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
The . The historical and kept only for legacy/self-hosted workflows. New users should start with the extension-first path below.
Train in Silence The first Task-Aware MCP server for LLM fine-tuning. Stop comparing GPU prices. Start training. 中文
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
本期系列相关视频如下，按照发布的先后顺序: 主要内容:MCP介绍、MCP功能测试,LLM(支持OpenAI接口风格的大模型)应用程序调用MCP https://www.bilibili.com/video/BV1HBquYbE7t/ https://youtu.be/Jmo7rgb_OXQ 主要内容:使用MCP实现LLM应用程序Text2SQL功能操纵MySQL数据库 https://www.
ChatPPT is an AI-powered presentation generation service that allows users to: - Generate PPTs based on themes or requirements. - Upload documents (e.g.
The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy...
AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems.
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
The cognitive memory layer for AI agents.
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP tools for codegen, browser control, and recordings.
GCO is a platform that spins up EKS Auto Mode clusters across AWS regions, wired together with Global Accelerator for low-latency routing.
Agent Skills
Open agent skills for Alpaca's Trading API and Broker API. Each skill is a SKILL.md file with step-by-step instructions your AI coding assistant follows when you ask it to complete a task, such as...
Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca...
Claude Code skill/plugin: Remnawave + Xray Reality/Vision + Caddy selfsteal + mihomo — reference, config generation, diagnostics
provide for AI agents, helping them build complete automated document workflows. Before large-model reasoning begins, ComPDF Skills can handle document parsing, OCR, data extraction, and structured...
AI agents should not give project advice from vibes.
Comprehensive best practices for building applications with the TanStack ecosystem. These skills provide AI coding agents with structured guidelines for TanStack Query, TanStack Router, and TanStack...
Running 5 AI agents in parallel is easy. Making them not break each other's code is the hard part.
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
for creating, directing, validating, and delivering image, video, audio, voice, music, 3D, avatar, and interactive media.
A curated list of high-signal resources for (formerly , originally ): frameworks, skills, tooling, deployments, and real-world use cases.
🧠 plan · 🔨 implement · 🔍 review · ✅ QA gate · 🚢 merge Thirty-five agent skills that run a full PR pipeline. Install them into any repo, with any coding agent.
A structured Agent workflow for CUMCM, MCM/ICM, and Diangong Cup — designed to keep a 72–96 hour modeling project coherent from the first decision to the final submission.