AWS 发布新一代 AgentCore runtime：硬件隔离会话与按用量计费
Run agents securely and efficiently with the next generation AgentCore runtime
AWS 这波更新给跑长任务的企业智能体补上了数据隔离这块短板，计费改成纯按用量，智能体闲着不烧钱。如果你的智能体要跑几小时、调一堆工具，又对数据安全有合规要求，新 runtime 值得测一测。
AWS 更新了 Amazon Bedrock AgentCore runtime，面向需要连续运行数小时、代替用户执行多步任务的企业级 AI 智能体。新版本提供硬件级隔离会话，并支持冷启动加速和更大的单会话算力。
技术层面，新一代 runtime 将隔离边界从会话本身扩展到数据层面，降低智能体在多步执行中泄露用户数据的风险。计费模式改为纯按用量计费，智能体闲置不产生费用，这对长时间运行、间歇等待工具调用的智能体工作负载尤为友好。
在企业部署智能体时，会话隔离、数据隔离和成本可控是常见的三大顾虑，此次更新直接针对这三点。开发者若用 AWS 部署 LangGraph、Strands 等框架构建的智能体，可以关注新 runtime 在吞吐和启动延迟上的表现。
Run agents securely and efficiently with the next generation AgentCore runtime
AI agents now run multi-step workloads for hours and act on behalf of users, raising the bar for secure, scalable agent compute. Learn how the next generation of Amazon Bedrock AgentCore runtime delivers hardware-isolated sessions with faster starts, more compute, usage-based billing, and isolation that now extends to your data.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include AgentCore, AWS, Bedrock, 智能体.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.