Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Open-source metasearch backend for MCP, AI agents, and LLM workflows.
AI assistants struggle with codebase understanding. You get:
Local MCP server for COMSOL modeling workflows, validation, and RAG-assisted multiphysics automation.
Full LinkedIn platform management from your terminal. 43 commands for profiles, posts, messaging, connections, search, feed, engagement, and more — powered by cookie session auth.
agentmako is a local-first codebase intelligence engine for AI coding tools.
Make any project agent-ready with .agents/ directory.
C++17 端到端智能语音对话系统，集成 ASR（语音识别）、LLM（大语言模型）、TTS（语音合成）、VAD（语音活动检测）和 AEC（全双工回声消除）。
Your agent starts every session as a stranger. Bolting a vector store onto it doesn't fix that: nothing is ever forgotten, near-duplicate memories pile up, and two contradictory facts come back...
Official MCP Registry · Glama · mcpservers.org · Lulu MCPs · Docker (GHCR)
Notion mcp to connect AI agents to notion through markdown | Read and write notion markdown
rekal is an MCP server that gives AI coding agents persistent memory across sessions. Memories are stored locally in SQLite and retrieved with hybrid search (BM25 keywords + vector semantics +...
is a lightweight Python framework for multi-agent orchestration. It implements the (the AI agent orchestration loop) as a deterministic harness with a closed feedback loop: a goal is decomposed into...
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."