mujoco

What it is and what it does

MuJoCo is Google DeepMind's physics simulation engine exposed through Python bindings that give direct access to the underlying C API. It provides structs, constants, and enumerations for rigid-body dynamics, collision detection, and constraint solving. The package bundles the MuJoCo library itself, so no separate installation is needed. It depends on numpy, absl-py, etils, glfw, and pyopengl for rendering utilities.

The bindings are designed as a low-level interface rather than a high-level scene authoring API. They include utilities for setting up OpenGL rendering contexts (egl, glfw, osmesa subpackages) and are commonly used in robotics research, reinforcement learning, and physics-based simulation workflows. The package is actively maintained by DeepMind and kept synchronized with MuJoCo's latest developments.

Use it for:

• Build reinforcement learning environments with physics-accurate robot simulation and control
• Prototype rigid-body dynamics for robotics applications with direct C API access
• Render physics simulations using OpenGL with built-in context setup utilities
• Conduct biomechanics or mechanical system research requiring precise collision and constraint solving
• Integrate physics simulation into game engines or interactive applications

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

MuJoCo is a physics simulation engine with Python bindings that provides direct access to the C API for rigid-body dynamics, collision detection, and rendering.

Yes, if you need a physics engine for robotics, reinforcement learning, or scientific simulation. The package is actively maintained, has no known vulnerabilities, carries a permissive Apache-2.0 license, and provides prebuilt wheels for common platforms. Medium install friction is typical for compiled bindings. Not necessary if you only need a higher-level scene API—consider wrapper libraries instead.

Install

mujoco on PyPI

pip install mujoco

uv add mujoco

poetry add mujoco

Installing mujoco

Before you install

Medium install friction due to compiled wheels for multiple architectures and Python versions (3.10–3.14). Active maintenance with a recent release (17 days old) and strong repository activity (14550 stars). No known vulnerabilities.

License in practice

Apache-2.0 permissive license allows commercial and private use with attribution. Pre-built wheels include third-party code (Abseil, cereal, Eigen, Collisions) under compatible licenses (Apache-2.0, BSD, MPL2).

Quickstart

pip install mujoco
import mujoco
model = mujoco.MjModel.from_xml_path('model.xml')
data = mujoco.MjData(model)
mujoco.mj_step(model, data)

Requires Python 3.10 or later. OpenGL rendering requires a display or headless context setup via the egl, glfw, or osmesa subpackages.

Verify before relying

• Whether the package includes pre-built MuJoCo binaries or requires separate installation
• Performance characteristics and simulation accuracy compared to other physics engines
• Specific use-case maturity for robotics vs. general rigid-body simulation

Package facts

Evidence: mujoco-3.11.0-cp310-cp310-macosx_11_0_arm64.whl; mujoco-3.11.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; mujoco-3.11.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; mujoco-3.11.0-cp310-cp310-win_amd64.whl; mujoco-3.11.0-cp311-cp311-macosx_11_0_arm64.whl; mujoco-3.11.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; mujoco-3.11.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; mujoco-3.11.0-cp311-cp311-win_amd64.whl; mujoco-3.11.0-cp312-cp312-macosx_11_0_arm64.whl; mujoco-3.11.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; mujoco-3.11.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; mujoco-3.11.0-cp312-cp312-win_amd64.whl; mujoco-3.11.0-cp313-cp313-macosx_11_0_arm64.whl; mujoco-3.11.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; mujoco-3.11.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; mujoco-3.11.0-cp313-cp313-win_amd64.whl; mujoco-3.11.0-cp314-cp314-macosx_11_0_arm64.whl; mujoco-3.11.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; mujoco-3.11.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; mujoco-3.11.0-cp314-cp314t-macosx_11_0_arm64.whl

Tags

More Scientific/Engineering packages