Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

Drive KiCad schematic, PCB, DRC/ERC, DFM, and manufacturing review from any MCP-capable AI agent.

A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance

This project is a python server that implements the Model Context Protocol (MCP) for Zotero, giving you access to your Zotero library within AI assistants.

Though I'm fairly confident the overall architecture is sound, and I myself rely on the implementation — so it should work :tm:. But definitely alpha software.

Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.

Model Context Protocol server for Cyclops

A Model Context Protocol server for DuckDuckGo Search

Plugin for JADX to integrate MCP server

MCP server for Atlassian tools (Confluence, Jira)

Curated Claude workflow infrastructure. HeyClaude is a file-backed, human-reviewed directory for Claude agents, MCP servers, skills, hooks, commands, tools, prompts, rules, guides, templates, and...

A local MCP server for agent literature work. Original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. Search is optional.

Most RAG frameworks fall into one of three traps: (1) they require you to ship your data to a cloud API, (2) they hand you 300 building blocks and 0 opinionated defaults, or (3) they bundle RAG as a...
Agent Skills

10 agentes (8 de núcleo, Selina si hay frontend y Lucius bajo demanda), catálogo de 11 skills de proceso, memoria persistente de decisiones por proyecto, 6 flujos de trabajo con quality gates...

A grab-bag of experimental transformer kernels and utilities (mostly PyTorch + Triton).

A Claude Code plugin that audits your mobile app against store review policies — the store rejects it.

TL;DR: Thea brings coding agents to the physical world.

JourniOne 旅行规划 Skill:从灵感与逐日路线,到带地图、可分享的 Travel Journal,按需衔接酒店与航班。

Your future self will thank you. Or blame you. It depends on the diff.

面向 AI Agents 的安全、可持久化沙箱执行平台(Secure, Persistent Execution Platform for AI Agents)

—— 一套可被任意 AI agent(Claude / GPT / Cursor…)使用的**。

小提示:导入数据时**,尽量不要用 JSON——多数微信导出工具的 JSON 是给 LLM 微调用的格式,没有时间戳,跑不出 K 线。详见 输入格式。

Why use many token when few token do trick?

🧬 Darwinia Give your AI agent the power to evolve its own trading strategies. Trading agents that discover strategies through Darwinian selection and adversarial self-play — not human-written rules.

This repository provides a collection of composable Dockerfiles and build scripts for deploying and running software, full applications, and select demonstrators on AMD Ryzen AI hardware.