Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Python library for Reinforcement Learning.

Unified framework for robot learning built on NVIDIA Isaac Sim

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

World's First Large-scale High-quality Robotic Manipulation Benchmark

Grokking Deep Reinforcement Learning

A generative world for general-purpose robotics & embodied AI learning.

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

TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning

robomimic: A Modular Framework for Robot Learning from Demonstration

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.

[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.

Efficient Track Anything

The Fastest Deep Reinforcement Learning Library

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥

RAI is a multi-vendor agent framework for robotics, utilizing Langchain and ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and…

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Develop your agent for generals.io!

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Depth Any Video with Scalable Synthetic Data

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

A journey into using Deep RL with Gazebo (WIP)

Code for Papeg.ai

OpenMMLab Detection Toolbox and Benchmark

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.