Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
This repo exposes the TMF620 command layer through two interfaces:
X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent
Search global patents and scientific literature in natural language, directly inside Claude, Cursor, or any MCP-compatible AI tool.
Official Sarvam MCP server. Exposes every public Sarvam API — STT, TTS, Translate, Transliterate, Language ID, Text Analytics, LLM (30B / 105B), Vision Document Intelligence, Pronunciation...
It gives agents a safe, inspectable, token-efficient way to without falling back to brittle UI automation.
Typed MCP tools for Autodesk Fusion. 75 named tools over the Fusion API: sketches, features, assemblies, joints, measurement, export.
MCP server for Shortlist — search, queue, and auto-apply to jobs from Claude Code
Qt C++ library for working with AI/LLM Providers and MCP
Connects any MCP-compatible AI assistant to Siemens TIA Portal via the Openness API
This project contains MCP Servers for IBM Cloud which provide an interface layer between AI assistants and IBM Cloud services.
VoidMob MCP server for mobile proxies, non-VoIP SMS verifications, dedicated private numbers and global eSIMs.
- The docker image is 2GB without pre-downloaded models. Its 3.76GB with pre-downloaded models!! Too big, someone please help me to reduce the size.
Agent Skills
Anthony Fu's curated collection of agent skills.
Skillpack helps teams turn AI skills into trusted local agents that can run in their own environment and be used directly from and .
Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents.
Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw
Starter-kit for writing services in Go using Kubernetes.
chDB is an in-process OLAP SQL Engine 🚀 powered by ClickHouse
In the AI era, why can't everyone be a Principal Investigator?
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, collector catalogs, automated session capture, feedback curation, thesis-driven investigation, source ingestion, wiki...
Spec-Driven Develop is an open-source, platform-agnostic workflow for AI coding agents. It turns large software changes into a spec-driven loop: project analysis, task decomposition, GitHub Issue/PR...
You don't write AGENTS.md. You train it with gradient descent.