仓库/Skill 库

一个 Python 库,使用 LLM 从非结构化文本中提取结构化信息,并提供精确的源溯源与交互式可视化。A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

深入讲解 LLM、RAG 以及真实场景 AI Agent 应用的教程。In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

面向实时和流媒体、跨平台可定制的 ML 解决方案。Cross-platform, customizable ML solutions for live and streaming media.

你的 AI 第二大脑，支持自托管。可从网页或本地文档获取答案，构建自定义 Agent，编排自动化任务，执行深度研究。将任意在线或本地 LLM（gpt、claude、gemini、llama、qwen、mistral）转变为你的个人自主 AI。立即免费开始。Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

DeepTutor:Agent 原生的个性化辅导系统。https://deeptutor.info/DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Vane 是一个由 AI 驱动的问答引擎Vane is an AI-powered answering engine.

模块化的、基于图结构的 Retrieval-Augmented Generation (RAG) 系统。A modular graph-based Retrieval-Augmented Generation (RAG) system

📑 PageIndex：面向无向量、基于推理的 RAG 的文档索引📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

你的个人 AI 助手；安装简便，可部署在本机或云端；支持多种聊天应用，能力易于扩展。Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

🪢 开源 AI 工程平台:涵盖 LLM 评测、可观测性、指标、prompt 管理、playground 和数据集。集成 OpenTelemetry、LangChain、OpenAI SDK、LiteLLM 等。🍊 YC W23🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

一个 AI 提示词优化器，用于编写更好的提示词并获得更好的 AI 结果。An AI prompt optimizer for writing better prompts and getting better AI results.

📚 从零开始构建大模型

开源 AI 平台——支持所有 LLM 的 AI Chat，并提供丰富的高级功能。Open Source AI Platform - AI Chat with advanced features that works with every LLM

SGLang 是一个面向大语言模型和多模态模型的高性能 serving 框架。SGLang is a high-performance serving framework for large language models and multimodal models.

用简单、原生的 C/CUDA 进行 LLM 训练LLM training in simple, raw C/CUDA

使用单卡 4GB GPU 推理 AirLLM 70BAirLLM 70B inference with single 4GB GPU

"Vibe-Trading：你的个人交易 Agent""Vibe-Trading: Your Personal Trading Agent"

为 AI Agent 构建实时知识图谱。Build Real-Time Knowledge Graphs for AI Agents

Local-first 代码智能图谱，面向 MCP 与 CLI。为代码库构建持久化映射，使 AI 编程工具只读取关键内容，在代码评审与大仓库工作流中实现可基准测试的上下文缩减。Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

Composio 提供 1000+ 工具集、工具搜索、上下文管理、身份认证及沙盒工作台，助力构建将意图转化为行动的 AI Agent。Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

FastGPT 是基于 LLM 构建的知识平台，提供开箱即用的全套能力，包括数据处理、RAG 检索与可视化 AI 工作流编排，让你无需复杂配置即可轻松开发并部署复杂的问答系统。FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

通过 API 访问的免费 LLM 推理资源列表。A list of free LLM inference resources accessible via API.

基于 AI 的 Python 爬虫。Python scraper based on AI

构建并运行可见、可理解、可信赖的 Agent。Build and run agents you can see, understand and trust.

该仓库展示了多种面向 Retrieval-Augmented Generation (RAG) 系统的高级技术，每个技术均配有详细的 notebook 教程。This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

一个自主 agent，可使用任意 LLM providers 对任意数据进行深度研究。An autonomous agent that conducts deep research on any data using any LLM providers

一站式生成式 AI 资源仓库,提供最新研究动态、面试资源、notebook 等。A one stop repository for generative AI research updates, interview resources, notebooks and much more!

📦 Repomix 是一个强大的工具，能将整个仓库打包为单个对 AI 友好的文件。非常适合需要将代码库喂给 LLM 或其他 AI 工具（如 Claude、ChatGPT、DeepSeek、Perplexity、Gemini、Gemma、Llama、Grok 等）的场景。📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

O'Reilly 书籍《Hands-On Large Language Models》的官方代码仓库。Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

面向 agents、LLM 和 ML 模型的开源 AI 工程平台。MLflow 帮助各种规模的团队调试、评估、监控和优化生产级 AI 应用，同时控制成本并管理对模型和数据的访问。The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Mastra 是面向 AI 驱动的应用与 agents 的现代 TypeScript 框架。Mastra is the modern TypeScript framework for AI-powered applications and agents.

为 AI agents 提供 817 项结构化网络安全技能 · 映射至 6 个框架：MITRE ATT&CK、NIST CSF 2.0、MITRE ATLAS、D3FEND、NIST AI RMF 与 MITRE F3（Fight Fraud）· 采用 agentskills.io 标准 · 兼容 Claude Code、GitHub Copilot、Codex CLI、Cursor、Gemini CLI 及 20+ 平台 · 覆盖 29 个安全领域 · Apache 2.0817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

一个开源的 AI coding Agent，驻留在你的终端中。An open-source AI coding agent that lives in your terminal.

🚀 构建 MCP servers 和 clients 的快速、Pythonic 方式。🚀 The fast, Pythonic way to build MCP servers and clients.