https://mujoco.readthedocs.io/en/stable/mjx.html#mjx-the-sharp-bits) in [MuJoCo MJX](https://mujoco.readthedocs.io/en/stable/mjx.html#). MJWarp is integrated into both [MJX](https://mujoco.readthedocs.io/en/stable/mjx.html) and [Newton](https://github.com/newton-physics/newton).\n\nMJWarp is maintained by [Google DeepMind](https://deepmind.google/) and [NVIDIA](https://www.nvidia.com/).\n\n# Getting started\n\nThere are a few ways to jump into using MuJoCo Warp:\n\n* For a quick overview of MJWarp's API and design, please see [our colab that introduces the basics](https://colab.research.google.com/github/google-deepmind/mujoco_warp/blob/main/notebooks/tutorial.ipynb).\n* For more details and advanced topics on using MJWarp, see the [MuJoCo Warp documentation](https://mujoco.readthedocs.io/en/latest/mjwarp/index.html).\n\nIf you would like to train robot policies using MJWarp, consider using a robotics research toolkit that integrates it:\n\n* [MuJoCo Playground](https://github.com/google-deepmind/mujoco_playground) integrates MJWarp via [MJX](https://mujoco.readthedocs.io/en/stable/mjx.html)\n* [Isaac Lab](https://github.com/isaac-sim/IsaacLab/tree/feature/newton) integrates MJWarp via [Newton](https://github.com/newton-physics/newton)\n* [mjlab](https://github.com/mujocolab/mjlab) integrates MJWarp directly\n\n# Installing\n\n**From PyPI:**\n\n```bash\npip install mujoco-warp\n```\n\n**From source:**\n\n```bash\ngit clone https://github.com/google-deepmind/mujoco_warp.git\ncd mujoco_warp\nuv sync --all-extras\n```\n\nTo make sure everything is working:\n\n```bash\nuv run pytest -n 8\n```\n\nIf you plan to write Warp kernels for MJWarp, please use the `kernel_analyzer` vscode plugin located in [`contrib/kernel_analyzer`](https://github.com/google-deepmind/mujoco_warp/tree/main/contrib/kernel_analyzer).\nPlease see the [README](https://github.com/google-deepmind/mujoco_warp/blob/main/contrib/kernel_analyzer/README.md) there for details on how to install it and use it.  The same kernel analyzer will be run on any PR\nyou open, so it's important to fix any issues it reports.\n\n# Compatibility\n\nThe following features are implemented:\n\n| Category           | Feature                                                                                                 |\n| ------------------ | --------------------------------------------------------------------------------------------------------|\n| Dynamics           | Forward, Inverse                                                                                        |\n| Transmission       | All                                                                                                     |\n| Actuator           | All except `PLUGIN`                                                                                     |\n| Geom               | All                                                                                                     |\n| Constraint         | All                                                                                                     |\n| Equality           | All                                                                                                     |\n| Integrator         | All except `IMPLICIT`                                                                                   |\n| Cone               | All                                                                                                     |\n| Condim             | All                                                                                                     |\n| Solver             | All except `PGS`, `noslip`                                                                              |\n| Fluid Model        | All                                                                                                     |\n| Tendon Wrap        | All                                                                                                     |\n| Sensors            | All except `PLUGIN`                                                                                     |\n| Flex               | All except flex-flex collisions, `selfcollide`, `mjEQ_FLEXVERT`, and `mjEQ_FLEXSTRAIN`                  |\n| Mass matrix format | Sparse and Dense                                                                                        |\n| Jacobian format    | `DENSE` only (row-sparse, no islanding yet)                                                             |\n\n[Differentiability via Warp](https://nvidia.github.io/warp/user_guide/differentiability.html) is not currently\navailable.\n\n# Viewing simulations\n\nExplore MuJoCo Warp simulations using an interactive viewer:\n\n```bash\nmjwarp-viewer benchmarks/humanoid/humanoid.xml\n```\n\nThis will open a window on your local machine that uses the [MuJoCo native visualizer](https://mujoco.readthedocs.io/en/stable/programming/visualization.html).\n\n# Batch Rendering\n\nMJWarp includes a **high-throughput** GPU batch renderer designed for simultaneous rendering of cameras across many parallel simulation worlds. The renderer uses ray-tracing to render MuJoCo primitives using Warp's BVH API.\n\nKey capabilities:\n- Mesh rendering\n- Texture support\n- Heightfield rendering\n- Flex deformable rendering\n- Heterogeneous multi-camera support (different resolutions/FOV/intrinsics for each camera)\n- Lighting and shadow support\n\n# Benchmarking\n\nBenchmark as follows:\n\n```bash\nmjwarp-testspeed benchmarks/humanoid/humanoid.xml\n```\n\nTo get a full trace of the physics steps (e.g. timings of the subcomponents) run the following:\n\n```bash\nmjwarp-testspeed benchmarks/humanoid/humanoid.xml --event_trace=True\n```\n\n`mjwarp-testspeed` has many configuration options, see ```mjwarp-testspeed --help``` for details.\n\nBenchmark rendering with:\n\n```bash\nmjwarp-testspeed benchmarks/primitives.xml --function=render\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle-deepmind%2Fmujoco_warp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoogle-deepmind%2Fmujoco_warp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle-deepmind%2Fmujoco_warp/lists"}