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

Your AI assistant now remembers everything. Forever. Across every conversation.

A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.

Norman MCP Server Your finances, inside your AI assistant. Norman connects your accounting, invoicing, and VAT filing directly to Claude, Cursor, and any MCP-compatible AI. https://mcp.norman.

Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation

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...

个人知识库 MCP 服务器 — 对本地文档建立索引,并提供一组飞书 API 工具,通过 MCP 协议供 AI 客户端访问。

douyin-mcp 让 AI 同时读懂你的抖音创作数据和视频内容 本地运行 · 音轨文案按需提取 · 数据可追溯 · 面向个人创作者的 MCP Server

Enhanced note taking for AI Agents with supervision.

Yet Another Frida MCP Server - Full-featured MCP server for Frida dynamic instrumentation

Chat with AI, run tasks on autopilot, and manage your projects — all from one tab.

Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.

MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
Agent Skills

基于 [Karpathy llm-wiki]方法论,利用 AI 持续构建和维护你的个人知识库。支持从多种素材源(网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件)自动整理为结构化的 wiki,并通过 Quartz 发布为静态wiki知识库网站。 并通过 claude_agent_sdk 调用 claude agent 使用 llm-wiki ,提供api接口对外访问服务 。

Automatically updates your terminal window title to reflect the current task Claude Code is working on. Perfect for developers managing multiple Claude Code instances across different terminals.

Offense, defense, and the reverse-engineering and code-audit core both sides share. Every skill is fact-checked against primary sources.

Every agentic runtime does the same thing: read a skill, call an LLM, execute tools, loop. SubZeroClaw is that principle written directly in C — no framework, no abstractions, no architecture...

使用表示默认遵循以下协议: ⚠️ CC BY-NC 4.0 (知识共享-署名-非商业性使用 4.0 国际许可协议)

One CLI. The whole modern .claude/ surface — settings.json, agents, skills, slash commands, hooks, PRPs — wired correctly the first time.

A pre-built configuration that gives Claude Code persistent memory, security guardrails, and structured workflows. Clone, run setup.sh, and your next session picks up where the last one left off.

PRFlow is the Claude Code plugin that closes that gap — it carries one feature request all the way to a , so you do the final review and merge, not the cleanup.

Connect external AI agents, the existing Sisyphus toolset, and SiYuan's official MCP plugin ecosystem.

輸入股票代碼,自動從 Goodinfo.tw 讀取公開財報數據,生成互動式三維財務分析儀表板。

We use Kimi-K2.5 as the MLLM and Z-Image-Turbo / Qwen-Image-2512 as the Generator. We use Sglang to serve MLLM and Diffusers to serve the Generator.

A skill that provides integration with Lightpanda, a fast headless browser optimized for data extraction and web automation.