graphiti
Build Real-Time Knowledge Graphs for AI Agents
What is graphiti?
Build Real-Time Knowledge Graphs for AI Agents
Overview of graphiti
What it is
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. It continuously integrates user interactions, structured and unstructured enterprise data, and external information into a coherent, queryable graph. The framework supports incremental data updates, efficient retrieval, and precise historical queries without requiring complete graph recomputation.
Key features
- Temporal fact management: Facts have validity windows; old facts are invalidated but not deleted, enabling queries of current or historical truth.
- Episodes and provenance: Every entity and relationship traces back to the raw data (episodes) that produced it, providing full lineage.
- Prescribed and learned ontology: Define entity and edge types upfront via Pydantic models or let structure emerge from data.
- Incremental graph construction: New data integrates immediately without batch recomputation.
- Hybrid retrieval: Combines semantic embeddings, keyword (BM25), and graph traversal for low-latency, high-precision queries.
- Scalability: Efficiently manages large datasets with parallel processing and pluggable graph backends.
Use cases
Build temporal knowledge graphs that evolve with every interaction, tracking what is true now and what was true before. Represent rich, structured context instead of flat document chunks or raw event streams. Query across time, meaning, and relationships with hybrid retrieval.
Getting started
See the repository README for installation commands. Requirements include Python 3.10 or higher, a supported graph database (Neo4j 5.26, FalkorDB 1.1.2, Amazon Neptune, or Kuzu 0.11.2 which is deprecated), and an OpenAI API key.
License and pricing
Graphiti is open source under the Apache-2.0 license.
Based on the project's public README and repository metadata.