AWS gives AI agents four times more compute in Bedrock AgentCore

Nov 12, 2026
Agent sessions can now use up to 8 virtual CPUs and 32GB of memory, idle agents scale to zero, and new baseline pricing targets always-on agents.

Amazon Web Services has upgraded the runtime of Amazon Bedrock AgentCore, its service for running AI agents, with up to four times more computing power per session, InfoWorld reported. Each agent session can now use up to eight virtual CPUs and 32GB of memory, with container images of up to 10GB.

AWS says that lets developers run heavier agent jobs inside the isolated environment, such as compiling large codebases, driving web browsers or running small models locally. The runtime now reclaims unused memory within minutes and lets idle agents scale to zero, which AWS says can cut memory use per session by up to 68% for agents that pause between turns. A new baseline pricing option sets a minimum memory allocation for always-on agents while letting them burst to four times that.

Agents can also now save their work directly to file systems such as Amazon S3 buckets, something companies previously had to build themselves.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

Industry analysis

2025 Global Business Services Agenda: Gen AI Takes Center Stage

The Hackett Group

This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.