← Back
AWS ML Blog

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

•14 min read•
#agents#nvidia
✦TL;DR

NVIDIA’s NeMo Agent Toolkit (NAT) now supports Amazon S3 Vectors as a persistent memory provider, enabling agents to retain contextual knowledge across sessions. By deploying NAT on Amazon EKS, the memory subsystem can be configured to use S3 Vectors for low‑latency vector retrieval, while still leveraging Kubernetes’ scalability and fault tolerance. The article walks through implementing a custom memory provider, detailing the required configuration changes and deployment steps. This integration allows agents to persist embeddings in S3, reducing the need for in‑memory storage and simplifying state management in production workloads.

⚡ Key Takeaways

  • NAT’s memory subsystem can be extended to use Amazon S3 Vectors as a durable vector store for agent memory.
  • The custom memory provider requires registering an S3 Vectors client and configuring the memory service via

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

Mathematical proof, powered by AI. And no hallucinations!

Amazon Science•#agents

AI’s GPU focus meets a CPU reality check at Dell and AMD

SiliconANGLE AI•#agents

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING