Home icon

Amazon ElastiCache re:Invent 2025 recap

Database Blog



This article recaps Amazon ElastiCache announcements and sessions from AWS re:Invent 2025, highlighting new capabilities and customer success stories.

  • ElastiCache for Valkey achieves 95% recall with lowest latency vector search for AI workloads
  • Scopely scaled MONOPOLY GO! to 2.1M writes/second using DynamoDB and ElastiCache Serverless
  • Valkey reduces memory usage by 40%, improves scaling by 230%, and cuts pricing by 33%
  • Semantic caching reduces AI latencies from seconds to milliseconds while cutting model costs
  • ElastiCache Serverless handles production-scale workloads with automatic scaling
  • Database Savings Plans offer up to 35% cost reduction with 1-year commitment
  • New connectors enable Valkey for agentic memory via Mem0, LMCache, and LangGraph frameworks

ElastiCache continues evolving as a high-performance, cost-efficient caching solution for AI, gaming, and enterprise applications.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Dec 1
2025
Top announcements of AWS re:Invent 2025
Jan 2
2026
AWS re:Invent 2025 Recap for Automotive and Manufacturing
Nov 18
2025
Amazon ECS at AWS re:Invent 2025
Mar 5
2026
AWS re:Invent 2025 recap for government agencies

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.