Repolode
Submit
n8n-io

n8n-io/self-hosted-ai-starter-kit

Docker Compose template that spins up a local AI and low-code stack with self-hosted n8n, Ollama, Qdrant and PostgreSQL.

Open-source alternative to:Zapier

View on GitHubWebsite
Stars
15,299
Forks
3,814
Open issues
6
Last commit
9 days ago

What is it?

The Self-hosted AI Starter Kit is a Docker Compose template that brings up a local AI and low-code development environment in one step. It bundles self-hosted n8n, a low-code workflow platform with over 400 integrations and AI nodes, together with Ollama for running local LLMs, Qdrant as a vector store, and PostgreSQL as the database.

The kit is meant for building AI workflows that keep data on your own machine, such as agents, document question answering, and chat bots. Compose profiles select GPU or CPU setups: NVIDIA and AMD GPUs on Linux are supported, while Apple Silicon Macs run the stack on CPU or connect to an Ollama instance running natively on the host.

The project is positioned as a proof-of-concept starting point rather than a production-ready deployment. It includes a sample chat workflow and links to n8n AI templates that can be imported into the local instance.

Key features

  • 01Docker Compose setup bundling n8n, Ollama, Qdrant and PostgreSQL
  • 02Compose profiles for NVIDIA GPU, AMD GPU on Linux, and CPU-only runs
  • 03Included sample chat workflow to test the stack after startup
  • 04Shared local folder mounted into the n8n container for file access
  • 05Option to connect n8n to an Ollama instance running natively on macOS

Use cases

  • Building an AI agent that schedules appointments without sending data to third-party APIs
  • Summarizing or querying company PDFs on a local machine
  • Prototyping a Slack bot for internal IT or company communications
  • Analyzing private financial documents with a locally hosted model

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
  2. 2

    Enter the project folder and create your environment file

    cd self-hosted-ai-starter-kit && cp .env.example .env
  3. 3

    Start the stack on CPU

    docker compose --profile cpu up
  4. 4

    Open n8n at http://localhost:5678/ in your browser and complete setup

Things to know

  • The README says it is not fully optimized for production and is aimed at proof-of-concept projects.
  • Apple Silicon Macs cannot expose the GPU to Docker, so Ollama runs on CPU unless you run it outside Docker.

Topics

#ai#low-code#workflow-automation#docker#self-hosted#llm#vector-database#ollama#ai-agents#starter-kit

FAQ

What is self-hosted-ai-starter-kit?
Docker Compose template that spins up a local AI and low-code stack with self-hosted n8n, Ollama, Qdrant and PostgreSQL. The Self-hosted AI Starter Kit is a Docker Compose template that brings up a local AI and low-code development environment in one step. It bundles self-hosted n8n, a low-code workflow platform with over 400 integrations and AI nodes, together with Ollama for running local LLMs, Qdrant as a vector store, and PostgreSQL as the database.
Is self-hosted-ai-starter-kit free to use? What license does it have?
self-hosted-ai-starter-kit is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is self-hosted-ai-starter-kit still maintained?
Actively maintained. The last commit to self-hosted-ai-starter-kit was on Oct 12, 2026.
What can I use self-hosted-ai-starter-kit for?
Building an AI agent that schedules appointments without sending data to third-party APIs Summarizing or querying company PDFs on a local machine Prototyping a Slack bot for internal IT or company communications Analyzing private financial documents with a locally hosted model
How do I install self-hosted-ai-starter-kit?
Clone the repository: git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git Enter the project folder and create your environment file: cd self-hosted-ai-starter-kit && cp .env.example .env Start the stack on CPU: docker compose --profile cpu up Open n8n at http://localhost:5678/ in your browser and complete setup
Where can I get self-hosted-ai-starter-kit?
The source code and installation instructions are on GitHub: https://github.com/n8n-io/self-hosted-ai-starter-kit

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects