仓库/Skill 库

NVIDIA AI Blueprint for video search and summarization（VSS）是一个 GPU 加速参考架构，用于构建具备实时验证告警、视觉问答与自动报告能力的视频分析 Agent。VSS Blueprint 采用 NVIDIA Cosmos 等视觉语言模型（VLM）、NVIDIA Nemotron 等 LLM，并结合 RAG 与 NVIDIA NIM。NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

收录 AIGC 领域 RAG 的优秀论文。我们在论文 "Retrieval-Augmented Generation for AI-Generated Content: A Survey" 中提出了 RAG 基础、增强与应用分类法。Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

面向Neovim的MCP客户端，以直观界面无缝将MCP服务器集成到编辑工作流中，便于与常用聊天插件一起管理、测试和使用An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins.

WFGY 正迈向 WFGY 5.0 Polaris Protocol，面向 AI reasoning、RAG、agents 与真实工作流的重要开源版本，包含 Problem Map、Global Debug Card、WFGY 4.0 与 CFV Easter EggWFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

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.

超快速 serverless GPU 推理、沙箱和后台任务Ultrafast serverless GPU inference, sandboxes, and background jobs

由 Claude 驱动的离线优先的科学写作工作空间。本地运行 LaTeX + Python + 100+ 科研 skill。An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

可扩展的 LLM 数据预处理与清洗工具集Scalable data pre processing and curation toolkit for LLMs

Aria 是由 GPT Large Language Models 驱动的 AI 研究助手。Aria is Your AI Research Assistant Powered by GPT Large Language Models

高性能 AI 模型推理引擎A high-performance inference engine for AI models

用于构建生产级Agent系统的Go框架，涵盖图工作流、工具、记忆、A2A、AG-UI、MCP、评估与可观测性A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

开源 LLM/VLM 负载均衡器与服务平台，用于规模化自托管 LLM（和 VLM）🏓🦙 作为 llm-d、Docker Model Runner 等项目的替代方案，组件更少、部署更简单，基于 ggml 生态构建。支持 CPU 和 GPU。Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

《构筑大语言模型应用：应用开发与架构设计》一本关于 LLM 在真实世界应用的开源电子书，介绍了大语言模型的基础知识和应用，以及如何构建自己的模型。其中包括Prompt的编写、开发和管理，探索最好的大语言模型能带来什么，以及LLM应用开发的模式和架构设计。

开源、端到端的 LLM 与 AI agent 应用评估、观测与改进平台。Tracing · Evals · Simulations · Datasets · Gateway · Guardrails。可自托管，Apache 2.0 许可。Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

[GenAI 应用开发框架] 🚀 快速轻松构建 GenAI 应用 💬 在代码中使用结构化数据和链式调用语法与 GenAI Agent 交互 🧩 使用事件驱动的 *TriggerFlow* 管理复杂的 GenAI 业务逻辑 🔀 无需重写代码即可切换任意模型[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code

【Zotero AI 管家】调用大模型，自动精读论文库里的论文，总结为Zotero笔记。支持主流大模型平台！您只需像往常一样把文献丢进 Zotero， 管家会自动帮您精读论文，将文章揉碎了总结为笔记，让您“十分钟完全了解”这篇论文！

构建 Agent 的更高标准Standards for building agents, better

面向攻击性安全的 MCP server，封装 205 个工具、17 个专家 agent 和 60 个 SPA 感知探针，覆盖 OWASP Top 10。支持 CLI + MCP，可自带 LLM，MCP 路径无需 API key。Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CLI + MCP, BYO LLM. No API key needed on MCP path.

基于 nvidia-smi 二进制工具的 Nvidia GPU Prometheus exporterNvidia GPU exporter for prometheus using nvidia-smi binary

一套开箱即用的 Claude Code 学术模板，基于 LaTeX/Beamer + R，支持多 Agent 评审、质量门禁、对抗式 QA 与复现协议。A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.

通过统一 API 接口路由、管理和分析跨多家服务商的 LLM 请求Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

面向 LLM、VLM、DiT 和 REC 模型的高性能推理引擎，针对多种 AI 加速器进行了优化。该项目托管于 OpenAtom 基金会。A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

LLM Council——一个 Claude Code skill，通过 5 位 AI 顾问并附带同行评审来辅助决策。LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review

下一代源码可用的 Codex 与 Claude Code 替代品——一个本地优先、可自托管的 Agent 工作空间，覆盖代码、办公文档、可编辑设计、演示文稿、网站与视频。用 AI 构建后，可像 PowerPoint 一样轻松编辑文字、图片、配色、布局与场景。Next-gen, source-available alternative to Codex and Claude Code — one local-first, self-hostable agent workspace for code, office work, editable design, presentations, websites, and video. Build with AI, then edit text, images, colors, layouts, and scenes as easily as PowerPoint.

兼容 OpenAI 和 Anthropic 协议的 Apple Silicon 服务端。可运行 LLM 和视觉语言模型（Llama、Qwen-VL、LLaVA），支持 continuous batching、MCP 工具调用与多模态。原生 MLX 后端，速度达 400+ tok/s，兼容 Claude Code。OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

用于加速工作流程的自定义 AI Agent 平台Custom AI agent platform to speed up your work.

BrowserWing 将浏览器操作转化为 MCP 命令或 Claude Skill，让 AI Agent 高效可靠地控制浏览器。告别缓慢、token 密集的 LLM 交互——让 Agent 直接调用命令，实现更快的自动化。适用于 AI 驱动任务、浏览器自动化和提升生产力。BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to control browsers efficiently and reliably. Say goodbye to slow, token-heavy LLM interactions — let agents call commands directly for faster automation. Perfect for AI-driven tasks, browser automation, and boosting productivity.

高性能推理引擎，支持 LLM、VLM、DiT 和 REC 模型，针对多种 AI 加速器优化A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

从自动化创意工厂到落地实现From Automated Idea Factory to Realization

AI 编程 Agent 的实用命令行工具。A Utility CLI for AI Coding Agents

一个支持与 MySQL 数据库安全交互的 Model Context Protocol (MCP) server。A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases

AI 驱动的系统综述摘要与 PDF 高效筛选工具AI-powered tool for efficient abstract and PDF screening in systematic reviews.

简易 Agent 开发工具包。The Simple Agent Development Kit.

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

RTP-LLM：阿里巴巴面向多样化应用的高性能 LLM 推理引擎。RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

基于 Rust 🦀 构建的高性能、模块化、内存安全、生产可用的推理、数据接入与索引系统Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀