Lists (9)
Agentic
Agents
Contains all of the greatest agents repo!Data Processing
Contains all of the greatest data processing repo!Flow matching
Contains all of the greatest flow-matching related repo!Learning
Contains all of the greatest course!LLM
Contains all of the greatest LLM repo!Medical
Reinforcement Learning
Stars
Efficient Finetuning for OpenAI GPT-OSS
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Convert PDF to markdown + JSON quickly with high accuracy
[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Fully open reproduction of DeepSeek-R1
CheXpert NLP tool to extract observations from radiology reports.
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
A generative world for general-purpose robotics & embodied AI learning.
FlashInfer: Kernel Library for LLM Serving
Radiology Objects in COntext (ROCO): A Multimodal Image Dataset
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
A live stream development of RL tunning for LLM agents
[ICLR 2025] This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“
Environments for LLM Reinforcement Learning
No fortress, purely open ground. OpenManus is Coming.
An extremely fast Python package and project manager, written in Rust.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Official Repo for Open-Reasoner-Zero
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
This repository contains the Hugging Face Agents Course.