AWS adds AgentCore memory to Agentic Retrieve
Understand this story
AWS has published a tutorial introducing how to add memoryConfiguration to the AgenticRetrieveStream request of Amazon Bedrock Managed Knowledge Base, using AgentCore memory as a retrieval source to support session resumption, fact extraction, and personalized retrieval. The integration is optional and backward compatible. According to the tutorial, the memory resource must be in the same AWS account as the knowledge base and in ACTIVE status; the example uses a managed knowledge base and AgentCore memory resource in the US West (Oregon) region (us-west-2), and the runtime environment requires Python 3.10 or later and Boto3 1.43.72 or later. The tutorial targets scenarios where multiple users share the same knowledge base and the same memory resource.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogBuild memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base
Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore memory now handle conversation storage, fact extraction, and retrieval of relevant facts when a memoryConfiguration is added to an AgenticRetrieveStream request, with userContext enforcing document ACLs in the same call. The post walks through building a multi-user employee assistant with Cognito identity, per-user memory namespaces, and IAM conditions that enforce per-user memory isolation, using trace events to confirm when the planner used memory.
Activity for this story
- Current comparable activity
- 5
- Peak comparable activity
- 10Nov 17 08:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.