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
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time.
XCode CLI MCP: Convenience wrapper for Xcode CLI tools & iOS Simulator. Progressive disclosure of tool responses to reduce context usage. Use --mini param for build-only with tiny context footprint.
Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built...
The only MCP Server you need. Connect any MCP host with the tools you use daily through our no-code, secure integration hub.
把 Google Antigravity 的 Nano Banana 生图能力封装成 MCP Server，让任何支持 MCP 的 AI 客户端都能画图。
基于 SunnyNet 中间件和 SunnyNetTools 抓包工具扩展的 MCP Server
Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.
"Reduce system lag by 99%, eliminate loading times, and cut token costs by 90%."
🌉 Local-first Proton Mail MCP and CLI through Proton Bridge. Search, read, draft, send, sync, and act on mail from Claude Desktop or Terminal.
Wavelet-based multi-resolution context management for LLMs via MCP.
AI assistants are powerful, but they struggle with Kubernetes because:
Issue tracking for the agentic coding era. One binary. One SQLite database (plus an attachments dir). MCP built in.
Agent Skills
用 Claude Code Skills 做的视频剪辑 Agent
Companion — self-hostable Skills Hub for organizations and coding agents.
A Claude Code skill for generating UI in the Nothing design language. Monochrome, typographic, industrial.
A hook-first runtime for agents that live alongside people.
OpenMinis — The AI Agent app across platforms. Fully free and open source.
Paper A minimal, production-ready storefront template for Saleor . Clean as a blank page — built to ship with agents and humans.
AI code assistants generate code. They don't decide where it goes, how it should be layered, or whether it stays consistent across 30 or 50 engineers in the team.
A collection of agent skills that turn your LLM coding assistant into a fully functional SAST scanner to find vulnerabilities in your codebase.
A smarter, self-hosted AI assistant — multi-user, multi-agent.
🇫🇷 Skills pour agents IA spécialisés dans la bureaucratie française : Comptable, Notaire, ...
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
- A terminal UI for orchestrating AI coding agents to work through task lists autonomously.