Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
IGraph 把代码仓库解析为「符号节点 + 调用关系边」的知识图谱，叠加 LLM 语义摘要与向量索引，通过双通道（Dense + FTS5）RRF 融合检索对外服务。支持挂载 PRD / DB Schema 等多模态资源建立跨模态关联，内置 MCP Server 可直接接入 Cursor / Claude Code 等 AI 助手。
Point Claude at any audio file and it can tell you the key, tempo, dynamics, timbre, percussive character, stereo field, structural sections, and how the music evolves over time -- all from raw audio...
is a local stdio MCP server that lets an Agent ask configured multimodal providers to inspect an explicitly supplied image, video, audio file, or music file.
The cognitive memory layer for AI agents.
Every scraper starts working. The question is how long before it breaks. Anansi is built on a different assumption: the web is adversarial and unstable, and your scraper should handle that without...
MCP-based assistant for busy people who are context switching
The AI agentic designer — open-source React design system + MCP that lets Claude, Codex, Cursor & Gemini build production UI in minutes. No AI slop.
A mcp server that bridges Dune Analytics data to AI agents.
This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:
The local-first knowledge layer for AI development.
One command. TypeScript Python. Example tools, the Inspector, and tests — all wired up. Or point it at an OpenAPI spec and get
WinDbg extension + Python MCP server. Lets MCP‑compatible clients (Cursor, Claude, VS Code + Cline/Roo) drive WinDbg with clean, validated commands. Kernel‑first; user‑mode works too.
Agent Skills
本仓库是基于 WorkBuddy / Claude Code / Cursor 等 AI Agent 的**。每个 Skill 是一个自包含文件夹，包含 SKILL.md（Agent 执行指令）、README.md（人类文档）、references/（Prompt 参考）和 assets/（模板 HTML）。
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes.
The Simulink® Agentic Toolkit allows you to use AI agents with Simulink by giving your AI agent the knowledge and context to read, build, edit, and test Simulink® models using Model-Based Design best...
is a high-performance music generation model for creating complete songs up to long. Conditioned on lyrics and a detailed music description, it generates structurally coherent songs with expressive...
AI Agent Skills for LibLib.tv — 让你的 AI Agent 轻松调用 LibTV 的生图、生视频等 AIGC 能力。
鲁班 | Luban — 把'能用的Skill'打磨成'能被装、能传播、能验证、能进化'的公共资产。Agent skill-polishing workshop: 验料·访行·过尺·慢刨·回炉
Open-source ChatCut alternative · agent-native · local-first AI video editor
今天凌晨五点的时候，我让 AI 帮我打磨一段文案，打磨三遍给我看。 AI 改完之后，我发现一遍比一遍讲究，但是一遍比一遍缺人味儿。 我已经用上最贵的 Claude Fable 5 了，还这样，让我很生气。
Generative AI can make mistakes. You should consider reviewing all output and costs generated by your chosen AI model and agentic coding assistant. See AWS Responsible AI Policy.
A Codex skill to brutally pressure-test startup ideas before you waste time building the wrong thing.
把中文故事文案或一组有序的手绘图片,转换成 3:4 竖屏**:手写体字幕、从左到右的「文字 → 黑白画稿 → 彩色插画」揭示、可选的右下角卷页翻书转场、安全不裁剪的画面构图。基于 Remotion,默认输出无配音、无音乐的 H.264 画面轨,方便后期配音。
你只想说一句“帮我做个 App”，但 Codex 真正需要的是一个能执行、能验证、知道边界、知道何时停下来的目标。 qiaomu-goal-meta-skill turns vague work into a copy-ready Codex /goal command with defaults, verification, boundaries, and pause conditions.