Deuz-SDK MCP Server
Deuz-AI/Deuz-SDK
[](https://agentrank-ai.com/tool/Deuz-AI--Deuz-SDK/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Zero-dependency TypeScript framework for production AI agents: durable execution, long-term memory, hybrid RAG, MCP tool calling, human-in-the-loop approval, planning and CodeAct sandboxes. One streaming API for Claude, GPT, Gemini, Grok, Mistral and DeepSeek — Node, Bun, Deno, serverless and edge.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
Deuz-AI/Deuz-SDK is a TypeScript tool licensed under MIT. Zero-dependency TypeScript framework for production AI agents: durable execution, long-term memory, hybrid RAG, MCP tool calling, human-in-the-loop approval, planning and CodeAct sandboxes. One streaming API for Claude, GPT, Gemini, Grok, Mistral and DeepSeek — Node, Bun, Deno, serverless and edge. Topics: ai-sdk, anthropic, llm, mcp, openai, rag, typescript, agent-framework, ai-agents, autonomous-agents, durable-execution, model-context-protocol, multi-agent, tool-calling, agentic-ai, ai, claude, gemini, human-in-the-loop, nodejs.
Ranked #5838 out of 24846 indexed tools.
Ecosystem
Score Breakdown
682 stars → growing community
Last commit 29d ago → recently updated
0/1 issues closed → many open issues
3 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Matched Queries
From the README
<div align="center">
# Deuz SDK
**One TypeScript SDK. Models, agents, and swarms.**
[Documentation](https://deuz-sdk.tech/docs) · [Examples](./examples) · [What's new in 2.2](./docs/content/docs/reference/whats-new-2-2.mdx)
</div>
## Start building
```sh
npm install @deuz-sdk/core
```
Set `ANTHROPIC_API_KEY`, then run your first agent:
```ts
import { runAgent } from '@deuz-sdk/core/agent';
import { createAnthropic } from '@deuz-sdk/core/anthropic';
const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY });
const result = await runAgent({
model: anthropic('claude-opus-4-8'),
prompt: 'Explain how rainbows form in three sentences.',
maxSteps: 4,
});
if (result.status === 'completed') console.log(result.output);
```
Use Node.js 22+, or an edge runtime with Web APIs. Node integrations have separate imports.
## What ships
- **Models** — multiple providers, streaming, structured output, and tool calls.
- **Agents** — typed results, verification, approval Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.