Deuz SDK

One TypeScript SDK. Models, agents, and swarms.

Documentation · Examples · What's new in 2.3

Start building

npm install @deuz-sdk/core

Set ANTHROPIC_API_KEY, then run your first agent:

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.

The repository has twenty examples: 01–06 call Anthropic with your key, and 07–20 run without a key or network.

What ships

• Models — multiple providers, streaming, structured output, tool calls, realtime voice, and batch requests.
• Agents — typed results, verification, approvals, resumable runs, and memory, chat and model fail-over.
• Swarms — task dependencies, runtime spawning, shared blackboards, rounds, and SQLite, Postgres or Redis persistence.
• Operations — leases, drain, cross-process cancel and recovery, persistent budgets, schedules, goal records, and a headless preview.
• Evolve — evolutionary program search with a mandatory budget and zero-call resume.
• Context — memory, retrieval, compaction, 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.

Core has zero required runtime dependencies; integrations use optional peers. Without a lease provider, drive each swarm or native agent run from one process; uncertain external effects require reconciliation before retry.

Agents · Swarms · React · Changelog

New in 2.3

• Native runs — memory, chat and model fail-over, and one path for every tool call: policy, approval, budget admission and an effect receipt.
• Interop — the MCP 2026-07-28 client, an MCP server, and A2A in both directions.
• Models — realtime voice on OpenAI Realtime and Gemini Live, provider batch requests, model profiles, a stable request prefix for Claude 5.x thinking, usage billed once, and models without a price under USD budgets.
• Redis — backends for swarms, leases, native runs, schedule claims and budgets.
• UI — useChat drives native agent runs, with their approvals and client tools.
• Goals and evals — goal records, versioned eval suites, and a headless preview for scripts and CI.

Nothing in 2.3 was run against a live provider or third-party service; it is tested offline. Read What's new in 2.3 for the upgrade notes and known limits before you deploy.

Add the coding-agent skill

npx skills add Deuz-AI/Deuz-SDK

API references and implementation guidance for your coding agent. Explore the skill →

MIT · Built by Umutcan Edizaslan