# AWS boosts Bedrock AgentCore runtime compute capacity to speed up AI agent development

DevFeed: [AWS boosts Bedrock AgentCore runtime compute capacity to speed up AI agent development](<https://devfeed.tech/articles/aws-boosts-bedrock-agentcore-runtime-compute-capacity-to-speed-up-ai-agent-development-130251.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4247866/aws-boosts-bedrock-agentcore-runtime-compute-capacity-to-speed-up-ai-agent-development.html>)

Author: Anirban Ghoshal

Published: 2026-11-12T12:38:52Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-development](<https://devfeed.tech/tags/ai-agent-development.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [compute](<https://devfeed.tech/tags/compute.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [faster](<https://devfeed.tech/tags/faster.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [memory](<https://devfeed.tech/tags/memory.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [speed](<https://devfeed.tech/tags/speed.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

## AI overview

AWS says Amazon Bedrock AgentCore sessions can now use up to 8 vCPUs, 32GB of memory and 10GB container images, with startup under two seconds regardless of image size. The update also reclaims unused memory within minutes and scales idle agents to zero; for multi-turn agents with pauses, AWS reports up to 68% lower memory use per session. Baseline pricing sets a minimum memory allocation while allowing bursts up to four times that level. Developers can mount and save agent files dynamically, including to Amazon S3, through FUSE. These changes may help run larger workloads and reduce idle-resource costs, but scale-to-zero can add resume latency and does not remove charges for storage, model calls or tools. Resumption state and credentials need testing, and baseline costs depend on setting and monitoring capacity appropriately. AWS says the capabilities are available in 19 Regions.

## Source excerpt

AWS on Thursday said that it was upgrading the runtime layer of Amazon Bedrock AgentCore with greater compute capacity, more efficient memory utilization, and faster startup times to help enterprises deploy and scale AI agents more quickly and cost-effectively. The greater compute capacity includes support for up to four times more compute than the previous version, with each session now supporting up to eight virtual CPUs (vCPUs) and 32GB of memory, the hyperscaler said in a statement. In addition, the runtime supports container images of up to 10GB, it further said, adding that these upgrades will allow developers to run more demanding agent workloads, including large codebase compilations, browser-driven workflows, and local model inference. As for memory utilization, the new updates will enable AgentCore runtime to reclaim unused memory within minutes of an agent releasing it and allow idle agents to scale to zero. This will help enterprises reduce the cost of running agents, particularly those that spend considerable time waiting for model responses, tool calls, or human intervention, the hyperscaler said. For multi-turn agents with natural pauses between interactions, this can reduce memory consumption per session by up to 68%, it added. Separately, in order to support always-on agents, the hyperscaler has introduced baseline pricing as part of the updates. Baseline pricing, according to the hyperscaler, sets a minimum memory allocation per session while allowing workloads to burst up to four times that baseline when additional capacity is needed. That predictability in pricing will allow enterprises to maintain always-on agent sessions without paying for peak capacity upfront while retaining the flexibility to scale when demand increases, it said. AWS has also extended the runtime's isolation capabilities beyond compute to the data that agents access and generate during execution by allowing developers to dynamically mount and save agent work to filesystems,