Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
This MCP server helps to build structured documentation system based on Cline's Memory Bank pattern for context preservation in AI assistant environments.
A demo MCP server showcasing interactive UI capabilities using the MCP Apps Extension (SEP-1865).
If your browser/GitHub blocks custom URI handlers, use the web fallback: Cursor install fallback
Agents write markdown — easy-notion-mcp converts it to Notion's block API and back again.
Test tenants sit empty. Static test data does not exercise real workflows. When you need agents that send real emails, schedule real meetings, and collaborate in real Teams channels, mocks and stubs...
Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
Collection of Google-native tools (e.g., Gmail, Calendar) for the MCP
with the integration of DeepSeek R1's advanced reasoning engine. This server enables Claude to tackle complex reasoning tasks by leveraging the reasoning capabilites of deepseek r1 model.
Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff & frontend↔backend integration.
mcpn.ai helps you create, organize, and share AI workflows and prompts. Like a dynamic prompt library you can share & version across MCP tools and servers for specific tasks.
A Visual Studio Code extension to connect to Siemens TIA Portal and interact with TIA Portal projects directly from VS Code with GitHub Copilot.
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats and learn from past errors through a lesson system.
Agent Skills
A Claude Code skill that turns any folder of static HTML pages into a . Highlight text, click an element, leave a note — the comment lands in a local inbox that Claude reads and responds to by...
Skills for . Your agent (the orchestrator) writes a self-contained brief, hands it to an implementer CLI, then reviews the diff and commits — staying the reviewer the whole way.
Empirically detect the repetitive defaults a model falls back on, then turn those findings into a reusable instruction file that makes future outputs less generic.
Persistent cognitive memory, optional HEXACO personality, multi-agent orchestration, and one dispatch interface across 11 LLM providers. Apache-2.0.
⛏️ Turning data into a visual language for better thinking with Skills.
给 Codex、Claude Code、Copilot、Gemini 这类 AI coding agent 用的代码库审计 skill。
Control Claude Code from your Apple Watch. See terminal output, approve permissions, and send voice commands — all from your wrist.
Sample Google Antigravity Skills
Defense-in-depth protection for Claude Code. Blocks dangerous commands and protects sensitive files via PreToolUse hooks.
A free, safe and open agent for everything. Alternative to Claude Cowork & Codex. Open Bridge, the AI bridge between your intention and get the job done.
这是一个长期维护的 AI 视频制作 skill 精选仓库，用来沉淀我在视频创作、视频复刻、动效生成、片头包装、质检交付等流程中反复使用的方法，也用来把优秀参考视频中的动效拆成 HyperFrames / Remotion 能够实现和复用的组件。
Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.