Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
@cyanheads/git-mcp-server A Git MCP server for AI agents. STDIO & Streamable HTTP. 28 Tools · 1 Resource · 1 Prompt
Automated deep malware reverse engineering driven by AI agents. A Kali-based Docker environment pairs 50+ RE tools with MCP-connected disassembler backends (Binary Ninja or Ghidra) and a structured...
Agentic AI for everyone. No API key. No credit card. Just pip install .
A remote MCP server for SubmitMap, a directory of product launch platforms and startup directories.
Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.
Open ChatGPT in your browser and manage multiple computers and servers from one conversation. Write code, change configuration, run commands, and deploy in the real environment where the work...
这是基于 everything-claude-code 进行二次开发，提供npm一键安装方式，协议沿用MIT
— 优先支持静态分析、dry-run 与本地靶场。exploit、横向移动、持久化、C2、数据外传等高风险能力属于受限实验特性；policy 与 sandbox 元数据不等同于操作系统或容器级隔离。
Open a document, select any text, ask a question — and the answer opens as a fully-rendered child document. Follow whatever pulls at you, as deep as it goes. Every hole is saved and revisitable.
Turn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen
MCP server for Agentset, an open-source platform for Retrieval-Augmented Generation (RAG). Designed for developers who want to build intelligent, document-based applications quickly and efficiently.
Too many MCP tools slowing your agent down? Might be a Skill Issue 😉
Agent Skills
🚀🎉📚 SaaS Boilerplate built with Next.js + Tailwind CSS + Shadcn UI + TypeScript. ⚡️ Full-stack React application with Auth, Multi-tenancy, Roles & Permissions, i18n, Landing Page, DB, Logging,...
Autonomous research system for measurable, computer-executable research.
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+
EigenFlux is an open-source framework that enables AI agents to communicate and broadcast within a shared network.
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
the runtime your coding agents live on
OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments that protect your data, credentials, and infrastructure — governed by declarative YAML...
Building AI agents, atomically
Small, composable skills for coding agents.
Anthony Fu's curated collection of agent skills.
In its final days before getting removed from the Subscription, Claude Fable 5 distilled its own way of approaching problems into a set of skills any model can run: classify the ask before touching...