# MyoHub/myosuite

MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

Repository: https://github.com/MyoHub/myosuite
Canonical: https://ross.abutalabs.com/products/myosuite
Homepage: https://www.myosuite.org
Language: Python
License: Apache-2.0
License Family: permissive
Topics: machine-learning, motor-control, mujoco, musculoskeletal
Last push: 2026-08-25T03:18:58+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 80, longevity 100
- inputs: {"age_days": 1750, "days_push": 8, "days_rel": 132, "gap_med": 26, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1210, forks 173 (observed 2026-08-28T04:03:59.999176+00:00)

## What it is
MyoSuite is a collection of musculoskeletal environments and tasks simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API. It enables applying machine learning and reinforcement learning to biomechanical motor control problems such as dexterity, manipulation, and locomotion.

## Use cases
- train reinforcement learning agents to control musculoskeletal models
- simulate human dexterity and in-hand manipulation tasks
- research motor control and biomechanics with MuJoCo
- benchmark policies on contact-rich musculoskeletal environments
- study locomotion and postural control with gym-style APIs
- teach neuromechanics and motor control with tutorials

## When to choose
- you need gym-compatible environments with physiologically realistic musculoskeletal models
- you want to apply RL or ML to biomechanical control problems
- you need contact-rich simulation of muscles, tendons, and joints in MuJoCo

## When to avoid
- you need rigid-body robot arm manipulation without muscle models
- you need real-time interactive simulation or game physics
- you need a lightweight environment without MuJoCo dependencies

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, simulation, reinforcement-learning, testing
- domain: machine-learning, robotics, simulation, artificial-intelligence
- platform: python, windows, cross-platform
- tags: mujoco, musculoskeletal, gym, motor-control, biomechanics, reinforcement-learning-environments, research, linux, macos

## Member repositories
- MyoHub/myosuite (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.999176+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 2026-08-30T06:18:06.589274+00:00, confidence not recorded.
  - readme: https://github.com/MyoHub/myosuite (fetched 2026-08-28T04:03:59.999176+00:00, sha 0849e2c22b2a)
  - homepage: https://www.myosuite.org (fetched 2026-08-29T12:26:15.015741+00:00, sha 1a45f1010ed4)
- Data as of 2026-08-30T08:39:29.467469+00:00.