OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Self Hosted AI Starter Kit

Self Hosted AI Starter Kit is an open-source Docker Compose template that combines self-hosted n8n with Ollama, Qdrant and PostgreSQL to initialize a local AI and low-code workflow development environment.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Self Hosted AI Starter Kit — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a preconfigured starting point for local, self-hosted AI workflow experiments and proof-of-concept projects.

Who it is for

  • Developers building self-hosted AI workflows
  • Technical teams prototyping local AI agents and document workflows
  • Users who want a Docker-based environment connecting n8n with local AI services

Documented uses

  • Create low-code AI agent workflows
  • Run language-model workflows through Ollama
  • Store vector data in Qdrant for local AI applications
  • Prototype document summarization, communications bots and analysis workflows
Before you choose

Requirements & limits

The project is available as a public open-source repository under the Apache-2.0 license. The documented setup uses Docker Compose and provides Nvidia GPU, AMD GPU on Linux, CPU and Apple Silicon Mac paths.

  • The stack requires Docker Compose and local machine setup rather than a hosted workflow service.
  • Ollama, Qdrant and n8n are the documented components for keeping language-model and vector-store processing local.
  • Hardware affects the startup path: Nvidia and AMD GPU profiles are documented, while Apple Silicon uses CPU in Docker or a separately running local Ollama service.
  • The repository describes the kit as suitable for proof-of-concept work and says it is not fully optimized for production environments.
  • The included stack provides n8n integrations and AI nodes alongside the local model and vector-store components.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the starter kit with Docker Compose

Initialize the local AI and low-code workflow environment using the repository’s documented installation paths.

Before you start

  • Docker and Docker Compose
  • A machine using an Nvidia GPU, AMD GPU on Linux, Apple Silicon Mac, or a non-GPU setup
  • The repository URL
  • A local .env file with updated secrets and passwords

Steps

  1. Clone the repository and change into its directory.

  2. Copy .env.example to .env and update the secrets and passwords.

  3. Start Docker Compose with the profile matching the machine: gpu-nvidia, gpu-amd, cpu, or the documented Mac command.

  4. Open the local n8n address in a browser and complete the one-time n8n setup.

Expected outcome

A local n8n-based AI environment is initialized and accessible through the local n8n address.

Guide limitations

  • The starter kit is intended for getting started and proof-of-concept projects rather than being fully optimized for production environments.
  • Nvidia users who have not previously used their GPU with Docker are directed to Ollama’s Docker instructions.
  • Apple Silicon Macs cannot expose their GPU to the Docker instance according to the repository instructions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
n8n-io/self-hosted-ai-starter-kit · Official homepage title · retained in its source language
How we review sourcesSuggest a correction