AI · Official
AWS Makes Next-Gen AgentCore Runtime the Default for New Deployments
AWS What's New ·
At a glance
Amazon Web Services has made the next generation of its AgentCore runtime, a hosting environment for AI agents, the default for newly created runtimes starting today. Idle agents now scale down to zero compute, and sessions restore quickly from saved snapshots of initialized agents.
Key points
- Sessions can use up to 8 vCPUs and 32 GB of memory and support container images up to 10 GB.
- On a 2 GB image, sessions start in under 2 seconds at P75, down from 29.7 seconds before.
- For multi-turn agents, billed memory per session can drop by up to 68%.
- Existing runtimes stay on the current version until moved, and users can choose V1 or V2 with a setting.
Why it matters
This change affects how fast and how cheaply companies can run AI agents.
Original source
The next generation AgentCore runtime is now the default
AWS What's New · Nov 12, 14:00 KST
Read on AWS What's New ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to AWS What's New.
Amazon Web Services · Ranking and more news
More from this field
- AWS Quick Adds Chat-Built Flows, Updated Web App, and Teamwork Among Agents
AWS Quick added updates that let a team turn one person's work routine into a shared, repeatable process. Flows can now be built and changed entirely in chat, and they can run from the web, desktop, or mobile app. Agents working together can also give more complete answers.
Amazon AWS Machine Learning blog · Nov 21, 10:06 KST - Amazon Bedrock Web Search Adds Five Languages and Country-Based Results
Amazon's Web Search tool for Bedrock, which gives AI agents cited, up-to-date web results, now supports Spanish, French, German, Italian, and Japanese, plus non-US English. A new optional country field can also steer results toward sources from a specific country. Existing customers get the language update automatically, and pricing stays the same in every language.
AWS What's New · Nov 21, 09:17 KST - AWS Adds Shared Cache Skill to Cut Self-Hosted LLM Cost and Latency
AWS wrote about a shared cache that lets self-hosted AI models reuse saved work across servers, aiming to cut cost and wait time. The post shows how a coding agent can help set it up. Amazon says it can cut inference cost by up to 40% and first-token delay by up to 80%.
Amazon AWS Machine Learning blog · Nov 21, 09:14 KST - Can AI Really Find Black Friday TV Deals? A BBC Test Says Not Yet
A BBC team tested four popular AI chatbots to see if they could find a good Black Friday deal on a 55-inch TV. The results were mixed, with many links broken or out of date.
BBC News · Nov 21, 09:06 KST