← Back
AWS ML Blog

Run agents securely and efficiently with the next generation AgentCore runtime

•9 min read•
#agents#deployment#bedrock
Level:Advanced
For:AI Engineers
✦TL;DR

Amazon Bedrock AgentCore’s new runtime delivers hardware‑isolated Firecracker MicroVM sessions that start up to 15× faster, can scale to 4× more compute, and run up to 68 % more efficiently while preserving isolation. The updates let agents dynamically increase memory and CPU within each session, supporting heavier workloads such as code compilation, browser automation, and local model inference. This enables enterprises to run thousands of concurrent, secure agent sessions without the traditional trade‑offs between latency, cost, and security. Engineers can now build production‑grade AI agents that scale elastically and remain auditable.

⚡ Key Takeaways

  • Sessions now start up to 15× faster than previous AgentCore runtimes.
  • Each session runs in its own hardware‑isolated Firecracker MicroVM with unique identity, policy, and audit trail.
  • Compute capacity per session can scale up to 4× higher, allowing larger workloads.
  • Runtime efficiency improves by up to 68 % while keeping isolation intact.
  • Agents can dynamically adjust memory and compute within the isolated session to match workload demands.
💡 Why It Matters

Engineers can ship high‑throughput, secure AI agents that meet enterprise compliance requirements without incurring cold‑start latency or excessive idle costs, accelerating time‑to‑value for AI‑driven products.

✅ Practical Steps

  1. Apply the concepts from this article to your own system design.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod

AWS ML Blog•#deployment

Introducing Unity Gateway Insights

Databricks Blog•#deployment

Introducing Gemini 4 Neon

Google DeepMind•#llm

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

Hugging Face Blog•#llm

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