awslabs/agentcore-samples

Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.

What it solves

This repository provides a collection of examples and tutorials for Amazon Bedrock AgentCore, a framework-agnostic and model-agnostic infrastructure designed to deploy and operate AI agents securely and at scale. It removes the operational burden of building specialized agent infrastructure, allowing developers to use their preferred LLM and agent framework (such as CrewAI, LangGraph, or LlamaIndex) without rewriting code.

How it works

AgentCore acts as a supporting infrastructure layer. The repository demonstrates how to use the AgentCore CLI to scaffold, develop locally, and deploy agents to the Amazon Bedrock AgentCore runtime. It provides samples across several key capabilities:

  • Runtime: A serverless environment for deploying agents and tools.
  • Gateway: A tool that converts APIs and Lambda functions into MCP-compatible tools.
  • Identity & Policy: Managed identity and access management (IAM) and fine-grained access control using Cedar policies.
  • Memory: Infrastructure for personalized agent experiences.
  • Tools: Built-in utilities like Code Interpreter, Browser Tool, and Web Search.
  • Observability & Evaluation: Tools for tracing, debugging, and using LLM-as-a-Judge for both on-demand and online evaluation.

Who it’s for

Developers and architects building production-ready agentic AI applications who want to deploy their agents on AWS without being locked into a specific agent framework or model.

Highlights

  • Framework Agnostic: Supports Strands, LangGraph, CrewAI, LlamaIndex, and others.
  • Model Agnostic: Works with any Large Language Model.
  • C’s CLI-driven Workflow: Streamlined project creation, local development with hot reload, and one-command deployment.
  • Comprehensive Samples: Includes end-to-end applications, infrastructure-as-code templates (CDK, Terraform), and integration examples for identity providers like Okta and Entra.

Related

  • Project
    aws/bedrock-agentcore-starter-toolkit

    A Python-based starter toolkit for deploying and operating scalable, secure AI agents on Amazon Bedrock AgentCore using any open-source framework.

  • Project
    awslabs/amazon-bedrock-agent-samples

    A collection of reference implementations and best practices for building single and multi-agent AI assistants using Amazon Bedrock Agents.

  • Project
    langchain-ai/langchain-aws

    A collection of LangChain and LangGraph components that integrate AWS services like Bedrock, SageMaker, and DynamoDB for building AI agents and RAG applications.

  • Project
    aws/bedrock-agentcore-sdk-python

    A Python SDK for deploying local AI agents to Amazon Bedrock AgentCore, providing serverless infrastructure, enterprise security, and integrated tools like memory and code execution.

  • Project
    awslabs/fullstack-solution-template-for-agentcore

    A full-stack starter template for AgentCore that provides a secured React frontend and AWS infrastructure to accelerate the deployment of AI agent applications.