仓库/Skill 库

.faf 官方网站 — faf.one，基于 SvelteKit，push 即自动部署。Official website for .faf — faf.one. SvelteKit, auto-deploys on push

独立 Go 守护进程，将 Homematic / HomeMatic IP CCU 桥接到 MQTT（支持 Home Assistant Discovery），提供 REST + WebSocket API、MCP 服务器、Svelte 配置 UI 以及原生 Matter 桥接 —— 多 CCU、单一静态二进制。Standalone Go daemon bridging Homematic / HomeMatic IP CCUs to MQTT (with Home Assistant Discovery), a REST + WebSocket API, an MCP server, a Svelte config UI, and a native Matter bridge — multi-CCU, single static binary.

CloserAI — 基于 DeepSeek Harness 构建的本地优先、模型无关、权限透明的桌面 AI 工作台。CloserAI - a local-first, model-agnostic, permission-transparent desktop AI workbench built on DeepSeek Harness.

自托管 AI 知识 Agent —— TypeScript、Bun、MCP。掌控你的数据，运行你自己的大脑。Self-hosted AI knowledge agent — TypeScript, Bun, MCP. Own your data, run your own brain.

面向 AI 编码 Agent 的跨工具、跨机器共享记忆。本地优先 SQLite，可选 Zenoh + RocksDB mesh，原生支持 MCP。Shared memory for AI coding agents, across tools and machines. Local-first SQLite, optional Zenoh+RocksDB mesh, MCP-native.

基于 DNS、证书透明日志与未认证身份发现的公开元数据域情报。本地 Python CLI、版本化 JSON 与 stdio MCP server，无需凭证或主动扫描。Public-metadata domain intelligence from DNS, certificate transparency, and unauthenticated identity discovery. Local Python CLI, versioned JSON, and stdio MCP server. No credentials or active scanning.

Local-first、确定性的验证层，用于 AI 声明、记忆写入和风险操作。Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.

AI 优先的工作流自动化，自托管且 MIT 许可。238 个集成、MCP server、4 种语言版本，无企业付费墙。Activepieces 的 fork。AI-first workflow automation, self-hosted and MIT. 238 integrations, MCP server, 4 locales, no enterprise paywalls. Fork of Activepieces.

Comic Sol —— 以本地优先的 AI 漫画生产，作为 Codex Skill、Python CLI 和 MCP 服务器。Comic Sol - local-first AI comic production as a Codex Skill, Python CLI, and MCP server.

讲者讲，你的 agent 听。vidtheque 将你没时间看完的演讲转化为带有"凭据"的扎实、带时间戳的知识——具体句子、对应幻灯片以及发生的时刻 (youtu.be/…?t=)。自托管，MIT 许可。Builders talk. Your agent listens. vidtheque turns the talks you didn't have time to watch into solid, timestamped knowledge with receipts — the sentence, the slide, and the second it happened (youtu.be/…?t=). Self-hosted, MIT.

面向 AI 编码 Agent 的 IDE 智能，集成 LSP 语义、tree-sitter 索引、项目记忆和并发安全编辑。IDE intelligence for AI coding agents, with LSP semantics, tree-sitter indexing, project memory, and concurrency-safe edits.

面向 Model Context Protocol 服务器的 OWASP MCP Top 10 安全扫描器OWASP MCP Top 10 security scanner for Model Context Protocol servers

为你的 AI 编程助手打造的持久记忆。它会记住你告诉它的内容，并在恰当时机把对应的笔记交还。本地机器全量运行。A memory for your AI coding assistant. It keeps what you tell it and hands the right note back at the moment it matters. Runs entirely on your own machine.

MendCode：可定制的 CLI，面向 agent、团队、记忆、评审与 TUI。MendCode: Customizable CLI for agents, teams, memory, reviews, and TUI.

面向多 Agent 工作流的 MCP 协调原语。LLM 无关、CLI 无关、可自托管。TypeScript + SQLite。MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

Bun 与 Node 的契约优先后端框架：一次 defineContract() 即可生成 HTTP API、MCP 工具、AI Agent 工具与类型化客户端。Contract-first backend framework for Bun and Node — one defineContract() into an HTTP API, MCP tools, AI-agent tools and a typed client.

确定性的 MCP 安全架构。以 FrozenNamespace 作为 Model Context Protocol 工具验证的可信根（Root of Trust）。Deterministic MCP Security Architecture. FrozenNamespace as Root of Trust for Model Context Protocol tool verification

通过 MCP 让任意 AI agent 在你真实已登录的 Chrome 中拥有"眼睛"和"双手"。零依赖。Give any AI agent eyes and hands in your real, logged-in Chrome — via MCP. Zero dependencies.

面向 Claude 等 LLM agent 的 MCP server，对 CSV、Parquet、Excel、JSON 等表格数据进行 profiling。MCP server that profiles tabular data files (CSV, Parquet, Excel, JSON) for LLM agents like Claude.

自托管、可扩展的 AI agent 平台，具备受治理的 MCP 工具、持久化项目记忆、持久工作流、能力包、自主执行，以及分布式本地模型计算能力。Self-hosted, extensible AI agent platform with governed MCP tools, persistent project memory, durable workflows, capability packs, autonomous execution, and distributed local-model compute.

基于课程大纲的 skill 图谱搭配 AI 学习教练——将官方课程转化为带依赖关系的学习路径，并追踪掌握程度。目前覆盖德国 Gymnasium（文理中学）课程。Curriculum-backed skill graphs with an AI learning coach — official curricula turned into dependency-aware learning paths with mastery tracking. Currently covering German Gymnasium.

一套配置、一组凭证、一个 MCP 端点——由 Claude Code、Cursor、Codex 等 10 余个客户端共享。Local-first，零遥测。One config, one credential set, one MCP endpoint — shared by Claude Code, Cursor, Codex and 9 more. Local-first, zero telemetry.

Commercient Data Lake / Data Hub CLI（dlake）——为 SQL Server 数据平台即时提供 REST + GraphQL API 以及面向 AI Agent 的 MCP 访问能力。提供官方二进制发行版。Commercient Data Lake / Data Hub CLI (dlake) - instant REST + GraphQL APIs and MCP access for AI agents over a SQL Server data platform. Official binaries.

LM Studio 的 Web 前端——支持浏览器访问、自适应记忆、多用户鉴权与 MCP 工具。Web frontend for LM Studio — browser access, adaptive memory, multi-user auth, MCP tools

自托管、隐私优先的个人 AI 知识伴侣，具备 RAG 驱动的检索、智能 Agent 与可扩展 SDK。Self-hosted, privacy-first Personal AI Knowledge Companion with RAG-powered retrieval, intelligent agents, and extensible SDK

infinite token glitch——让 ChatGPT 在真实机器上调用 Codex 工具的 MCP serverinfinite token glitch - mcp server for chatgpt to use codex tools on a real machine

开放兼容性测试网络：该库 API 是否能在你的版本、操作系统和运行时上真正运行？提供真实构建证据、已验证样本以及每个结果对应的运行环境。An open compatibility testing network: does this library API actually run on your version, OS and runtime? Real build evidence, verified samples, and the environment each result came from.

MCP server，可从 URL 提取任意视频（包括微信视频号）。可选择性地分析并提取场景感知的去重关键帧，并对视频进行转录。完全本地运行MCP server that extracts any video from URL(inc/ WeChat channels). Optionally analyzes and extracts scene-aware deduplicated key frames and transcribes the video. ALL LOCAL

全栈博客平台 · Go 后端 + React 前端，内置 MCP server 供 AI agent 读写文章

Base MCP Server：AI Agent 加密货币空投 2026 🚀 | 免费 & 安全Base MCP Server: AI Agent Crypto Airdrops 2026 🚀 | Free & Secure

跨所有编码 CLI 的统一 agent 配置——导入、渲染、切换工具集，诊断偏移，安全恢复。本地优先，厂商中立，Rust 实现。One agent setup across every coding CLI — import, render, switch toolsets, diagnose drift, and restore safely. Local-first, vendor-neutral, Rust.

Ultimate AI Spellbook Workflows 2026 – 构建多平台 Skill 与自动化Ultimate AI Spellbook Workflows 2026 – Build Multi-Platform Skills & Automation

面向 Kubernetes 环境的 air-gapped RAG pipeline。在 LibreChat/LiteLLM/Keycloak/vLLM 之上增加文档摄取、强制的分类/可发布性标签、策展人审核与基于声明的访问控制检索，并以自定义 MCP 工具的形式对外暴露。Air-gapped RAG pipeline for Kubernetes environments. Adds document ingestion, mandatory classification/releasability tagging, curator review, and claims-based access-controlled retrieval on top of LibreChat/LiteLLM/Keycloak/vLLM — exposed as a custom MCP tool.

FastMCP 3.2 语音 gateway：FunASR 本地 STT、Gemini Live/TTS、Hume、ElevenLabs 声音克隆、唤醒词、RAG。MCP server + React webapp。FastMCP 3.2 speech gateway: FunASR local STT, Gemini Live/TTS, Hume, ElevenLabs cloning, wake word, RAG. MCP server + React webapp.

面向 Node 与浏览器的 AI 数据库对话：用自然语言提问、审视查询、获取答案。支持 Postgres、MySQL、SQLite、DuckDB、Oracle、MongoDB。具备只读 AST 守卫、React UI、MCP server、VS Code 与 JetBrains 集成。AI database chat for Node and the browser: ask in plain language, review the query, get answers. Postgres, MySQL, SQLite, DuckDB, Oracle, MongoDB. Read-only AST guard, React UI, MCP server, VS Code & JetBrains.

Bruno 的 MCP server：AI agent 可编写、读取并运行 .bru 与 .yml API 集合。无需 bru CLI，与 Bruno 字节级一致。兼容 Claude、Cursor、Codex。MCP server for Bruno: an AI agent authors, reads and runs .bru and .yml API collections. No bru CLI, byte-parity with Bruno. Claude, Cursor, Codex.