仓库/Skill 库

OpenAI Whisper 模型的 C/C++ 移植版本。Port of OpenAI's Whisper model in C/C++

Milvus 是一款高性能、云原生的向量数据库，专为可扩展的向量 ANN 搜索而构建。Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

DeepSpeed 是一个深度学习优化库，使分布式训练和推理变得简单、高效且有效。DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

OpenClaw 的轻量级替代方案，在容器中运行以保障安全。可连接 WhatsApp、Telegram、Slack、Discord、Gmail 等消息应用，具备 memory、定时任务能力，直接基于 Anthropic Agents SDK 运行。A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

开箱即用的 OCR，支持 80+ 种语言及所有主流书写系统，包括拉丁文、中文、阿拉伯文、天城文、西里尔文等。Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

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.

用于快速文本表示与分类的库。Library for fast text representation and classification.

OpenViking 是专为 AI Agent（如 openclaw）设计的开源上下文数据库，以文件系统范式统一管理 Agent 所需的上下文（memory、资源与 Skill），支持分层上下文交付与自我演进。OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

TypeScript 的 AI 工具包。由 Next.js 创作者打造，AI SDK 是一个免费开源库，用于构建 AI 驱动的应用和 Agent。The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

结构化输出（Structured Outputs）Structured Outputs

面向机器学习的 Tensor 库Tensor library for machine learning

🎨 TypeScript 的穷尽式 Pattern Matching 库，具备智能类型推断。🎨 The exhaustive Pattern Matching library for TypeScript, with smart type inference.

NVIDIA® TensorRT™ 是在 NVIDIA GPU 上进行高性能深度学习推理的 SDK。本仓库包含 TensorRT 的开源组件。NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

用于本地运行 AI 的生产就绪工具包。Production ready toolkit to run AI locally

基于 OpenTelemetry，为你的 GenAI 或 LLM 应用提供开源可观测性。Open-source observability for your GenAI or LLM application, based on OpenTelemetry

用于构建有状态 Agent 的 Memory 库Memory library for building stateful agents

面向并利用基础模型的数据处理！🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

🚀 新兴模型架构的高效实现🚀 Efficient implementations for emerging model architectures

🐢 面向 LLM Agent 的开源评估与测试库🐢 Open-Source Evaluation & Testing library for LLM Agents

一个用于构建 AI Agent 的 Python 库，可充分发挥 Google Antigravity 的全部能力。A Python library for building AI agents that leverage the full power of Google Antigravity.

快速、准确、轻量的 Python 库，用于构建 SOTA embeddingFast, Accurate, Lightweight Python library to make State of the Art Embedding

在 JavaScript 中使用 Hugging FaceUse Hugging Face with JavaScript

通过统一接口对接 LLM 服务商Communicate with an LLM provider using a single interface

快速、灵活、可移植的结构化生成。Fast, Flexible and Portable Structured Generation

在 Postgres 中可扩展、快速且节省磁盘的向量搜索，pgvecto.rs 的继任者。Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

轻量、可移植的 LLM 沙箱运行时（代码解释器）Python 库。Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

Rust 库，用于本地生成向量 embedding 和重排序！Rust library for generating vector embeddings and reranking locally!

高性能且兼容 CommonMark 的 HTML 转 Markdown 转换器。由 Kreuzberg 团队维护。Kreuzberg 是一个以 Rust 为核心的快速多语言文档智能引擎，基于流式解析器与内置 OCR，支持从 98+ 文档格式中抽取结构化数据。High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts structured data from 98+ document formats using streaming parsers and built-in OCR.

一个面向动态文本分类的灵活、自适应分类系统A flexible, adaptive classification system for dynamic text classification

MIT 许可、无 COM 依赖的 .NET 库，用于创建、读取、编辑、转换、渲染和提取 Office、PDF、邮件、OneNote 及文本格式。MIT-licensed, COM-free .NET libraries for creating, reading, editing, converting, rendering, and extracting Office, PDF, email, OneNote, and text formats.

📚 一个零依赖、基于 git 的微型课程库，供 AI Agent 异步共享和检索经过验证的调试经验。| https://misakanet.org📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. | https://misakanet.org

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

Java 8+ agentic SDK：统一 LLM 接入（OpenAI/Anthropic/DashScope/Doubao/DeepSeek...）、Tool Calling、MCP、RAG、Agent Runtime，以及内置的 Coding Agent CLI/TUI/ACP。Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...), Tool Calling, MCP, RAG, Agent Runtime, and a built-in Coding Agent CLI/TUI/ACP.

生产级 Go SDK，用于构建具备长期记忆、知识检索与语音能力的 AI agent，可作为库、守护进程或实时管道运行。Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

面向 Machine Learning 的数据搜索与增强库 —— 可从数百个公开和付费的外部数据源（包括开源和商用 LLM）中轻松查找并添加相关特征到你的 ML & AI pipelineData search & enrichment library for Machine Learning → Easily find and add relevant features to your ML & AI pipeline from hundreds of public and premium external data sources, including open & commercial LLMs

一人即一队 Agent。支持多终端协作的多会话 CLI；/goal 让长任务持续运行；微信/企业微信/飞书网关让你离开后也能随时召回。异步 Python SDK，持久化记忆，自演化 SkillOne person, a team of agents. Multi-session CLI that collaborates across terminals; /goal keeps long tasks running; WeChat/WeCom/Feishu gateway lets you call them back when you walk away. Async Python SDK, persistent memory, self-evolving skills.