For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
PlaygroundDiscordStatusDashboardSign Up >
DocumentationSDK ReferenceGraphiti
DocumentationSDK ReferenceGraphiti
  • Getting Started
    • Welcome
    • Overview
    • Quick Start
    • MCP Server
  • Configuration
    • LLM Configuration
    • Neo4j Configuration
    • FalkorDB Configuration
    • AWS Neptune Configuration
    • Kuzu DB Configuration
  • Core Concepts
    • Adding Episodes
    • Custom Entity and Edge Types
    • Communities
    • Graph Namespacing
  • Working with Data
    • Searching
    • CRUD Operations
    • Adding Fact Triples
  • Integrations
    • LangGraph Agent
  • Other
    • Telemetry
LogoLogo
PlaygroundDiscordStatusDashboardSign Up >
Getting Started

Welcome to Graphiti!

Was this page helpful?

Overview

The open-source temporal knowledge graph framework

Next
Built with

Want to use Graphiti with AI assistants like Claude Desktop or Cursor? Check out the Graphiti MCP Server.

Graphiti is the open-source framework for building temporal knowledge graphs — Context Graphs — that power Zep. It makes real-time incremental updates to graphs for AI agents, with no batch recomputation, so relationships and facts evolve as your data does.

Overview

Learn about Graphiti’s core concepts and how temporal knowledge graphs work.

Quick Start

Get up and running with Graphiti in minutes including installation, episodes, search, and basic operations.

Graphiti MCP Server

Use Graphiti with AI assistants like Claude Desktop or Cursor.

Adding Episodes

Learn how to add text and JSON episodes to build your knowledge graph.

Searching

Discover hybrid search capabilities combining semantic, keyword, and graph-based retrieval.

Custom Entities

Define domain-specific entity types for more precise knowledge representation.