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

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.

Repository: https://github.com/n8n-io/self-hosted-ai-starter-kit
Canonical: https://ross.abutalabs.com/products/self-hosted-ai-starter-kit
Homepage: https://n8n.io
License: Apache-2.0
License Family: permissive
Topics: ai, low-code, self-hosted, starter-kit, ai-agents
Last push: 2026-07-23T11:28:09+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 65
- inputs: {"age_days": 922, "days_push": 41, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15208, forks 3811 (observed 2026-08-28T04:11:09.393462+00:00)

## What it is
A Docker Compose template from n8n that spins up a local, self-hosted AI development environment bundling n8n, Ollama, Qdrant, and PostgreSQL. It provides a ready-made stack for building private AI agents and RAG workflows without sending data to cloud providers.

## Use cases
- set up a local ai development environment with docker compose
- build self-hosted ai agents without data leaving my machine
- summarize company pdfs privately with local llms
- run a local rag stack with ollama and qdrant
- prototype ai workflow automation on my own hardware
- create a private slack bot powered by local ai

## When to choose
- you want a one-command local AI stack with n8n, Ollama, Qdrant, and Postgres preconfigured
- data privacy matters and you need on-prem or air-gapped AI workflows
- you're prototyping AI agents or RAG pipelines before productionizing
- you have an Nvidia or AMD GPU and want local LLM inference

## When to avoid
- you need a production-grade, scaled deployment rather than a starter template
- you don't want Docker or lack resources to run local LLMs
- you only need n8n itself without the bundled AI components
- you prefer fully managed cloud AI services

## Facets
- artifact type: infra-config
- maturity: active
- function: workflow-automation, agent-framework, rag, llm-inference, vector-database, self-hosted, chatbot
- domain: artificial-intelligence, self-hosted, developer-tools, large-language-models
- platform: self-hosted, windows
- tags: docker-compose, starter-kit, ollama, qdrant, n8n, low-code, local-llm, postgres, ai-agents, automation, docker, linux, macos, gpu

## Member repositories
- n8n-io/self-hosted-ai-starter-kit (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.393462+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:33.306418+00:00, confidence not recorded.
  - readme: https://github.com/n8n-io/self-hosted-ai-starter-kit (fetched 2026-08-28T04:11:09.393462+00:00, sha bdf7f99a87ae)
  - homepage: https://n8n.io (fetched 2026-08-29T08:04:47.724094+00:00, sha a2768a8f3ba0)
  - site_page: https://n8n.io/features (fetched 2026-08-29T08:04:47.733686+00:00, sha 8d6431e522b9)
  - site_page: https://docs.n8n.io/ (fetched 2026-08-29T08:04:47.739813+00:00, sha 86f9eb764786)
  - site_page: https://docs.n8n.io (fetched 2026-08-29T08:04:47.741413+00:00, sha 86f9eb764786)
  - site_page: https://docs.n8n.io/changelog (fetched 2026-08-29T08:04:47.743138+00:00, sha f049d019458f)
  - site_page: https://n8n.io/integrations (fetched 2026-08-29T08:04:47.736097+00:00, sha 8a7e13640eda)
  - site_page: https://n8n.io/limitless-integrations (fetched 2026-08-29T08:04:47.738174+00:00, sha 2e5e887fc8a4)
  - site_page: https://n8n.io/pricing (fetched 2026-08-29T08:04:47.746298+00:00, sha 1bbb537a876b)
- Data as of 2026-08-30T08:39:29.467469+00:00.