Back to directory

Guidance for Multi-Agent Orchestration using Amazon Bedrock AgentCore on AWS

An AWS reference guidance showing how to build and deploy a multi-agent customer-support system using Amazon Bedrock AgentCore and the Strands Agents SDK.

Guidance for Multi-Agent Orchestration using Amazon Bedrock AgentCore on AWS

This guidance demonstrates how to build and deploy multi-agent systems on Amazon Bedrock AgentCore with the Strands Agents SDK. AgentCore provides managed runtime, memory, identity and observability services so a team does not have to build that infrastructure itself, while Strands lets a developer define agents with Python decorators.

A worked customer-support example shows a supervisor agent coordinating four specialized sub-agents, with session isolation in per-user microVMs, APIs and Lambda functions exposed as MCP endpoints through AgentCore Gateway, Cognito-based authentication, and OpenTelemetry and CloudWatch observability. A React front end streams responses over server-sent events, and the whole stack deploys through AWS CDK. It is MIT-0 licensed.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.