ElastiCache Serverless for Valkey adds vector, full-text and hybrid search, with up to 99% vector recall and writes searchable within microseconds
Search moves into the cache layer, removing the need for a separate vector store in some cases. What it suits and where it is available.
// Key points
- ElastiCache Serverless for Valkey adds vector, full-text and hybrid search plus server-side aggregations, combining search types in one query with tunable recall.
- AWS cites latency as low as microseconds, up to 99% recall for vector search and billions of queries per day; updates become searchable within microseconds of a write completing.
- AWS suggests giving each agent, session or task its own datastore for memory and context retrieval, ready in seconds and billed only for usage.
- It is available in all commercial AWS Regions, GovCloud (US) and the European Sovereign Cloud, on ElastiCache version 9 for Valkey.
Builder's takeFor something like AI Cloud Drive, where a file must be searchable right after upload, write-to-search latency matters more than the recall figure. I would not move the main index, but I would try this kind of usage-billed store for agents' short-term memory and session context, one per task and thrown away after, leaving the main vector store for long-lived data.
// Background · from #AI agents
Full timeline →- Nov 11 NVIDIA donates Agent Substrate to the CNCF Sandbox: idle agent sessions are snapshotted with memory and filesystem, at 10x the density of standard containers
- Nov 11 Amazon Bedrock AgentCore launches a Web Search API: ranked web results in one call at $7 per 1,000 queries
- Nov 10 AWS launches Nitro Sandboxes: each EKS pod, ECS task or lightweight VM gets its own hardware-isolated VM, enabled with a one-line change at no additional charge