# google/brax

Massively parallel rigidbody physics simulation on accelerator hardware.

Repository: https://github.com/google/brax
Canonical: https://ross.abutalabs.com/products/brax
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: jax, reinforcement-learning, robotics, physics-simulation
Last push: 2026-08-06T15:04:10+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 63, longevity 100
- inputs: {"age_days": 1918, "days_push": 27, "days_rel": 171, "gap_med": 59, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3223, forks 347 (observed 2026-08-28T04:07:49.864197+00:00)

## What it is
Brax is a fast, fully differentiable rigidbody physics engine written in JAX, designed for massively parallel simulation on accelerator hardware like TPUs and GPUs. It also includes a suite of reinforcement learning training algorithms (PPO, SAC, ARS, ES, APG), which is now the actively maintained part of the project.

## Use cases
- train reinforcement learning agents for robotics in minutes
- run massively parallel physics simulation on GPU or TPU
- differentiable physics simulation for research
- simulate humanoid and quadruped environments at millions of steps per second
- train RL policies with PPO or SAC on simulated environments
- use analytic policy gradients with a differentiable simulator

## When to choose
- you need differentiable or massively parallel physics simulation in JAX
- you want to train RL agents quickly on accelerator hardware
- you are doing robotics or RL research with GPU/TPU access

## When to avoid
- you need a general-purpose physics engine for production robotics simulation - use MuJoCo MJX or MuJoCo Warp instead
- you need the brax/envs pipeline - it is no longer maintained
- you have no accelerator hardware, since Brax is designed for TPU/GPU

## Facets
- artifact type: library
- maturity: maintenance
- function: simulation, machine-learning, reinforcement-learning, gpu-computing
- domain: robotics, reinforcement-learning, simulation, machine-learning
- platform: python, cross-platform
- tags: jax, differentiable-physics, physics-engine, ppo, sac, mujoco, tpu, robotics-simulation, gpu, linux

## Member repositories
- google/brax (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.864197+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 2026-08-29T18:44:18.566340+00:00, confidence not recorded.
  - readme: https://github.com/google/brax (fetched 2026-08-28T04:07:49.864197+00:00, sha 106049ee509e)
  - registry_pypi: https://pypi.org/pypi/brax/json (fetched 2026-08-29T09:37:51.676242+00:00, sha d480b7183622)
- Data as of 2026-08-30T08:39:29.467469+00:00.