Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
locklens 是一个基于 audit-ci 的 lockfile 审计工具，支持三种运行模式：
AnalyticDB for MySQL MCP Server is a universal interface between AI Agents and AnalyticDB MySQL. It provides two tool groups:
The only Apple Mail MCP server with — reliable on large mailboxes where AppleScript-based servers timeout. 8 tools for reading, searching, and extracting email content.
把小米 MiMo 全模态能力(对话/图像/视频/TTS/声音克隆)封装成 stdio MCP Server,Claude Code 与 Codex 可直接调用
Index documents from Jira, Confluence, or local files into a local vector database and search them. All data stays on your machine.
AgentMail has one MCP tool implementation, hosted at:
Offensive security you run yourself — a local MCP workflow for authorized testing, in CI or against staging.
Production-grade vector memory MCP server for Claude Code. Semantic search, per-project isolation, rules enforcement, team sharing via git.
A Claude Code plugin that turns Remotion from a motion graphics tool into a .
claude-mem-lite is a (also called long-term memory or cross-session context) system for — Anthropic's CLI coding agent.
🍎 Mac (Apple Silicon) adaptation of baidu/Unlimited-OCR 6.7B VLM. .cuda()→.to('mps') patches + autocast workaround + MCP server. 20s/document on M4 Pro.
AI 에이전트에게 라고 말하면, 흩어진 자료(웹 링크·PDF·대화 로그·텍스트)를 **하고, 관련 있는 노트끼리 **하고, **하고, **까지 해 주고, 원하면 **해주는 **이에요. (Codex엔 "플러그인 설치(/plugin)"가 없어서, 대신 저장소를 받아 codex mcp add로 **해 연동해요.)
Agent Skills
AI assistant for Obsidian with , , and powered by Google Gemini.
基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。
基于 LangGraph 和 DeepAgents 框架的智能体 Skills 能力演示项目。
基于 GJB 438C-2021 [5.10] 标准模板的 SRS 文档自动生成
Generate and review MiniMax H3 video prompts from user goals and multimodal references.
面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑，覆盖内容创作、设计视觉、工具集成、合规文书等场景。
Command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT LLM, SGLang and vLLM.
Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.
A git custom command that enhances Git's native worktree functionality with interactive features, automation, and repository migration capabilities.
先归根，再分化；先明道，再造物。 从混沌需求出发，生成可运行、可验证、可进化的 Agent Skill。
"Writing doesn't just communicate ideas; it generates them."