Stars
Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
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.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Simplifying reinforcement learning for complex game environments
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Astro template to help you build an interactive project page for your research paper
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
Simple and extensible administrative interface framework for Flask
Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!
Hackable and optimized Transformers building blocks, supporting a composable construction.
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
[ICCV 25] Official repository of "Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues"
TensorDict is a pytorch dedicated tensor container.
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
The Python micro framework for building web applications.
Rich is a Python library for rich text and beautiful formatting in the terminal.
Build your own visual reasoning model
Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.