mujocolab

    mujocolab/mjlab

    Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

    api
    isaaclab
    mujoco
    mujoco-warp
    reinforcement-learning
    robotics-simulation
    Python
    Apache-2.0
    3.3K stars
    576 forks
    3.3K GitHub watchers
    Updated Oct 30, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    1 release in the last 90 days, the latest 83 days ago, with 63 contributors on GitHub.

    Use Cases & Benefits

    • Provides a GPU-accelerated API combining Isaac Lab and MuJoCo Warp for reinforcement learning and robotics simulation.
    • Enables scalable, high-performance environment design with direct access to native MuJoCo data and minimal dependencies.
    • Use for training complex robot control policies like velocity tracking on humanoid robots with multi-GPU support.
    • Use for motion imitation tasks to train robots to mimic reference motions using customizable datasets.
    • Use for rapid sanity checks of Markov Decision Processes with built-in dummy agents before full training.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    mjlab combines Isaac Lab's manager-based API with MuJoCo Warp, a GPU-accelerated version of MuJoCo. The framework provides composable building blocks for environment design, with minimal dependencies and direct access to native MuJoCo data structures.

    mjlab requires an NVIDIA GPU for training. macOS is supported for evaluation only.

    Or try in Google Colab (no local setup required).

    For alternative installation methods (PyPI, Docker), see the Installation Guide.

    Excerpt from the mujocolab/mjlab README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Sep 2: +10

    +367 stars over 60 days across 6 snapshot days; best day +10 on Sep 2.

    Forks

    576+60

    Open issues

    71+38

    Compared with peers in API

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    mujocolab/mjlab compared with API repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    vxcontrol/pentagi33.5K+7123831 days ago
    usebruno/bruno48.2K+2815914 days ago
    agentgateway/agentgateway6.0K+183609 days ago
    mudler/LocalAI50.2K+1765912 days ago
    sveltejs/svelte88.6K+77659 days ago
    mujocolab/mjlab3.3K—5583 days ago
    Category median48.2K+18359—

    Discover Repositories

    Search across tracked repositories by name or description