arXiv:2607.18439v2 Announce Type: replace Abstract: The Hopfield network established that static memories can be stored as energy minima of an energy-based model. Real intelligent agents, however, must navigate sequences of memories rather than isolatedcsnapshots. Biological cortex addresses this through a separation of timescales, where fast synaptic dynamics encode individual states while slow neuromodulatory processes govern transitions between them. Inspired by this organization, we propose a sequential memory architecture that is fully continuous and admits exponential storage capacity. The architecture is programmable, since the transition structure is carried by a mechanism that is decoupled from the stored patterns, driven by the input context, and free to be chosen, optimized, or learned from data. Specifically, we construct an autonomous three-timescale dynamical system with three coupled layers. A fast Kuramoto layer stores phase patterns as exponentially stable phase-locked configurations, an intermediate recognition layer sets the dwell times, and a slow attention layer routes the transitions. We analyze the stability, dwell time, and capacity of the system, and we validate the dynamics through numerical simulations of sequential memory retrieval.