Today’s voice assistants remain fundamentally constrained by their stateless architecture, where each exchange is treated as an isolated incident, precluding meaningful long-term personalization. This limitation results in repetitive, context-blind dialogues that degrade user experience. This paper introduces an architectural blueprint for a lightweight, retention-augmented voice assistant, designed as a proof-of-concept to address this challenge. Our architecture prioritizes user privacy and transparency through on-device Automatic Speech Recognition via Whisper and a human-readable, file-based memory system, using a zero-shot Natural Language Understanding model (Google Gemini) for rapid prototyping. To rigorously test our retention mechanism, we introduce the Personalization Success Rate (PSR) as a novel evaluation metric. In a controlled evaluation with 150 scripted scenarios, our system achieved an 88% PSR, starkly contrasting with a 0% for the stateless baseline. This study validates the feasibility of achieving significant personalization gains with a simple, explicit memory model, providing a strong foundation and a clear roadmap for future work on scalable, adaptive, and privacy-preserving dialogue systems.