Graphiti

Graphiti is a framework for building and querying temporal context graphs for AI agents. Unlike static knowledge graphs, Graphiti tracks how facts change over time, maintains provenance to source data, and supports both prescribed and learned ontology. The framework supports incremental data updates, efficient retrieval, and precise historical queries without complete graph recomputation. Key features include hybrid retrieval combining semantic search, keyword search, and graph traversal; automatic fact invalidation with temporal history preserved; custom entity and relationship types via Pydantic models; support for multiple graph backends including Neo4j, FalkorDB, and Amazon Neptune; and sub-second query latency even on large datasets. Graphiti is the open-source temporal context graph engine at the core of Zep's context infrastructure for AI agents and is ideal for personalized AI assistants, customer support agents, and any application needing dynamic, evolving knowledge management.