AI Toolbox

Kickstarts a locally hosted AI toolbox with n8n (with a built in puppeteer node), postgres, qdrant, neo4j, and redis

What’s included

✅ n8n - Low-code platform with over 400 integrations and advanced AI components. This is a custom n8n image with puppeteer built in.

✅ Neo4j - Knowledge graph engine that powers tools like GraphRAG, LightRAG, and Graphiti

✅ Postgres - Defacto DB

✅ Qdrant - Fast Vector DB for RAG workflows

✅ Redis - Key val cache DB

Installation

1. Make a copy of .env.example and rename it to .env in the root directory of the project
2. Set the required environment variables:

Important

Make sure to generate secure random values for all secrets. Never use the example values in production.

---

start the containers

sh start.sh

upgrade containers

sh rebuild.sh

Stop all containers

sh stop.sh

n8n templates

For AI workflow ideas, visit the official n8n AI template gallery. From each workflow, select the Use workflow button to automatically import the workflow into your local n8n instance.

Accessing local files

The self-hosted AI starter kit will create a shared folder (by default, located in the same directory, called 'shared', but can be specified in the .env file ) which is mounted to the n8n container and allows n8n to access files on disk. This folder within the n8n container is located at /data/shared -- this is the path you’ll need to use in nodes that interact with the local filesystem.

Nodes that interact with the local filesystem

• Read/Write Files from Disk
• Local File Trigger
• Execute Command