MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaces

TL;DR

MemoriesDB is a unified, long-term memory architecture combining temporal, semantic, and relational data in a graph structure, enabling efficient retrieval and reasoning over extended periods.

Contribution

It introduces a novel data model that integrates time, meaning, and relations into a single graph-based memory system built on PostgreSQL.

Findings

Supports scalable, efficient long-term memory retrieval

Enables hybrid semantic search and structural reasoning

Demonstrates effective contextual reinforcement in prototype

Abstract

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.