# nicrusso7/rex-gym

OpenAI Gym environments for an open-source quadruped robot (SpotMicro)

Repository: https://github.com/nicrusso7/rex-gym
Canonical: https://ross.abutalabs.com/products/rex-gym
Language: Python
License: Apache-2.0
License Family: permissive
Topics: openai-gym, openai-gym-environments, robotics, tensorflow, python3, pybullet, reinforcement-learning, reinforcement-learning-algorithms, artificial-intelligence, gym-environment, robot, spotmicro, quadruped, openai, inverse-kinematics, quadruped-robot-gaits, quadruped-robot, legged-robots, machine-learning, robotic-arm
Last push: 2023-03-24T23:44:23+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2502, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1102, forks 140 (observed 2026-08-28T04:03:35.901660+00:00)

## What it is
Rex-gym provides OpenAI Gym environments for the open-source SpotMicro quadruped robot, built on PyBullet simulation, along with a PPO learning agent and training scripts. It includes a CLI for batch training, rendering single training sessions, and replaying learned control policies intended for sim-to-real transfer to the physical robot.

## Use cases
- train a quadruped robot with reinforcement learning in simulation
- create custom OpenAI Gym environments for legged robots
- run PPO training on a PyBullet robot simulation
- transfer learned control policies from simulation to a real SpotMicro robot
- visualize pre-trained quadruped gaits and policies
- experiment with inverse kinematics vs open-loop gait controllers

## When to choose
- you want to learn or teach reinforcement learning on a realistic legged-robot simulation
- you own or plan to build a SpotMicro quadruped and want sim-to-real policies
- you need ready-made Gym environments with PyBullet for quadruped locomotion research

## When to avoid
- you need a maintained, actively updated project (last release 2023, Python 3.7 era)
- you work with robots other than SpotMicro-style quadrupeds
- you need modern RL frameworks or GPU-accelerated simulation rather than TensorFlow/PyBullet

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, simulation, machine-learning, cli
- domain: robotics, reinforcement-learning, artificial-intelligence, simulation
- platform: python, windows
- tags: openai-gym, pybullet, quadruped-robot, spotmicro, ppo, inverse-kinematics, sim-to-real, legged-robots, linux, macos

## Member repositories
- nicrusso7/rex-gym (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.901660+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 2026-08-30T06:45:39.358770+00:00, confidence not recorded.
  - readme: https://github.com/nicrusso7/rex-gym (fetched 2026-08-28T04:03:35.901660+00:00, sha 47f99042ba20)
  - registry_pypi: https://pypi.org/pypi/rex-gym/json (fetched 2026-08-29T12:48:44.774339+00:00, sha ef2a754ccd4d)
- Data as of 2026-08-30T08:39:29.467469+00:00.