graphiti

Name: graphiti
Availability: InStock
Author: aeonbridge

Manage persistent, temporal knowledge graphs for AI agents with bi-temporal data modeling.

Updated Dec 14, 2025

Search Tags:#memory #temporal #graph #knowledge-graph #AI-agents #Graphiti #Zep

Ready to run

npx skills add https://github.com/aeonbridge/ab-anthropic-claude-skills --skill graphiti

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: graphiti
Source: https://github.com/aeonbridge/ab-anthropic-claude-skills/tree/main/output/graphiti
Command: npx skills add https://github.com/aeonbridge/ab-anthropic-claude-skills --skill graphiti

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Graphiti & Zep Knowledge Graph Skill enables AI agents to maintain persistent, time-aware memory by constructing and querying temporal knowledge graphs, improving context continuity and reducing hallucinations across conversations.

Core Features & Use Cases

Temporal knowledge graphs with bi-temporal data and historical context tracking
Hybrid search combining semantic embeddings, BM25, and graph traversal for precise retrieval
Zep context engineering for memory management, user and conversation state, and enterprise features
Easy integration with common agent frameworks (LangGraph, CrewAI, Autogen)
Use cases: building personalized, multi-user agents, enterprise data integration, and memory-driven dialogue

Quick Start

Install and configure Graphiti and Zep, connect to a supported graph database (Neo4j, FalkorDB, or Kuzu), then run a minimal script to initialize the graph and perform a sample memory query.

Frequently Asked Questions about graphiti

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build temporal knowledge graphs for persistent AI agent memory?▼

Temporal knowledge graphs for persistent AI agent memory are built using bi-temporal data modeling to track historical context and point-in-time accuracy, reducing hallucinations across conversations. This approach maintains state continuity for multi-user and enterprise integrations.

Can I integrate temporal knowledge graphs with LangGraph, CrewAI, or Autogen frameworks?▼

Yes, temporal knowledge graphs integrate easily with common agent frameworks like LangGraph, CrewAI, and Autogen. This allows memory-driven dialogue and personalized user experiences to function across multi-framework deployments without changing existing agent architectures.

What is hybrid search retrieval and how does it work for AI agent memory?▼

Hybrid search for AI agent memory combines semantic embeddings, BM25, and graph traversal to retrieve precise historical context. This mechanism ensures accurate point-in-time queries across conversation states and enterprise data.

What graph databases are supported for deploying Zep context engineering and memory management?▼

Zep context engineering and memory management support deployment on Neo4j, FalkorDB, or Kuzu graph databases. Connecting to one of these supported databases is required to initialize the graph and perform memory queries.

How do I set up bi-temporal data modeling for enterprise knowledge integration?▼

Bi-temporal data modeling for enterprise knowledge integration is set up by configuring Graphiti and Zep, connecting to a graph database, and initializing a script. This tracks historical context and conversation state for personalized multi-user agents.