Graphiti
Graphiti is a framework designed for building and querying temporally-aware knowledge graphs, specifically tailored for AI agents operating in dynamic environments. Unlike traditional retrieval-augmented generation (RAG) methods, Graphiti continuously integrates user interactions, structured and unstructured enterprise data, and external information into a coherent, queryable graph.
Key Features:
- Real-Time Incremental Updates: Integrates new data episodes immediately without batch recomputation.
- Bi-Temporal Data Model: Tracks event occurrence and ingestion times for accurate point-in-time queries.
- Efficient Hybrid Retrieval: Combines semantic embeddings, keyword search, and graph traversal for low-latency queries.
- Custom Entity Definitions: Supports developer-defined entities through Pydantic models.
- Scalability: Efficiently manages large datasets with parallel processing suitable for enterprise environments.
Benefits:
- Enables state-based reasoning and task automation for agents.
- Facilitates complex, evolving data queries with semantic, keyword, and graph-based methods.
- Powers the core of Zep's memory layer for AI agents, enhancing their memory capabilities.
Highlights:
- Open-source framework with active development and community contributions.
- Supports integration with various LLM services like OpenAI and Google Gemini.
- Comprehensive documentation and quick start guides available for developers.