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 11.7k 1.3k

  2. Minari Minari Public

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

    Python 505 63

  3. PettingZoo PettingZoo Public

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

    Python 3.4k 482

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

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

    C++ 2.4k 463

  5. Gymnasium-Robotics Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Python 882 135

  6. Minigrid Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Python 2.4k 640

Repositories

Showing 10 of 50 repositories
  • Shimmy Public

    An API conversion tool for popular external reinforcement learning environments

    Farama-Foundation/Shimmy’s past year of commit activity
    Python 205 MIT 24 5 2 Updated Apr 7, 2026
  • farama.org Public
    Farama-Foundation/farama.org’s past year of commit activity
    HTML 5 7 0 0 Updated Apr 7, 2026
  • miniwob-plusplus Public

    MiniWoB++: a web interaction benchmark for reinforcement learning

    Farama-Foundation/miniwob-plusplus’s past year of commit activity
    HTML 377 MIT 55 2 0 Updated Apr 6, 2026
  • Arcade-Learning-Environment Public

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

    Farama-Foundation/Arcade-Learning-Environment’s past year of commit activity
    C++ 2,406 GPL-2.0 463 35 15 Updated Apr 6, 2026
  • stable-retro Public

    Retro games for Reinforcement Learning Research

    Farama-Foundation/stable-retro’s past year of commit activity
    C++ 363 MIT 68 3 7 Updated Apr 6, 2026
  • Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Farama-Foundation/Minigrid’s past year of commit activity
    Python 2,424 640 19 6 Updated Apr 5, 2026
  • Jumpy Public

    On-the-fly conversions between Jax and NumPy tensors

    Farama-Foundation/Jumpy’s past year of commit activity
    Python 56 Apache-2.0 9 7 1 Updated Apr 5, 2026
  • MPE2 Public

    A set of communication oriented environments

    Farama-Foundation/MPE2’s past year of commit activity
    Python 32 MIT 16 3 1 Updated Apr 5, 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 11,656 MIT 1,313 75 (1 issue needs help) 11 Updated Mar 28, 2026
  • HighwayEnv Public

    A minimalist environment for decision-making in autonomous driving

    Farama-Foundation/HighwayEnv’s past year of commit activity
    Python 3,217 MIT 867 73 9 Updated Mar 6, 2026

Sponsors

  • @jarl-hoyem
  • @JurajZelman

Top languages

Loading…

Most used topics

Loading…