MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaces
This addresses the challenge of decoherence in long-term memory for AI agents, though it appears incremental as it builds on existing database technologies like PostgreSQL and pgvector.
The paper tackles the problem of maintaining coherence across time, meaning, and relation in long-term computational memory by introducing MemoriesDB, a unified data architecture that combines time-series, vector, and graph properties in a single append-only schema, with a prototype demonstrating scalable recall and contextual reinforcement.
We introduce MemoriesDB, a unified data architecture designed to avoid decoherence across time, meaning, and relation in long-term computational memory. Each memory is a time-semantic-relational entity-a structure that simultaneously encodes when an event occurred, what it means, and how it connects to other events. Built initially atop PostgreSQL with pgvector extensions, MemoriesDB combines the properties of a time-series datastore, a vector database, and a graph system within a single append-only schema. Each memory is represented as a vertex uniquely labeled by its microsecond timestamp and accompanied by low- and high-dimensional normalized embeddings that capture semantic context. Directed edges between memories form labeled relations with per-edge metadata, enabling multiple contextual links between the same vertices. Together these constructs form a time-indexed stack of temporal-semantic surfaces, where edges project as directional arrows in a 1+1-dimensional similarity field, tracing the evolution of meaning through time while maintaining cross-temporal coherence. This formulation supports efficient time-bounded retrieval, hybrid semantic search, and lightweight structural reasoning in a single query path. A working prototype demonstrates scalable recall and contextual reinforcement using standard relational infrastructure, and we discuss extensions toward a columnar backend, distributed clustering, and emergent topic modeling.