This is the official implementation of Multi-Agent PPO (MAPPO).

Various AI scripts. Mostly Stable Diffusion stuff.

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

A language model programming library.

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

Official implementation of HARL algorithms based on PyTorch.

Presentation Slides for Developers

A customisable 2D platform for agent-based AI research

A JAX research toolkit for building, editing, and visualizing neural networks.

Anthropic's educational courses

Free and Open Source Enterprise Resource Planning (ERP)

The authentication glue you need.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Containers for machine learning

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

Efficient baselines for autocurricula in JAX.

a Hassle-Free Python Experience

This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

Our maintained PFN repository. Come here to train SOTA PFNs.

Official Implementation of "Transformers Can Do Bayesian Inference", the PFN paper

BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground

Datasets with baselines for offline multi-agent reinforcement learning.

♟️ Vectorized RL game environments in JAX