Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

Multi-Agent + Automation: Workflows, Automation, Self-Improving Agents

is the open-source directory for Claude Skills, MCP Servers, Codex Skills, and AI agent tools. 117,000+ projects · + quality-scored on 10 dimensions · refreshed every 8 hours.

Unlike cat videos, most data are trapped in the physical world. Bagel unlocks them and —just like you do with ChatGPT. For example:

一个本地优先的 AI 知识库系统(RAG),用于将本地文档接入向量检索与大模型对话流程。项目提供 Web UI,支持知识库管理、文档上传、检索增强问答、聊天记录持久化,以及基于 Ollama 或 OpenAI 兼容接口的模型接入。

is open-source AI teammate infrastructure for . Connect company tools once, then let ChatGPT, Claude, Codex, and custom agents work from the same durable organizational memory — with scoped...

Local-first memory, visualized. 3,800+ entities and 41,000+ connections, captured automatically as you work.

基于 FastAPI + LangChain + OpenAI 构建的小红书内容挖掘与自动生成系统。支持从爬取竞品数据、分析爆款规律、AI 生成文案与配图,到一键发布至小红书的完整闭环。

One command. Full visibility. Read-only.

Aleph is an MCP server and skill for (RLMs). It keeps working state — search indexes, code execution, evidence, recursion — in a Python process outside the prompt window, so the LLM reasons...

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool...

⚡ — Cross-session orchestration: wake system v2 (dynamic /loop, event watcher, turn-end guard) + targeted sibling-session driving + agent reuse recommendation + context watermark observability.

Every AI can do tax math. None of them can stand behind an answer. Here, real accountants put their on the Guides your AI reads — publicly, on the record, in this repo.
Agent Skills

A Claude Code skill plus guard hooks that give a non-frontier model Fable-5-grade work discipline: plan-gate, self-verification, and sub-agent routing, enforced mechanically.

—— 凌驾于全部技能/工具之上的元规则,强制 Agent 先查后用、有匹配必用、无匹配必搜。跨平台通用(WorkBuddy / Claude / ChatGPT / Cursor / Gemini / ...)

A hands-on showcase for anyone running Agentic Coding Agents at scale on macOS.

把已经导出的 MP4、MOV 交给 Agent,依次完成转录、术语纠错、人工预览、章节生成和 FFmpeg 烧录。默认只生成中文字幕,只需要一个百炼 API Key。

Mode-aware directing, prompt design, extension, and editing for Jimeng Seedance 2.5

ARM64 函数级 VM 执行与指令跟踪框架。把任意 native 函数放进 Unicorn 引擎中执行,暴露每条指令、外部调用、SVC、内存访问的全部细节。 支持多进程,多线程,多并发,多个函数同时追踪,测试抖音,美团,等大型app均无崩溃情况。

- 读完 README 和 CLAUDE.md 后,可以引导用户完成配置 - 用户遇到问题时,主动提出"我可以读 docs/FAQ.md 帮你排查" - 用户有功能想法时,主动说"我可以帮你提交到 GitHub" - mycc 的 cc 会定期读取 Issues,你提交的建议会被看到

A Claude skill that walks you through writing a systematic literature review following the PRISMA 2020 framework.

Complete UI/UX system for Claude Code -- 152 agents, 70 plugins, 76 commands, 74 skills

让 Claude Code 拥有一支 12 人 AI 软件开发团队 + 1 位总指挥,从需求到上线全流程自动跑通。

A Claude Code / Claude Desktop skill for creating and reading XMind mind maps. Zero npm dependencies — uses only Node.js built-ins.

Энэхүү монгол толь нь Hunspell үгийн алдаа шалгагчид тулгуурлан ажиллах бөгөөд 75 мянга орчим үндэс, тэдгээрийн 2.5 тэрбум гаруй хувилал бүхий үгийн санг агуулсан.