Multi-Joint dynamics with Contact. A general purpose physics simulator.
★ 18,059⑂ 2,212👁 143⑃ 998● 1,981▤ 59
More from this author
+99
Daily
+1,399
Weekly
+2,427
Monthly
18,059
stars
2,212
forks
143
watchers
998
prs
1,981
issues
59
releases
README
MuJoCo stands for Multi-Joint dynamics with Contact. It is a general purpose physics engine that aims to facilitate research and development in robotics, biomechanics, graphics and animation, machine learning, and other areas which demand fast and accurate simulation of articulated structures interacting with their environment. This repository is maintained by Google DeepMind. MuJoCo has a C API and is intended for researchers and developers. The runtime simulation module is tuned to maximize performance and operates on low-level data structures that are preallocated by the built-in XML compiler. The library includes interactive visualization in native desktop windows and web browsers. MuJoCo further exposes a large number of utility functions for computing physics-related quantities. We also provide [Python bindings] and a plug-in for the [Unity] game engine. Documentation MuJoCo's documentation can be found at [mujoco.readthedocs.io]. Upcoming features due for the next release can be found in the [changelog] in the "latest" branch. Getting Started 1. Try MuJoCo in your browser. Visit mujoco.org to explore MuJoCo on desktop or mobile with nothing to install, or open live.mujoco.org to inspect and drag and drop your own models in the WebAssembly version of the [MuJoCo Studio] app (slower than native C, since it runs in WebAssembly). 2. Run a viewer on your machine. Follow the [Getting Started] guide in the documentation to download a prebuilt release and run the [MuJoCo Studio] app or the classic simulate viewer (shown in this video) on your machine. 3. Explore our online IPython notebooks. If you are a Python user, you might want to start with our tutorial notebooks running on Google Colab: - The introductory tutorial teaches MuJoCo basics: - The Model Editing tutorial shows how to create and edit models procedurally: - The rollout tutorial shows how to use the multithreaded rollout module: - The LQR tutorial synthesizes a linear-quadratic controller, balancing a humanoid on one leg: - The least-squares tutorial explains how to use the Python-based nonlinear least-squares solver: - The MJX tutorial provides usage examples of MuJoCo XLA, a branch of MuJoCo written in JAX: - The differentiable physics tutorial trains locomotion policies with analytical gradients automatically derived from MuJoCo's physics step: Installation Prebuilt binaries Versioned releases are available as precompiled binaries from the GitHub [releases page], built for Linux (x86-64 and AArch64), Windows (x86-64 only), and macOS (universal). This is the recommended way to use the software. Building from source Users who wish to build MuJoCo from source should consult the [build from source] section of the documentation. However, note that the commit at the tip of the main branch may be unstable. Python (= 3.11) The native Python bindings, which come pre-packaged with a copy of MuJoCo, can be installed from [
Top issues
#2275use the python version of mujoco3.2.6 under win11, an OSError: [WinError 1114] The dynamic link library (DLL) initialization routine failed.39 comments · 2024-12-06#639AMD GPU: GUI is rendered incorrectly all over the window38 comments · 2022-12-09#1427Running mujoco.viewer in a Wayland session results in borderless window25 comments · 2024-02-17#2934Mysterious behavior when grasping while controlling gripper poses using caterisan control19 comments · 2025-11-07#2259[MJX] jax.lax.while_loop in solver.py prevents computation of backward gradients15 comments · 2024-11-29#2487Renderer API13 comments · 2025-03-09#3013Both internal and external plugins do not get loaded when running simulate executable11 comments · 2026-01-09#3397[Performance; Model editing] Batch adding of bodies/geoms/etc.10 comments · 2026-07-12
Discussions
#3907batchplan 0.11: Python motion planning and MuJoCo camera replay0 comments · 2026-11-14#3889Alloy: MJCF robots in scenes with cloth, liquids and sand0 comments · 2026-11-13#3809MuJoCo Lunch at CoRL Austin 20260 comments · 2026-11-10#3780A loadable MJCF can still be the wrong experiment: a small free-fall acceptance gate0 comments · 2026-11-09#3777Discrepancies between MATLAB and MuJoCo for second-order discrete controllers1 comments · 2026-11-08#3773MuJoCo 4: Studio & Filament, Deformables, Speculative Contacts5 comments · 2026-11-07#3708Patch list created0 comments · 2026-10-19#3680Black and Grey / incorrectly rendered UI panels on Windows with AMD Radeon PRO Graphics1 comments · 2026-10-10
Latest release
4.0.1 4.0.1 2026-11-11Version 4.0.1 (November 11, 2026) Compiler 1. 21a076966 Added mjs_getInStringVec to read entries from an mjStringVec by index. Python bindings 2. a937a4f91 Enabled the MuJoCo Studio Web Viewer (mujoco-studio --gfx=web and mujoco.studio.launch_web) on Windows by shipping the precompiled browser client in a platform-independent mujoco-studio-wasm wheel installed automatically by mujoco-studio. Bug fixes 3. 9ae9bad01 Fixed a bug in the sparse Cholesky factorization introduced in 4.0.0, which merged rows with different descendants into one supernode and gave the Ne
相关报道 (6)
Pasquale PillitteriKingKong 发布开源螃蟹机器人 Jumper, 40 厘米 1.8 公斤2026-10-12OSCHINAMicroduck 刚开源,就有人把它从MJCF 跑到了CAD 装配图2026-09-01OSCHINA399 美元的鸭子机器人开源了,今年最让人想立刻掏钱的硬件产品2026-09-01雷峰网RSS’26最新!大幅领先Isaac Sim与MuJoCo,单卡万帧+零微调!视觉仿真器GSP来啦~2026-07-20智源社区宇树机器人强化学习代码全面开源,还有训练到仿真和实操手把手教学2024-12-18凤凰网Mujoco3开源:物理仿真器速度更快 稳定性大大提高2023-10-20
News & coverage (9)
Hacker NewsMuJoCo – Advanced Physics Simulation▲ 116 · 24 comments · 2026-04-19Hacker NewsMuJoCo 4: Studio and Filament, Deformables, Speculative Contacts▲ 1 · 0 comments · 2026-11-09Hacker NewsMuJoCo 3▲ 1 · 0 comments · 2023-10-18GIGAZINEThe physics engine 'MuJoCo' can be downloaded for free with the acquisition of DeepMind.2021-10-19Pasquale PillitteriOpen-Source Crab Robot, KingKong Releases Jumper at 40 cm and 1.8 kg2026-10-11AdafruitRL training environments for Microduck2026-09-01Hackster.ioSimulate Mobile Aloha in Mujoco2024-03-30The Robot ReportDeepMind’s open-source version of MuJoCo available on GitHub2022-05-25Google DeepMindOpen-sourcing MuJoCo2022-05-23