Hippocampus: An Efficient and Scalable Memory Module for Agentic AI

Agentic AI systems require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems rely on the dense vector databases, knowledge-graph traversal, or hybrids, which incur high retrieval latency and poor storage scalability. We introduce HIPPOCAMPUS, an agentic memory management system that uses compact binary signatures for semantic search and lossless token-ID streams for exact content reconstruction. Its core is a Dynamic Wavelet Matrix (DWM) that compresses and co-indexes both streams to support ultra-fast search in the compressed domain, thus avoiding costly dense-vector or graph computations. For a fixed tokenizer vocabulary, the storage footprint of this design grows linearly with memory size, making it suitable for long-horizon agentic deployments. Empirically, across LoCoMo and LongMemEval, HIPPOCAMPUS achieves end-to-end retrieval latency that is comparable to or lower than the evaluated agentic memory baselines, with 1.1X–31.5X speedups over the evaluated baselines, and reduces per-query token footprint by 1.1X–14.5X, while maintaining competitive task accuracy.