Stars
The Python micro framework for building web applications.
Rich is a Python library for rich text and beautiful formatting in the terminal.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
pix2tex: Using a ViT to convert images of equations into LaTeX code.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Hackable and optimized Transformers building blocks, supporting a composable construction.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Simple and extensible administrative interface framework for Flask
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Witness the aha moment of VLM with less than $3.
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
PyTorch code and models for VJEPA2 self-supervised learning from video.
SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.
A JAX research toolkit for building, editing, and visualizing neural networks.
A large-scale benchmark and learning environment.
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence
BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
TensorDict is a pytorch dedicated tensor container.