Japanese telco KDDI left an Elasticsearch cluster unsecured, leaking login details for 142 million managed email accounts. The misconfiguration went unnoticed for weeks before security researchers alerted KDDI, forcing the company to lock down its database and warn affected users.

This article describes an Elasticsearch-based system for long-term agent memory, dividing data into episodic, semantic, and procedural indices with tailored aging and update rules. It uses hybrid retrieval—BM25 plus dense vectors fused by RRF and refined with a cross-encoder reranker—alongside per-user DLS, supersession, decay, and an LLM-driven consolidation process to keep memory accurate and scalable.