Deuz-SDK

MCP server by Deuz-AI · ★ 682 · updated today

Memory & KnowledgeMaintainedOne-click install

TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.

Install View on GitHub Website

Install Deuz-SDK

Choose your AI client and copy the config.

Add to claude_desktop_config.json — macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Then restart Claude.

{
  "mcpServers": {
    "deuz-sdk": {
      "command": "npx",
      "args": [
        "skills",
        "add",
        "Deuz-AI/Deuz-SDK"
      ]
    }
  }
}

Add to Cursor

Or add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "deuz-sdk": {
      "command": "npx",
      "args": [
        "skills",
        "add",
        "Deuz-AI/Deuz-SDK"
      ]
    }
  }
}

Install in VS Code

Or add to .vscode/mcp.json in your workspace.

{
  "servers": {
    "deuz-sdk": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "skills",
        "add",
        "Deuz-AI/Deuz-SDK"
      ]
    }
  }
}

Run in your terminal:

claude mcp add deuz-sdk -- npx skills add Deuz-AI/Deuz-SDK

Run the server directly:

npx skills add Deuz-AI/Deuz-SDK

Before you install: Install command taken from the project README. The README mentions API keys or tokens — you'll likely need to add them as environment variables ("env") in the config.

Related Memory & Knowledge servers

Memory (Knowledge Graph) (official reference server)

by modelcontextprotocol · TypeScript

Basic persistent memory using a local knowledge graph of entities, relations and observations, so the assistant can remember information about you across chats.

Memory & KnowledgeOfficialMaintained91.2k (repo)

headroom

by headroomlabs-ai · Python

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Memory & KnowledgeMaintained75.2k

private-gpt

by zylon-ai · Python

Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.

Memory & KnowledgeMaintainedRemote57.6k

context-mode

by mksglu · TypeScript

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Memory & KnowledgeMaintained27.9k

xberg

by xberg-io · Rust

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

Memory & KnowledgeMaintained9.4k

engram

by Gentleman-Programming · Go

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.

Memory & KnowledgeMaintained7.2k