google-deepmind/mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 27 minutes ago
Added to GitGenius on September 3rd, 2026
Created on August 27th, 2021
Open Issues & Pull Requests: 367 (+0)
GitHub issues: Enabled
Number of forks: 1,723
Total Stargazers: 14,973 (+0)
Total Subscribers: 134 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 15.2 hours
Mean response time: 32.5 days
90th percentile: 29.7 days
Tracked items: 545

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 97% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "question" is answered fastest, typically in about 9 hours, while "Unity" waits about 28 months. 58% of tracked open issues have had no activity in three months. Only 6% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 145
New in 7 days: 4
Closed in 7 days: 3
Avg open age: 450 days
Stale 30+ days: 123
Stale 90+ days: 111

Recent activity

Opened in 7 days: 4
Closed in 7 days: 3
Comments in 7 days: 1
Events in 7 days: 3

Top labels

  • bug (315)
  • enhancement (155)
  • question (65)
  • MJX (39)
  • Unity (11)
  • good first issue (5)
  • python (3)
  • documentation (2)

Detailed Description

MuJoCo is a general purpose physics engine designed to facilitate research and development in robotics, biomechanics, graphics, animation, and machine learning through fast and accurate simulation of articulated structures.

The tool addresses the need for high-performance physics simulation by providing a C API with a runtime module tuned for speed, operating on preallocated low-level data structures compiled from XML. It includes an interactive visualization system with a native OpenGL GUI and exposes utility functions for computing physics-related quantities. The engine is built to handle complex interactions between articulated bodies and their environments with both accuracy and computational efficiency.

Researchers and developers working on robotics, biomechanics, or machine learning projects that require detailed physics simulation should consider this tool. It suits projects where performance matters and where researchers need access to low-level simulation data. The project provides Python bindings for those preferring to work in Python rather than C, and offers a Unity plugin for developers integrating physics simulation into game engines. Interactive visualization through the native viewer allows for quick iteration and debugging of simulations.

The project maintains a comprehensive test suite that runs on every commit to the main branch. Documentation is actively maintained and kept current with upcoming features documented in advance. The codebase receives regular updates addressing both new capabilities and refinements to existing functionality.