Conversational agents in long-term healthcare often lack the ability to retain and recall information across sessions, leading to fragmented and impersonal interactions. This paper presents a scalable hybrid memory system that addresses this limitation by combining short-term memory for real-time dialogue with a persistent long-term memory layer based on MongoDB. The system, developed within the SALUS project, employs a dual-agent architecture: GenAI A handles immediate conversations using a short-term buffer, while GenAI B manages memory consolidation by generating and storing reflections—semantic summaries of past interactions. Inspired by generative agent models, this design enables thematic memory organization, deferred storage, and keyword-based retrieval. Validated through use cases involving elderly patients and routine care scenarios, the architecture improves personalization, minimizes redundancy, and fosters trust in multi-session dialogues. The modular and extensible design supports future enhancements such as semantic search, explainable AI, and integration with socio-sanitary platforms like SALUS.