# openai/mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Repository: https://github.com/openai/mujoco-py
Canonical: https://ross.abutalabs.com/products/mujoco-py
Language: Cython
License: NOASSERTION
License Family: other
Archived: true
Last push: 2023-12-10T12:47:21+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3783, "days_push": 997, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3143, forks 823 (observed 2026-08-28T04:07:45.931605+00:00)

## What it is
mujoco-py provides Cython-based Python 3 bindings for the MuJoCo physics engine, enabling rigid body simulation with contacts from Python. It is now deprecated and users should switch to the official DeepMind MuJoCo Python bindings.

## Use cases
- simulate rigid body physics with contacts from python
- run mujoco environments for reinforcement learning research
- load and step mujoco xml models in python
- reproduce legacy gym robotics environments
- simulate humanoid and other articulated models

## When to choose
- maintaining legacy code that depends on mujoco-py or mujoco 2.1.0
- reproducing older reinforcement learning benchmarks that require mujoco-py

## When to avoid
- starting a new project - use the official DeepMind MuJoCo Python bindings instead
- you need MuJoCo versions after 2.1.0
- you need Windows support
- you want actively maintained software

## Facets
- artifact type: library
- maturity: abandoned
- function: simulation, machine-learning, sdk
- domain: robotics, reinforcement-learning, simulation, machine-learning
- platform: python
- tags: physics-engine, mujoco, cython-bindings, deprecated, rigid-body-dynamics, linux, macos

## Member repositories
- openai/mujoco-py (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:45.931605+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:45:36.013642+00:00, confidence not recorded.
  - readme: https://github.com/openai/mujoco-py (fetched 2026-08-28T04:07:45.931605+00:00, sha 32ad355378a4)
  - registry_pypi: https://pypi.org/pypi/mujoco-py/json (fetched 2026-08-29T09:40:38.293397+00:00, sha d8f153afeca0)
- Data as of 2026-08-30T08:39:29.467469+00:00.