Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

Open-source AI browser agent for web automation: a web browsing agent and computer-use agent in plain English. Browser MCP for Claude Code and Gemini CLI.

A single agent thinks. A collective decides. We're building the swarm.

Evidence from your and sources (GitHub repos, PRs, npm). One toolset: ripgrep + AST search, trees, precise reads, and LSP — as a or , backed by a for fast, token-efficient results across single files...

MCP server and CLI tool for searching and downloading documents from Anna's Archive

Instead of relying on one-off scripts generated for a single question, analysts and AI agents can use tested analytical primitives and reusable workflows to inspect customer journeys, explore...

A collection of skills and MCP systems to enable users of CLI, VSCode, Claude to operate over Microsoft Fabric

Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

MCP server with runtime-level tools for Phoenix development

Fetch · crawl · bypass bot walls · read PDFs (even scanned) · search the web One MCP server · one warm browser · zero accounts · runs on your machine

Secure, audit, and govern every AI API call and MCP tool invocation across your organization — from a single control plane.

A flexible multi-interface AI agent framework that can interact through various platforms including Telegram, Discord, Twitter, Farcaster, REST API, and MCP.

Buoy is a floating dev menu that ships inside your React Native app — every request, state change, render, and frame, live on the phone, on your desktop, and in Claude or Cursor.
Agent Skills

一款基于 Taro 框架开发的多端 UI 组件库

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal.

Official Sketch Plugin directory

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Edit videos with coding agents

这是一个领域无关的 AI Context 工作区模板,用于为任意类型的多轮 AI 协作提供稳定、可追踪的上下文结构。

"Where'd you get that prompt?! It's lovely!" "Oh, this old thing? I got it at JeffreysPrompts.com."

tdoc is a prompt-native document surface for agent-assisted writing and review. It creates versioned HTML snapshots, adds Google-Docs-style comments on text and artifacts, and lets an agent pull...

Slides from Anything is a local-first presentation agent workflow for turning source material into delivery-ready decks.

A monolith for your agent's loop. Silent until it talks back.

一个 Claude Code skill(Codex 用户经 AGENTS.md 同样可用): 把你拍的照片蒸馏成极简 zine 纸质海报——手写 HTML/CSS/SVG、无头 Chrome 渲染。 不用图像生成模型,成品里没有一个照片像素。

Unofficial Python CLI for Google Flow. Drive Veo (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.