Multi-Agent Orchestrator framework

Looking for details on Amazon Bedrock’s multi-agent collaboration capability announced during Matt Garman's keynote at re:Invent 2024?

Visit the Amazon Bedrock Agents page to explore how multi-agent collaboration enables developers to build, deploy, and manage specialized agents designed for tackling complex workflows efficiently and accurately.

Key Features

• Multi-Agent Orchestration: Seamlessly coordinate and leverage multiple AI agents in a single system
• Dual language support: Fully implemented in both Python and TypeScript
• Intelligent intent classification: Dynamically route queries to the most suitable agent based on context and content
• Flexible agent responses: Support for both streaming and non-streaming responses from different agents
• Context management: Maintain and utilize conversation context across multiple agents for coherent interactions
• Extensible architecture: Easily integrate new agents or customize existing ones to fit your specific needs
• Universal deployment: Run anywhere - from AWS Lambda to your local environment or any cloud platform

Quick Installation

Get up and running in minutes: See our Quick Start Guide for more details.

How it works

See our How it works for more details.

Code Samples & Deployment

Explore our code samples and deployment options:

• Local Development Guide
• AWS Lambda Deployment (TypeScript)
• AWS Lambda Deployment (Python)
• Chainlit (Python)
• FastAPI streaming (Python)

Powerful Agents

Discover our built-in agents:

• New Supervisor Agent
• New Open AI Agent
• New Bedrock Inline Agent
• New Bedrock Flows Agent
• Bedrock LLM Agent
• Amazon Bedrock Agent
• Lex Bot Agent
• AWS Lambda Agent
• Bedrock Translator Agent
• Comprehend Filter Agent
• Chain Agent Learn how to create your own custom agents.