Skip to content
@Farama-Foundation

Farama Foundation

Maintaining the World's Open Source Reinforcement Learning Tools

Pinned Loading

  1. Gymnasium Gymnasium Public

    A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

    Python 12.6k 1.5k

  2. PettingZoo PettingZoo Public

    A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

    Python 3.5k 540

  3. Minari Minari Public

    A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

    Python 1.8k 77

  4. Arcade-Learning-Environment Arcade-Learning-Environment Public

    A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games

    C++ 2.5k 480

  5. Minigrid Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Python 2.5k 650

  6. Gymnasium-Robotics Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Python 2k 150

Repositories

Showing 10 of 45 repositories
  • PettingZoo Public

    A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

    Farama-Foundation/PettingZoo's past year of commit activity
    Python 3,524 MIT 540 31 (11 issues need help) 18 Updated Oct 4, 2026
  • farama.org Public
    Farama-Foundation/farama.org's past year of commit activity
    HTML 6 3 0 0 Updated Oct 3, 2026
  • Gymnasium Public

    A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

    Farama-Foundation/Gymnasium's past year of commit activity
    Python 12,616 MIT 1,490 69 (3 issues need help) 36 Updated Oct 2, 2026
  • Minari Public

    A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

    Farama-Foundation/Minari's past year of commit activity
    Python 1,775 77 18 (1 issue needs help) 8 Updated Sep 30, 2026
  • HighwayEnv Public

    A collection of environments for autonomous driving and tactical decision-making tasks

    Farama-Foundation/HighwayEnv's past year of commit activity
    Python 3,323 MIT 896 37 (8 issues need help) 6 Updated Sep 29, 2026
  • Celshast Public
    Farama-Foundation/Celshast's past year of commit activity
    Sass 6 MIT 5 0 2 Updated Sep 29, 2026
  • ViZDoom Public

    Reinforcement Learning environments based on the 1993 game Doom :godmode:

    Farama-Foundation/ViZDoom's past year of commit activity
    C++ 2,097 456 31 (4 issues need help) 8 Updated Sep 25, 2026
  • Stable-Retro Public

    A fork of gym-retro with additional games, emulators and supported platforms

    Farama-Foundation/Stable-Retro's past year of commit activity
    C++ 1,086 MIT 84 13 11 Updated Sep 17, 2026
  • MAgent2 Public

    An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments

    Farama-Foundation/MAgent2's past year of commit activity
    Python 968 MIT 66 15 (3 issues need help) 4 Updated Sep 13, 2026
  • Metaworld Public

    Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

    Farama-Foundation/Metaworld's past year of commit activity
    Python 1,889 MIT 355 7 (2 issues need help) 11 Updated Sep 12, 2026