Stars
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Helios: Real Real-Time Long Video Generation Model
Install Kubernetes/K3s, and related cloud-native add-ons, it supports all-in-one, multi-node, and HA 🔥 ⎈ 🐳
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
The ultimate training toolkit for finetuning diffusion models
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding
Enjoy the magic of Diffusion models!
An wrapper for Turbodiffusion to support 100-200x fast video generations.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
Youtu-Tip: Tap for Intelligence, Keep on Device.
A simple yet powerful agent framework that delivers with open-source models
"DeepTutor: Agent-Native Personalized Learning Assistant"
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
An autonomous agent that conducts deep research on any data using any LLM providers
Tongyi Deep Research, the Leading Open-source Deep Research Agent
An Open Source implementation of Notebook LM with more flexibility and features
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
🤗 smolagents: a barebones library for agents that think in code.
VIP cheatsheet for Stanford's CME 295 Transformers and Large Language Models
Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.
Build and run agents you can see, understand and trust.
Train transformer language models with reinforcement learning.
RoboBrain 2.5: Advanced version of RoboBrain. Depth in Sight, Time in Mind. 🎉🎉🎉
verl: Volcano Engine Reinforcement Learning for LLMs