Skip to content
@Farama-Foundation

Farama Foundation

The Farama foundation is a nonprofit organization working to develop and maintain open source reinforcement learning tools.

Pinned Loading

  1. Gymnasium Gymnasium Public

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

    Python 11.3k 1.3k

  2. Minari Minari Public

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

    Python 492 63

  3. PettingZoo PettingZoo Public

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

    Python 3.3k 471

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

    The Arcade Learning Environment (ALE) -- a platform for AI research.

    C++ 2.4k 461

  5. Gymnasium-Robotics Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Python 853 134

  6. Minigrid Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Python 2.4k 640

Repositories

Showing 10 of 50 repositories
  • farama.org Public
    Farama-Foundation/farama.org’s past year of commit activity
    HTML 5 7 0 1 Updated Feb 17, 2026
  • Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Farama-Foundation/Minigrid’s past year of commit activity
    Python 2,402 640 25 10 Updated Feb 16, 2026
  • stable-retro Public

    Retro games for Reinforcement Learning Research

    Farama-Foundation/stable-retro’s past year of commit activity
    C++ 347 MIT 65 3 5 Updated Feb 16, 2026
  • MO-Gymnasium Public

    Multi-objective Gymnasium environments for reinforcement learning

    Farama-Foundation/MO-Gymnasium’s past year of commit activity
    Python 369 MIT 52 2 3 Updated Feb 11, 2026
  • ViZDoom Public

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

    Farama-Foundation/ViZDoom’s past year of commit activity
    C++ 1,975 429 24 (3 issues need help) 5 Updated Feb 11, 2026
  • Gymnasium Public

    An API standard 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 11,338 MIT 1,274 76 (1 issue needs help) 8 Updated Feb 10, 2026
  • PettingZoo Public

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

    Farama-Foundation/PettingZoo’s past year of commit activity
    Python 3,312 471 44 15 Updated Feb 6, 2026
  • Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Farama-Foundation/Gymnasium-Robotics’s past year of commit activity
    Python 853 MIT 134 17 (1 issue needs help) 9 Updated Jan 24, 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 1,743 MIT 338 3 5 Updated Jan 20, 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 492 63 19 1 Updated Jan 10, 2026