Mohammed
Efaz

MeReader: Offline, Privacy-Preserving, Progress-Aware AI Reading Assistant

MeReader is a privacy-preserving, offline, and progress-aware AI assistant designed to function as a contextual companion for narrative reading on consumer hardware. Unlike conventional LLM-based systems that process documents in an all-texts-at-once fashion -- risking narrative spoilers -- MeReader confines both retrieval and generation to the reader's distinct position in the text. The system integrates a hybrid retrieval architecture combining vector similarity, BM25, and summary embeddings to ensure high fidelity to the reader's current context. Evaluated across classical English novels using quantitative comprehension metrics and qualitative LLM-based judging, the results identify a quality-latency frontier showing that mid-sized local models (2B--4B) can achieve comprehension parity with larger counterparts while maintaining acceptable response quality. The progress-aware boundary mechanism prevents future-content leakage without compromising retrieval correctness, demonstrating that a localized, privacy-centric approach can augment the digital reading experience as a viable alternative to cloud-dependent services.