New: Decision Runtime — closed-set judgments for Agent OS. Read the guide →
HazelJS LogoHazelJS

TypeScript Multi-Agent Framework

A multi-agent framework coordinates specialized agents under shared identity, execution, and authorization rules. HazelJS supports coordinator patterns with AgentGraph, SupervisorAgent, @Delegate, and A2A — each tool call still passes Gatekeeper.

Get Started with HazelJSView on GitHub

01Example architecture

User
 ↓
Coordinator Agent
 ├── Research Agent
 ├── Support Agent
 ├── Billing Agent
 └── Operations Agent

02How HazelJS handles the hard parts

  • Identity: Agent DNA + in-process AgentRegistry
  • Communication: @Delegate, supervisor routing, optional A2A
  • Execution: AgentRuntime with shared durable run stores
  • Authorization: Gatekeeper per tool — cross-agent does not bypass policy
  • Lifecycle: AgentOS / hazeld start, pause, delete
  • Failures: durable suspend, HITL resume, run cancel/resume CLI
  • Observability: JSONL timelines, hazel logs, inspector

03Register and execute an agent

typescript
import { AgentRuntime, createMockLlmProvider } from '@hazeljs/agent';

const runtime = new AgentRuntime({
  llmProvider: createMockLlmProvider(),
  enableRetry: false,
});
runtime.registerAgent(SupportAgent);

const result = await runtime.execute('support-agent', 'Check open orders', {
  maxSteps: 8,
  loop: { maxIterations: 8, successScore: 95 },
});