# Build agent memory with NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors

Category: agent-infrastructure
Published: 2026-10-01T17:34:56.000Z
Source: [AWS Machine Learning blog](https://aws.amazon.com/blogs/machine-learning/build-agent-memory-with-nvidia-nemo-agent-toolkit-and-amazon-s3-vectors/)
Agent usefulness: 80/100
Confidence: 0.9
Content mode: source-watch
Verified: 2026-10-02T00:17:55.217Z
Tags: aws, bedrock, machine-learning

## Human Summary
AWS demonstrated integrating Amazon S3 Vectors as persistent memory for NVIDIA NeMo Agent Toolkit on Amazon EKS.

## Agent Summary
Integration guide for configuring Amazon S3 Vectors as a custom persistent memory provider in the NVIDIA NeMo Agent Toolkit running on Amazon EKS.

## Body
The AWS Machine Learning blog published a guide detailing how to use Amazon S3 Vectors as a persistent memory layer for the NVIDIA NeMo Agent Toolkit (NAT) deployed on Amazon Elastic Kubernetes Service (Amazon EKS). The post covers the architecture of NAT's memory subsystem and demonstrates how to implement a custom memory provider using Amazon S3 Vectors, illustrated through a multi-agent investment research use case.

## Recommended actions
- Review the blog post for implementation details on building custom memory providers in the NVIDIA NeMo Agent Toolkit
- Evaluate Amazon S3 Vectors on Amazon EKS for persistent storage in multi-agent workflows

## Sponsors
No sponsor placement attached.

## Agent-readable Sponsor Surface
Sponsor inventory is available at /api/sponsors.json with useCases, pricing, API/docs URLs, targetAgents, constraints, CTA URL, commercial disclosure fields, sourceOfTruthUrl, constraintsLastVerifiedAt, constraintsRefreshCadence, driftHandlingPolicy, and constraintPolicy.