EEmbodied AI Hub
ProjectFeaturedBeginner

MuJoCo Menagerie

Curated collection of high-quality MuJoCo robot models (arms, quadrupeds, humanoids) maintained by Google DeepMind.

Why: Best public MJCF robot assets for MuJoCo experiments

Official / sourceBack to Project
Simulation模型库MuJoCoOpen source

Overview

MuJoCo Menagerie is DeepMind’s curated set of high-quality robot MJCF assets (arms, quadrupeds, humanoids). It removes the pain of hunting broken URDFs when you just want a trustworthy Franka, Unitree, or humanoid model in MuJoCo.

Use it with MuJoCo or dm_control wrappers. Always check each model’s license and actuator ranges before real-robot transfer.

Learning Path: keep it next to MuJoCo so simulation intro is “engine + good assets,” not engine alone.

Who it is for

Researchers, students, and builders comparing open embodied stacks.

Key highlights

  • Curated collection of high-quality MuJoCo robot models (arms, quadrupeds, humanoids) maintained by Google DeepMind.
  • Type: project; categories: simulation, tool
  • Marked recommended on the hub

When to use

  • You are mapping the open embodied AI landscape
  • You need a starting URL and judgment note before deep-diving

When not to use

  • You need production SLAs or certified industrial support only
  • License or hardware constraints are incompatible with your deployment

Getting started

  1. 1Open the official URL and read README install pins.
  2. 2Skim license and citation requirements.
  3. 3Run the smallest official example before scaling experiments.
  4. 4Cross-link related hub resources (sim / data / policy) for a full stack.

Install / setup

git clone https://github.com/google-deepmind/mujoco_menagerie.git

Caveats & pitfalls

  • Hub cards are curated summaries — always verify upstream docs.
  • Stars and dates drift; treat extra.stars as approximate.

Content reviewed 2026-07-28