Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/neo4j-labs/create-context-graph/llms.txt

Use this file to discover all available pages before exploring further.

Create Context Graph is an interactive CLI scaffolding tool that generates complete, domain-specific AI agent applications. Pick your industry domain, pick your agent framework, and get a full-stack app with a FastAPI backend, Next.js frontend, Neo4j knowledge graph, and streaming AI agent — all wired together and ready to run. 
# Run without installing
uvx create-context-graph

# Or via Node.js
npx create-context-graph

Quick Start

Get a running context graph app in under 5 minutes

Introduction

Learn what Create Context Graph builds and why

CLI Reference

Every flag and option, with defaults and examples

Domain Catalog

Browse all 22 built-in industry domains

​
What gets generated

Running create-context-graph produces a complete full-stack application tailored to your domain:

FastAPI backend

AI agent with domain-specific Cypher tools, streaming SSE endpoint, and Neo4j memory integration

Next.js frontend

Streaming chat UI, interactive NVL graph visualization, document browser, and decision trace viewer

Neo4j schema

Domain-specific constraints, indexes, GDS projections, and pre-loaded fixture data

8 agent frameworks

PydanticAI, Claude Agent SDK, LangGraph, OpenAI Agents, CrewAI, Strands, Google ADK, and Anthropic Tools

​
Get started in 3 steps

1

Scaffold your project

Run the CLI and choose your domain and framework, or pass flags directly:
uvx create-context-graph my-app \
  --domain healthcare \
  --framework pydanticai \
  --demo-data
2

Start Neo4j and seed data

Choose Neo4j Aura (free cloud), Docker, or neo4j-local — then seed the domain data:
cd my-app
make install
make neo4j-start   # or: make docker-up
make seed
3

Run the app

Start the backend and frontend:
make start
Open http://localhost:3000 to chat with your AI agent and explore the knowledge graph.

​
Explore the docs

Neo4j setup options

Aura, Docker, or neo4j-local — pick the right option for your workflow

Custom domains

Generate a full ontology from a plain-English description

SaaS connectors

Import real data from GitHub, Slack, Jira, Notion, and more

Why context graphs?

How graph memory differs from RAG and why it matters for agents

Framework comparison

Compare all 8 supported agent frameworks side by side

Ontology YAML schema

Full reference for the domain definition format

Build docs developers (and LLMs) love

Get started for freeTalk to us