Deuz-SDK
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.
Links
README
From the repo.
Deuz SDK
One TypeScript SDK. Models, agents, and swarms.
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.
What ships
- Models — multiple providers, streaming, structured output, and tool calls.
- Agents — typed results, verification, approvals, and resumable runs.
- Swarms — task dependencies, bounded parallel work, reducers, and SQLite persistence.
- Context — memory, retrieval, compaction, and MCP tools.
- Control — shared execution policies, budget accounting, traces, and optional React bindings.
Core has zero required runtime dependencies; integrations use optional peers. In 2.1, each swarm run has one executor, and uncertain external effects require reconciliation before retry.
Agents · Swarms · React · Changelog
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
Built with Opus 4.8 / 5, Fable 5 / 5.1, and GPT-6 Astra Ultra.
Collected info
- ★ 697 stars
- ⎇ 1 forks
- Language: TypeScript
- Source updated: 9/20/2026