Deuz-SDK

TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG

What is Deuz-SDK?

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.

Overview of Deuz-SDK

What it is

Deuz-SDK is a TypeScript AI SDK and agent framework with zero required runtime dependencies. It is designed for building production AI agents and multi-agent swarms. The SDK supports durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, and realtime voice. It provides a single streaming API that works with 29 model providers including Claude, GPT, Gemini, Grok, DeepSeek, and Ollama. The SDK runs on Node.js (22+), Bun, Deno, and edge runtimes.

Key features

  • Models: multiple providers, streaming, structured output, tool calls, realtime voice, and batch requests.
  • Agents: typed results, verification, approvals, resumable runs, memory, chat and model fail-over.
  • Swarms: task dependencies, runtime spawning, shared blackboards, rounds, and persistence via SQLite, Postgres, or Redis.
  • Context: versioned memory, a context compiler with working memory, retrieval, compaction, transcript search, and MCP tools.
  • Interop: an MCP server and A2A to call other agents and serve your own.
  • Control: shared execution policies, budget accounting, traces, eval suites, and optional React bindings.

Use cases

  • Building production AI agents with durable execution and long-term memory.
  • Creating multi-agent swarms with task dependencies and shared blackboards.
  • Implementing hybrid RAG with versioned memory and context compilation.
  • Running agent-written code in a local Docker sandbox (preview).
  • Using MCP client/server and A2A for agent interoperability.

Getting started

shnpm install @deuz-sdk/coreSet the ANTHROPIC_API_KEY environment variable, then run a basic agent (see the repository README for the full example).To add the coding-agent skill:shnpx skills add Deuz-AI/Deuz-SDK

License and pricing

MIT license, open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/deuz-aideuz-sdk.svg)](https://yunodb.com/tools/deuz-aideuz-sdk?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/deuz-aideuz-sdk?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/deuz-aideuz-sdk.svg" alt="Featured on YunoDB" height="20"></a>