AgentCore Memory: Episodic Memory & Patterns for Production Agents | AWS Show and Tell

In this episode of "AWS Show and Tell — What's New in Amazon Bedrock AgentCore Memory", we'll dive into the latest memory capabilities that make your AI agents smarter, more personalized, and truly context-aware across every interaction. Through hands-on demonstrations, you'll learn how to implement Episodic Memory to enable agents that reflect and learn across past conversations, leverage Streaming to read any new events from Long term memory, and apply proven memory patterns that combine semantic, user preference, summary, and episodic strategies for maximum impact. We'll walk through practical examples showing how AgentCore Memory's built-in strategies work together to transform stateless agents into intelligent assistants that remember what matters. You'll see how to customize memory strategies, which strategies to use for conversational agents, task-oriented workflows, and multi-agent systems, and deliver personalized experiences at scale — all without managing any infrastructure. Get ready to give your agents a memory that makes every conversation count! Amazon Bedrock AgentCore samples: https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials/04-AgentCore-memory Amazon Bedrock AgentCore SDK: https://github.com/aws/bedrock-agentcore-sdk-python Amazon Bedrock AgentCore starter kit: https://github.com/aws/bedrock-agentcore-starter-toolkit