Stars
Bash is all you need！write a claude code with only 16 line code
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: AI-Powered 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.
AgentScope: Agent-Oriented Programming for Building LLM Applications
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
Sky-T1: Train your own O1 preview model within $450
一个简洁优雅的词典翻译 macOS App。开箱即用，支持离线 OCR 识别，支持有道词典，🍎 苹果系统词典，🍎 苹果系统翻译，OpenAI，Gemini，DeepL，Google，Bing，腾讯，百度，阿里，小牛，彩云和火山翻译。A concise and elegant Dictionary and Translator macOS App for looking up words an…
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.