Stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Library for building powerful interactive command line applications in Python
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
An agentic skills framework & software development methodology that works.
AI agents running research on single-GPU nanochat training automatically
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
🤱🏻 Turn any webpage into a desktop app with one command.
A feature-rich command-line audio/video downloader
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
本教程将全面指导你如何快速搭建自己的AI应用环境，从Docker桌面版的安装与配置开始，到本地部署Dify并自定义AI助手功能，让你轻松实现“猜病例”、“甜蜜哄人”、“新生入学指南”、“小红书读书卡片”与“面试宝典”等多种特色AI应用。并教会你从基础智能体到使用工作流，再到知识库、DeepResearch、数据库、MCP、复杂任务编排等高阶任务，由浅到深的学习掌握基于dify的大模型应用开发。
(best/better) practices of megatron on veRL and tuning guide
My learning notes for ML SYS.
Faker is a Python package that generates fake data for you.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
🔧Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
✅（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】