--- title: Runtime instances: persistent compute for production AI... description: Amazon Bedrock AgentCore now offers runtime instances, a new persistent compute option built on managed EC2 infrastructure for production AI agents. Unlike the... canonical: https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore | daily.dev og:description: Amazon Bedrock AgentCore now offers runtime instances, a new persistent compute option built on managed EC2 infrastructure for production AI agents. Unlike the... og:url: https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg og:image: https://api.daily.dev/og/posts/eX8xT1XHg.png og:image:alt: Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore **[AWS](https://daily.dev/sources/aws)** · 8 min read · 2 upvotes · 0 comments ## Summary Amazon Bedrock AgentCore now offers runtime instances, a new persistent compute option built on managed EC2 infrastructure for production AI agents. Unlike the existing microVM option (limited to 8-hour invocations), runtime instances support sessions lasting up to 14 days, GPU acceleration, shared file systems for multi-agent collaboration, and session hibernate/resume. Multiple agents can run on the same host, share a session directory, and collaborate without direct API calls between them. The service supports Python 3.11–3.14, container images, and popular frameworks like CrewAI, LangGraph, LlamaIndex, and Strands. Pricing is standard EC2 rates plus an AgentCore management fee, and the feature is available in multiple AWS regions. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How long can a session persist with Amazon Bedrock AgentCore runtime instances? Sessions on Amazon Bedrock AgentCore runtime instances persist for up to 14 days, compared to the 8-hour limit on AgentCore runtime microVMs. This is achieved through AWS-managed EC2 infrastructure that supports session stop and restart, letting you hibernate a workflow and resume it later with state intact, useful for long-running or multi-day agent tasks. _Teams weighing long-running agent architectures can track infrastructure changes like this via daily.dev._ ### How can multiple AI agents share state and collaborate on Amazon Bedrock AgentCore? Multiple agents deployed to the same AgentCore runtime instance can collaborate through a shared file system tied to a session ID, without exchanging API calls or messages. One agent writes output to a shared session directory (for example /tmp/agentcore-session/{session-id}/) and another agent reads it directly, enabling patterns like a code writer agent and a code reviewer agent working on the same files. _Developers designing multi-agent workflows can follow patterns like this through daily.dev._ ### What instance types and operating systems does Amazon Bedrock AgentCore runtime instances support? At launch, runtime instances support Linux on both ARM64 and x86_64 architectures, with Python 3.11 through 3.14 runtimes including native code support, plus container image deployments. GPU-accelerated instance types are supported for compute-intensive tasks, and pricing follows standard EC2 rates plus an additional management fee for AgentCore orchestration. _Engineers evaluating GPU-backed agent infrastructure can stay current on options like this via daily.dev._ ## Similar posts on daily.dev - [Multi Agent Collaboration Gets Persistent Compute in Bedrock AgentCore](https://daily.dev/posts/multi-agent-collaboration-gets-persistent-compute-in-bedrock-agentcore-3ih0ur64c) · InfoQ · 0 upvotes · 0 comments - [Running deep research AI agents on Amazon Bedrock AgentCore](https://daily.dev/posts/running-deep-research-ai-agents-on-amazon-bedrock-agentcore-t8ow7kvyw) · AWS · 1 upvotes · 0 comments - [From 'Works on My Machine' to Production-Ready: Building AI Agents with Amazon Bedrock AgentCore](https://daily.dev/posts/from-works-on-my-machine-to-production-ready-building-ai-agents-with-amazon-bedrock-agentcore-bt6s0repy) · Pulumi · 1 upvotes · 0 comments - [Amazon Bedrock AgentCore is now generally available](https://daily.dev/posts/amazon-bedrock-agentcore-is-now-generally-available-myrlhbbds) · AWS · 1 upvotes · 0 comments - [Deploying Agentic AI Solutions with Infrastructure as Code](https://daily.dev/posts/deploying-agentic-ai-solutions-with-infrastructure-as-code-7udwr0zae) · Spacelift · 2 upvotes · 0 comments --- Tags: [#aws](https://daily.dev/tags/aws), [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock) [View this post on daily.dev](https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore","url":"https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg"},"datePublished":"2026-08-07T00:35:58.452Z","dateModified":"2026-09-13T21:33:23.944Z","description":"Amazon Bedrock AgentCore now offers runtime instances, a new persistent compute option built on managed EC2 infrastructure for production AI agents. Unlike the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7b466fc87812a1f3016f7c37bea23f9e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7b466fc87812a1f3016f7c37bea23f9e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"AWS","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"aws,ai-agents,langchain,amazon-bedrock","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore-ex8xt1xhg#faq","mainEntity":[{"@type":"Question","name":"How long can a session persist with Amazon Bedrock AgentCore runtime instances?","acceptedAnswer":{"@type":"Answer","text":"Sessions on Amazon Bedrock AgentCore runtime instances persist for up to 14 days, compared to the 8-hour limit on AgentCore runtime microVMs. This is achieved through AWS-managed EC2 infrastructure that supports session stop and restart, letting you hibernate a workflow and resume it later with state intact, useful for long-running or multi-day agent tasks. Teams weighing long-running agent architectures can track infrastructure changes like this via daily.dev."}},{"@type":"Question","name":"How can multiple AI agents share state and collaborate on Amazon Bedrock AgentCore?","acceptedAnswer":{"@type":"Answer","text":"Multiple agents deployed to the same AgentCore runtime instance can collaborate through a shared file system tied to a session ID, without exchanging API calls or messages. One agent writes output to a shared session directory (for example /tmp/agentcore-session/{session-id}/) and another agent reads it directly, enabling patterns like a code writer agent and a code reviewer agent working on the same files. Developers designing multi-agent workflows can follow patterns like this through daily.dev."}},{"@type":"Question","name":"What instance types and operating systems does Amazon Bedrock AgentCore runtime instances support?","acceptedAnswer":{"@type":"Answer","text":"At launch, runtime instances support Linux on both ARM64 and x86_64 architectures, with Python 3.11 through 3.14 runtimes including native code support, plus container image deployments. GPU-accelerated instance types are supported for compute-intensive tasks, and pricing follows standard EC2 rates plus an additional management fee for AgentCore orchestration. Engineers evaluating GPU-backed agent infrastructure can stay current on options like this via daily.dev."}}]} ```