For info on contributing things other than code, such as translations, decks and add-ons, please see the contribution guide. If you'd like to contribute but don't know what to work on, please take a ...

It has official support for C#, Python, and Java, and covers memory management, multi-step planning, and plugin orchestration across model providers. The framework underpins Microsoft's own Copilot ...

LeanRL is a lightweight library consisting of single-file, pytorch-based implementations of popular Reinforcement Learning (RL) algorithms. The primary goal of this library is to inform the RL PyTorch ...