---
title: "Deploy Graphiti + Neo4j"
description: "Build Real-Time Knowledge Graphs for AI Agents"
category: "AI/ML"
url: https://railway.com/deploy/graphiti-neo4j
---

# Deploy Graphiti + Neo4j

Build Real-Time Knowledge Graphs for AI Agents

**[Deploy Graphiti + Neo4j on Railway](https://railway.com/template/graphiti-neo4j)**

- **Creator:** Şükrü
- **Category:** AI/ML
- **Total deploys:** 47

## Template content

### neo4j https://cdn.jsdelivr.net/gh/devicons/devicon@latest/icons/neo4j/neo4j-original-wordmark.svg

- **Image:** neo4j:5.26.2

### graphiti https://i.ibb.co/j9YM427s/132832125-s-200-v-4.png

- **Image:** zepai/graphiti:latest
- **Health check:** /healthcheck
- **Public domain:** Yes

## Documentation

# Deploy and Host Graphiti + Neo4j on Railway

Graphiti + Neo4j provides a robust, time-aware knowledge graph system
for AI applications. Graphiti extracts structured facts, entities,
relationships, and temporal context from text, while Neo4j stores this
evolving knowledge graph efficiently. Together, they enable long‑term AI
memory, graph‑based reasoning, and hybrid semantic search.

## About Hosting Graphiti + Neo4j

Hosting Graphiti with Neo4j on Railway delivers a fully managed,
scalable environment for AI memory systems. Railway automatically
handles service deployment, networking, environment variables, logs, and
scaling so you can focus on building your AI logic instead of server
management. The included template provisions a Graphiti API server and a
connected Neo4j graph database, making it easy to ingest data through
Graphiti's episode API, run extraction pipelines, and perform semantic +
graph-based search over your knowledge. This setup is ideal for building
production-grade agent memory systems, chatbots with evolving knowledge,
or applications that require rich relationship modeling.

## Common Use Cases

-   AI agents that require long-term, structured memory
-   Knowledge graph--powered assistants
-   Entity and relationship extraction pipelines
-   Semantic + graph hybrid retrieval workflows
-   Applications needing time-aware or evolving information tracking

## Dependencies for Graphiti + Neo4j Hosting

-   An LLM provider API key (Google Gemini, Anthropic, or OpenAI)\
-   A Railway-hosted Neo4j database linked to the Graphiti service

### Deployment Dependencies

-   Neo4j Documentation: 
https://neo4j.com/docs/
-   Graphiti Documentation: https://help.getzep.com/overview



## Why Deploy Graphiti + Neo4j on Railway?

Railway is a singular platform to deploy your infrastructure stack.
Railway will host your infrastructure so you don't have to deal with
configuration, while allowing you to vertically and horizontally scale
it.

By deploying Graphiti + Neo4j on Railway, you are one step closer to
supporting a complete full-stack application with minimal burden. Host
your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/graphiti-neo4j