{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/8"}],"enrichment":{"capability":"A JAX-based reimplementation of the MuJoCo physics engine that runs physics simulations on accelerators (GPUs/TPUs) with an API compatible with MuJoCo.","skillfed_tags":["physics-simulation","jax-native","gpu-accelerated"],"use_cases":["Train reinforcement learning policies with differentiable physics gradients flowing through the simulation.","Run batched physics simulations in parallel on GPU/TPU for robotics research or control optimization.","Integrate physics simulation into JAX-based neural network training pipelines.","Prototype physics-based learning algorithms that require automatic differentiation through dynamics.","Accelerate large-scale multi-environment simulations for population-based training."],"what_it_does":"MJX is a physics simulation library that reimplements MuJoCo using JAX, enabling physics computations to run on GPUs and TPUs. It maintains API compatibility with MuJoCo but is not a drop-in replacement\u2014some features are missing. The package is developed and maintained by Google DeepMind and is kept synchronized with MuJoCo releases.\n\nYou use MJX when you need differentiable physics for reinforcement learning, want to exploit accelerator hardware for batch simulations, or need to integrate physics into JAX-based machine learning pipelines. It depends on JAX, jaxlib, the base mujoco package, scipy, trimesh, absl-py, and etils.","worth_installing":"Yes, if you are doing machine learning with physics simulation and have access to GPU/TPU hardware. MJX is actively maintained by DeepMind, has no known vulnerabilities, and is permissively licensed. Install only if you need JAX integration and can tolerate that some MuJoCo features are not yet supported; if you need full MuJoCo compatibility, use the base mujoco package instead."},"id":"mujoco-mjx","links":{"html":"https://skillfed.io/packages/mujoco-mjx","md":"https://skillfed.io/packages/mujoco-mjx.md","pypi":"https://pypi.org/project/mujoco-mjx/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-07-28","license_spdx":"Apache-2.0","license_treatment":"permissive","name":"mujoco-mjx","python_support":"supports_current","summary":"MuJoCo XLA (MJX)"},"popularity":{"monthly_downloads":99309,"position":13029,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"3.11.0"}