1 repository
Fact stores that record subject-predicate-object statements with validity periods and support timeline queries and state transitions.
Distinct from Fact Extraction Pipelines: Distinct from Fact Extraction Pipelines: focuses on storing and querying facts with temporal validity windows, not on extracting facts from unstructured data.
Explore 1 awesome GitHub repository matching data & databases · Temporal Fact Stores. Refine with filters or upvote what's useful.
OpenMemory is an embeddable memory engine for LLM agents that stores, retrieves, and manages conversational context and agent state using semantic indexing and temporal facts. It functions as a semantic memory store backed by vector indexing, where memories are organized by meaning rather than by exact key, and includes a tiered decay engine that gradually reduces the salience of unused memories while compressing cold vectors and fingerprinting dormant entries to conserve storage. The system also maintains a temporal fact database that records factual statements with subject-predicate-object s
Records factual statements with subject-predicate-object structure and explicit validity windows for time-aware knowledge queries.