Amazon launched the next generation of OpenSearch Serverless, a fully managed search and vector engine for customers building AI agents. The service scales from zero to thousands of requests per second and back to zero when idle, with AWS claiming up to 60% cost savings compared to OpenSearch Service clusters provisioned for peak capacity. Resources can be created in seconds, and capacity scales up to 20 times faster than the previous generation. The new version includes native integrations with AI development platforms Vercel and Kiro, letting developers deploy production-ready search and vector backends in minutes without managing infrastructure. AWS also introduced OpenSearch Agent Skills, a repository of skills that brings OpenSearch intelligence directly into agents built with Claude Code, Cursor, and Kiro. The next generation is generally available in all AWS commercial regions where OpenSearch Serverless is currently offered.
