Skip to content

Amazon Bedrock AgentCore

Amazon Bedrock AgentCore is a comprehensive platform for deploying and operating highly effective AI agents securely at scale. The platform includes a Python SDK and Starter Toolkit that work together to help you build, deploy, and manage agent applications.

GitHub commit activity License PyPI version

Preview Status

Amazon Bedrock AgentCore is currently in preview release. APIs may change as we refine the platform.

🚀 From Local Development to Bedrock AgentCore

# Your existing agent (any framework)
from strands import Agent
# or LangGraph, CrewAI, Autogen, custom logic - doesn't matter

def my_local_agent(query):
    # Your carefully crafted agent logic
    return agent.process(query)

# Deploy to Bedrock AgentCore
from bedrock_agentcore import BedrockAgentCoreApp
app = BedrockAgentCoreApp()

@app.entrypoint
def production_agent(request):
    return my_local_agent(request['query'])  # Same logic, enterprise platform

production_agent.run()  # Ready to run on Bedrock AgentCore

What you get with Bedrock AgentCore:

  • ✅ Keep your agent logic - Works with Strands, LangGraph, CrewAI, Autogen, custom frameworks.
  • ✅ Zero infrastructure management - No servers, containers, or scaling concerns.
  • ✅ Enterprise-grade platform - Built-in auth, memory, observability, security.
  • ✅ Production-ready deployment - Reliable, scalable, compliant hosting.

Your function is now a production-ready API server with health monitoring, streaming support, and AWS integration.

Platform Components

🔧 Bedrock AgentCore SDK

The SDK provides Python primitives for agent development with built-in support for:

  • Runtime: Lightweight wrapper to convert functions into API servers
  • Memory: Persistent storage for conversation history and agent context
  • Tools: Built-in clients for code interpretation and browser automation
  • Identity: Secure authentication and access management

🚀 Bedrock AgentCore Starter Toolkit

The Toolkit provides CLI tools and higher-level abstractions for:

  • Deployment: Containerize and deploy agents to AWS infrastructure
  • Gateway Integration: Transform existing APIs into agent tools
  • Configuration Management: Manage environment and deployment settings
  • Observability: Monitor agents in production environments

Platform Services

Amazon Bedrock AgentCore provides enterprise-grade services for AI agent development:

  • 🚀 AgentCore Runtime - Serverless deployment and scaling for dynamic AI agents
  • 🧠 AgentCore Memory - Persistent knowledge with event and semantic memory
  • 💻 AgentCore Code Interpreter - Secure code execution in isolated sandboxes
  • 🌐 AgentCore Browser - Fast, secure cloud-based browser for web interaction
  • 🔗 AgentCore Gateway - Transform existing APIs into agent tools
  • 📊 AgentCore Observability - Real-time monitoring and tracing
  • 🔐 AgentCore Identity - Secure authentication and access management

Getting Started

  • SDK Quickstart

    Get started with the core SDK for agent development

    Start coding

  • Toolkit Guide

    Learn to deploy and manage agents in production

    Deploy agents

  • API Reference

    Detailed API documentation for developers

    Explore APIs

Features

  • Zero Code Changes: Your existing functions remain untouched
  • Production Ready: Automatic HTTP endpoints with health monitoring
  • Streaming Support: Native support for generators and async generators
  • Framework Agnostic: Works with any AI framework (Strands, LangGraph, LangChain, custom)
  • AWS Optimized: Ready for deployment to AWS infrastructure
  • Enterprise Security: Built-in identity, isolation, and access controls