MuJoCo Warp
- Software
- Simulators
- Simulator
A GPU-accelerated version of the MuJoCo physics simulator, built on Warp and designed mainly for NVIDIA hardware, for high-throughput robotics simulation.
Made by Google DeepMind.
Source on GitHub: github.com/google-deepmind/mujoco_warp (opens in a new tab). Facts read at commit c384ac5 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit c384ac5 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Runs MuJoCo physics simulation on the GPU for many parallel worlds at once.
- Simulates rigid bodies with contacts, along with soft bodies, cloth, and signed distance fields.
- Offers a ray-tracing batch renderer for rendering many cameras across parallel simulation worlds.
- Can be installed from PyPI and used as a drop-in replacement for MuJoCo in many projects.
- Supports most MuJoCo features, except some integrators, solvers, plugins, and differentiability.
- Also reachable through the JAX ecosystem via MJX, and used by Isaac Lab and mjlab.
Written by Robotheca from the project's README (opens in a new tab) at commit c384ac5.
Getting started
- Difficulty
- Advanced
- Hardware it needs, as the project states it
- Requires an NVIDIA GPU for fast simulation; CPU is supported for development and debugging.
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 15 Oct 2026 on main
- Latest release
- v3.16.0 (14 Oct 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.