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

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects to 1000+ app tools and MCP servers.

mTarsier - The Open Source MCP & Skill Manager for Claude, Cursor, VS Code & any AI client.

This is a PoC MCP server developed as part of some internal experiments during the development of CS 4.12 and the CS REST API. More information can be found here.

Unicode/ASCII Mathematical Typesetting Engine with LaTeX Input, VSCode Integration, MCP server, and Automatic Rendering into Source Code Comments

An MCP server implementation that integrates the Hyperliquid SDK.

A memory, docs, and repo context layer for engineering agents.

We use AI for everything - analysis, reports, strategy. But when it comes to actually seeing the story in your data, you're stuck copying numbers into a spreadsheet and building charts yourself.

— A crypto data gateway for AI assistants, powered by the BlockBeats Pro API.

A股 AI 金融智能决策中台 · 129 个 MCP 工具 · eltdx 通达信协议 + akshare + 同花顺 + 东财 + 本地数据 · SmartRouter 多源降级路由 · 免费零鉴权

The Model-Context-Protocol (MCP) gives LLMs a way to call APIs and thus access external systems in a well-defined manner.

Minimal but real MCP server that ingests a GLB/GLTF floorplan scan (for example captured with Polycam https://poly.cam/) and exposes deterministic spatial tools over a compact derived scene graph.

Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.
Agent Skills

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.

🧬 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.

Why use many token when few token do trick?

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。

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

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

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

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

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

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

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...
Most research-idea workflows fail in one of three ways: