Back to directory

Graphiti

An open-source framework for building temporal knowledge graphs for AI agents, where each stored fact carries a validity window recording when it became true and when it was superseded.

Graphiti

Graphiti builds context graphs out of entities, facts and relationships, continuously integrating user interactions and both structured and unstructured data into a graph that can be queried without a full recomputation, unlike static knowledge graphs or plain retrieval-augmented generation. Every derived fact traces back to the raw "episode" data it came from, entity summaries update over time, and developers can define custom entity and edge types through Pydantic models.

It supports hybrid retrieval combining semantic search, keyword search and graph traversal, so an application can query across time, meaning and relationships rather than flat document chunks or raw event streams. Graphiti is the open-source framework underlying Zep, a separate, proprietary managed service that runs context graphs at scale for production deployments using its own graph database engine.

It is written in Python and licensed under Apache-2.0.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.