Review
Aug 2026
A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware
OreoLook (formerly lixSearch), an open-source answer engine using automated browser agents and provider-routed LLM inference, is developed, which presents a three-layer caching architecture that deduplicates embedding computations across sessions.
A. Bhattacharya, Nihal Gazi
· 0 citations