仓库/Skill 库

用于 AI 辅助管理 Altium Designer 元件库的 MCP server。MCP server for AI-assisted management of Altium Designer component libraries

在你自有的服务器上运行一家由 Agent 组成"公司"。可启动具名 Agent（claude、codex、pi 等），将它们组织成组织架构图并共享待办列表，让它们交接工作，只在需要人类决策时推送通知到你的手机。MIT 协议。Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.

通过 MCP 为 Claude Code 提供持久化长期记忆 — 跨会话捕获编码决策、Bug 修复和上下文。采用 FTS5 + TF-IDF 混合搜索与 episode 批处理。单一 SQLite 数据库，无需外部服务。作为 claude-mem 的替代方案，成本降低 600 倍。Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

通过 hooks 拦截 AI 编程 Agent 发起的 cargo/gcc 构建，并透明地将其路由到远程工作机器，像在本地编译一样返回产物。Intercepts cargo/gcc builds from AI coding agents via hooks and transparently routes them to remote worker machines, returning artifacts as if compiled locally

为 Pi Agent 构建的持久化、多人、移动优先的 Web 应用，基于 Pi Durable 构建。A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable

一个接口对接九个基因组深度学习 oracle——变异效应预测、按轨道校准的百分位数与通过 MCP 提供的通俗易懂分析。One interface to nine genomic deep-learning oracles — variant effect prediction, calibrated per-track percentiles, and plain-English analysis through MCP.

为 AI 编码 Agent 提供长期、跨项目的记忆。以你自己的 Obsidian 仓库为唯一信源。无守护进程、不依赖不透明数据库，记忆归你所有。Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

用于可复现 AI Agent 评测的确定性、可分叉、有状态 MCP 测试世界——不对生产环境产生副作用。Deterministic, forkable, stateful MCP test worlds for reproducible AI agent evaluation—without production side effects.

AI Bro——一个 local-first 的工作空间，用于 AI 对话、源链接知识与任务管理。AI Bro — a local-first workspace for AI conversations, source-linked knowledge, and tasks.

覆盖 100+ 操作系统上 100+ 浏览器的自动化 User-Agent 数据库。通过 GitHub Actions 每 5 分钟更新一次。按真实流行度加权，按 OS 与浏览器分组，并附带累积的 ALL/ 文件夹存放唯一 agent。Automated User-Agent database for 100+ browsers on 100+ operating systems. Updated every 5 minutes via GitHub Actions. Weighted by real-world popularity, grouped by OS and browser, with a cumulative ALL/ folder of unique agents.

Local-first、无需 API key 的 MCP server，支持网页搜索、抓取与文档阅读。多引擎（DuckDuckGo、Mojeek、Startpage）、智能 Playwright 兜底、FTS5 缓存、面向 LLM 调优的输出。Local-first, no-API-key MCP server for web search, fetch, and document reading. Multi-engine (DuckDuckGo, Mojeek, Startpage), smart Playwright fallback, FTS5 cache, LLM-tuned output.

面向任意场景、任意任务的 Agentic 导航系统。An Agentic Navigation System for Any Task in Any Scene

开源、可自托管的 Markdown 团队 Wiki，内置 MCP server——让 AI Agent 作为"一等队友"读写并检索你的文档。支持实时多人协作、语义+全文搜索。基于 Go + PostgreSQL + React/Milkdown。Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.

一个多 provider、多 Agent 编排器，将 Agent 组织成可视化的权限层级。A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.

面向视觉创作者与编程 agent 的本地音频响应节奏图与可复用时序包。Local audio-reactive rhythm maps and reusable timing packages for visual creators and coding agents.

你专属的、持续进化的社交媒体助手，让创作更轻松。Your private evolving social media assistant, making creation easier.

Local-first 的 MCP 插件，为 AI coding Agent 提供持续的软件质量审查，由 Jev 驱动。Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

端到端 AI 文献综述自动化：抓取、筛选、下载、多智能体评审与报告生成End-to-end AI literature review automation: crawl, screen, download, multi-agent review, and report generation

面向 AI Agent 的集中式 SSH 网关，提供 MCP 接入、凭据托管、细粒度授权与全程审计。

面向持续论证技巧的学术写作助手Academic Writing Assistant for Continuous Argumentation Technique

即插即用、成本高效且轻量化的长周期 LLM Agent 记忆插件A Plug-and-Play, Cost-Efficient, and Lightweight Memory Plugin for Long-Horizon LLM Agents

CoRT 2.0：面向 AI Agents 的革命性上下文推理工具包（2026）。CoRT 2.0: Revolutionary Contextual Reasoning Toolkit for AI Agents 2026

无需盯守的编程 Agent。启动任务后即可离开。AFK 会构建功能、验证自身工作，完成后发消息通知你。回来即可看到每一步、每个决策以及待处理事项的详细清单。遇到不确定时，它会停下询问而非猜测。The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decision, and what’s waiting on you. If it’s unsure, it stops and asks instead of guessing.

基于 Cloudflare Workers 驱动的 ESP32 个人桌面 Agent。Personal desk agent for ESP32, powered by Cloudflare Workers

面向挪威政府的 Copilot、Agent、MCP、Skill 及编码相关 AI 功能综述All things Copilot, Agents, MCPs, Skills, and coding related AI features for the Norwegian Government

面向编程 Agent 的更快运行时。平均提速 25%、降本 30%，同时质量持平或更优。同等任务、同等质量，更快更便宜。Faster runtime for coding agents. Make coding agents 25% faster and 30% cheaper on average while keeping the quality same or more. Same Task, Same Quality, Faster and Cheaper.

无头持久化 Agent 调度引擎，可可靠且可扩展地运行持久化 AI Agent。Headless durable agentic harness engine. Run durable AI agents reliably and scalably.

用于编排 AI 编程 Agent 的委派环境。支持跨 git worktree 管理 Claude、Gemini 与 Codex 会话，集成终端、上下文注入与工作流自动化。A delegation environment for orchestrating AI coding agents. Manage Claude, Gemini, and Codex sessions across git worktrees with integrated terminals, context injection, and workflow automation.

面向本地文件、终端进程、Office 文档与已命名计算机的自托管 MCP。Self-hosted MCP for local files, terminal processes, Office documents and named computers

为开发者及其编码 Agent 提供持久化的本地记忆。将命令、输出、错误以及有效修复方案记录到 SQLite，并通过 MCP 提供服务Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.

开源、自托管的 Linear 替代方案。项目管理与 issue tracking，团队与 AI Agent 并肩协作完成产品规划与交付。Open-source, self-hosted alternative to Linear. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

为你的 AI 助手提供真实的网络搜索、整页阅读与多源研究能力，引用内容绝不伪造。Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.

基于公开 API 的香港智慧城市实时仪表盘。海底隧道过海分钟数、战略道路车速、街道摄像头、工程、事故、八个陆路口岸及天文台预警，统一绘制在一张地图上。繁体中文与英文。24 小时内由 Cursor 与 Grok 4.7 完成，用于 Agentic Engineer 课程与客座讲座。A live Hong Kong smart-city dashboard on public APIs. Harbour crossing minutes, strategic-road speed, street cameras, works, incidents, eight land control points, and Observatory warnings, drawn as one map. Traditional Chinese and English. Made in 24 hours with Cursor and Grok 4.7, for Agentic Engineer classes and guest lectures.

开源元搜索引擎后端、MCP server 与面向 LLM agent 的 AI 搜索 API。基于 Python FastAPI 的搜索网关，通过 SerpBase 与 Serper 集成 Google 搜索，支持多引擎搜索聚合、结构化 JSON 输出、provider 回退与去重，并提供 SearXNG 替代架构以适配 agent 工作流。Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.

将所有本地 AI 编程会话集中到一个标签页：Claude Code、Codex、OpenCode 统一列表展示，支持可调度的任务队列，以及相互隔离的 Claude Desktop 实例。本地运行、隐私安全、原生支持 MCP。Every local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.

本地 LLM 工作马，记录你的工作日。macOS 上的端上会议笔记、听写、自动补全与回忆功能。GPLv3 许可。A local LLM workhorse that keeps a memory of your workday. On-device meeting notes, dictation, autocomplete, and recall for macOS. GPLv3.