Skip to main content
PromptQuorum
Home/Power Local LLM/Self-Hosted AI Starter Kit Review 2026: n8n + Ollama + Qdrant in One Compose File
Local AI Agents & Tool Use

Self-Hosted AI Starter Kit Review 2026: n8n + Ollama + Qdrant in One Compose File

Β·12 min readΒ·By Hans Kuepper Β· Founder of PromptQuorum, multi-model AI dispatch tool Β· PromptQuorum

The Self-hosted AI Starter Kit (github.com/n8n-io/self-hosted-ai-starter-kit) is a free, open-source Docker Compose template curated by n8n that bundles n8n (workflow automation with 400+ integrations), Ollama (local LLM inference), Qdrant (vector database), and PostgreSQL into one ready-to-run local AI stack. It is licensed under Apache-2.0 and requires no cloud account or API key to get a working local AI workflow environment running β€” a single docker compose --profile cpu up (or a GPU-specific profile) starts every bundled service. It ships with an example workflow pre-loaded in n8n to demonstrate a local RAG pipeline using the bundled Ollama and Qdrant services.

The Self-hosted AI Starter Kit (github.com/n8n-io/self-hosted-ai-starter-kit) is an open-source Docker Compose template, curated by n8n, that bundles n8n's workflow automation platform, Ollama for local model inference, Qdrant as a vector database, and PostgreSQL into a single docker compose up command. It is not a standalone application β€” it is a pre-wired starting point for building local AI agents, RAG pipelines, and automation workflows with no cloud dependency required. This review covers what it actually bundles, how to install it, and how it compares to running these tools separately.

Key Takeaways

  • A Docker Compose template, not a standalone app β€” it wires together four existing open-source tools rather than shipping new code of its own
  • Bundles n8n (workflow automation, 400+ integrations), Ollama (local LLM inference), Qdrant (vector database), and PostgreSQL (data storage)
  • Licensed under Apache-2.0, free with no account or API key required
  • Separate Docker Compose profiles for CPU-only, Nvidia GPU, and AMD GPU (Linux) model inference
  • Ships a pre-loaded example n8n workflow demonstrating a local RAG pipeline using the bundled Ollama and Qdrant services
  • GitHub repository shows roughly 15,300 stars and around 3,800 forks as of September 2026
  • Curated and maintained by n8n, the low-code workflow automation company behind the n8n platform itself

πŸ“ In One Sentence

The Self-hosted AI Starter Kit is a free, Apache-2.0-licensed Docker Compose template from n8n that bundles n8n, Ollama, Qdrant, and PostgreSQL into one command for building local AI workflows with no cloud dependency.

πŸ’¬ In Plain Terms

Instead of separately installing a workflow tool, a local model runner, and a vector database and wiring them together yourself, this kit gives you all four already configured to talk to each other β€” you run one docker-compose command and get a working local AI automation environment with an example RAG workflow already loaded.

πŸ“ŒNote: This review is the deep-dive companion to the Self-hosted AI Starter Kit's entry in the Local LLM Software Directory β€” see that page for how it compares at a glance to dozens of other local AI tools.

What Is the Self-Hosted AI Starter Kit?

The Self-hosted AI Starter Kit is a Docker Compose template, not a new piece of software β€” its own GitHub description calls it "an open, docker compose template" that helps you "swiftly initialize a comprehensive local AI and low-code development environment." It combines four separately maintained open-source projects (n8n, Ollama, Qdrant, and PostgreSQL) into one pre-wired configuration, so you get a working local AI stack without manually installing and networking each piece yourself.

  • Core function: a docker-compose.yml and supporting configuration files that start n8n, Ollama, Qdrant, and PostgreSQL together, pre-networked so they can talk to each other
  • n8n: a low-code workflow automation platform with over 400 integrations and dedicated AI/LangChain nodes for building agents and automations
  • Ollama: runs open-weight language models locally, exposed to n8n workflows as a model provider
  • Qdrant: an open-source vector database used for storing and retrieving embeddings in RAG-style workflows
  • PostgreSQL: the relational database backing n8n's own workflow and credential storage
  • Maintainer: n8n, the company behind the n8n workflow automation platform
  • Canonical repository: github.com/n8n-io/self-hosted-ai-starter-kit β€” the source of the install steps and version history used in this review

The Starter Kit's Project History and Version Milestones

n8n published the Self-hosted AI Starter Kit as a companion resource to its own growing set of AI and LangChain-integration nodes, aimed at giving developers a fast, reproducible way to try local-AI workflow automation without assembling the underlying stack by hand.

  1. 1
    Initial release β€” core four-service bundle
    Why it matters: Shipped the original docker-compose.yml wiring together n8n, Ollama, Qdrant, and PostgreSQL with a pre-loaded example RAG workflow.
  2. 2
    Added GPU Compose profiles
    Why it matters: Introduced separate `gpu-nvidia` and `gpu-amd` Compose profiles alongside the default `cpu` profile, letting Ollama use available GPU acceleration on supported systems instead of running CPU-only inference for every model.
  3. 3
    Ongoing: kept pace with n8n's own AI/LangChain node additions
    Why it matters: As n8n's core product added more AI-specific nodes and agent-building capabilities, the starter kit's pre-loaded example workflow and documentation were updated to reflect what the bundled n8n version can do.

What Can You Do With the Starter Kit?

The starter kit's value is in what the bundled services do together, not in new functionality of its own. Here is what each part actually does, per the official GitHub README.

  • Local workflow automation β€” build and run automations in n8n's visual editor, using any of its 400+ integrations alongside dedicated AI/LangChain nodes for building agents
  • Local LLM inference β€” Ollama runs open-weight models (Llama, Qwen, Gemma, and others) locally, available to n8n workflows as a model provider with no external API key needed
  • Local vector storage for RAG β€” Qdrant stores and retrieves embeddings so n8n workflows can build retrieval-augmented generation pipelines entirely on local infrastructure
  • Persistent workflow and credential storage β€” PostgreSQL backs n8n's own database, so workflows, credentials, and execution history persist across container restarts
  • GPU acceleration profiles β€” separate Compose profiles (cpu, gpu-nvidia, gpu-amd) let Ollama use available GPU hardware for faster local inference where supported
  • Shared file access β€” a mounted /data/shared folder gives n8n workflows a way to read and write local files, useful for document-ingestion RAG workflows
  • Pre-loaded example workflow β€” the kit ships with a working n8n workflow already imported, demonstrating a local RAG pattern using the bundled Ollama and Qdrant services as a starting template

Usage Examples: Three Ways to Use the Starter Kit

These are concrete workflows built from the starter kit's documented, bundled features above β€” not hypothetical use cases.

Install the Self-Hosted AI Starter Kit

The starter kit installs via git clone and Docker Compose β€” there is no separate downloadable app. The steps below are from the official GitHub README β€” always verify against that page directly, since exact commands can change between updates.

Step
Command / Link
1. Clone the repositorygit clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
2. Enter the directorycd self-hosted-ai-starter-kit
3. Copy the environment filecp .env.example .env
4a. Start (CPU-only)docker compose --profile cpu up
4b. Start (Nvidia GPU)docker compose --profile gpu-nvidia up
4c. Start (AMD GPU, Linux)docker compose --profile gpu-amd up
Source codegithub.com/n8n-io/self-hosted-ai-starter-kit

n8n becomes available at http://localhost:5678 once the stack is up. Hardware needs scale with which models you run in Ollama β€” a small model works on a modest CPU-only machine, while larger models benefit from the Nvidia or AMD GPU profiles; check a given model's size in Ollama's library before pulling it. Requires Docker and Docker Compose installed on macOS, Windows (via WSL2), or Linux β€” the starter kit itself has no OS-specific build.

Pricing and Licensing

The starter kit itself is free and open-source, licensed under Apache-2.0. Since it bundles other open-source projects, it is worth knowing each bundled component's own licensing and cost model too.

Self-hosted AI Starter Kit (this template)

License:
Apache-2.0, per the repository LICENSE file
Cost:
Free

n8n (bundled)

License:
Sustainable Use License (source-available, not OSI-approved) for self-hosted use; see the n8n review for full licensing detail
Cost:
Free for self-hosted use under n8n's license terms

Ollama (bundled)

License:
MIT
Cost:
Free

Qdrant (bundled)

License:
Apache-2.0
Cost:
Free

PostgreSQL (bundled)

License:
PostgreSQL License (permissive)
Cost:
Free

Running the full stack costs nothing in software licensing β€” only your own infrastructure (compute, storage, and optionally a GPU) is a real cost. If you extend the pre-loaded n8n workflow to call a paid cloud LLM API or a paid third-party integration, that provider's own pricing applies; the starter kit itself does not add any markup or subscription fee.

Self-Hosted AI Starter Kit vs. Plain n8n

The starter kit is not a replacement for n8n β€” it is n8n plus a pre-wired local AI stack around it. The clearest way to think about the difference is what you get out of the box versus what you would have to configure yourself.

What you install

Self-Hosted AI Starter Kit:
n8n + Ollama + Qdrant + PostgreSQL, pre-networked in one docker-compose.yml
Plain n8n Self-Hosted:
n8n only β€” see the n8n review for its own install steps

Local LLM inference

Self-Hosted AI Starter Kit:
Included by default via bundled Ollama
Plain n8n Self-Hosted:
Not included; you connect your own model provider (local or cloud) manually

Vector database for RAG

Self-Hosted AI Starter Kit:
Included by default via bundled Qdrant
Plain n8n Self-Hosted:
Not included; you would add and network a vector database yourself

Example workflow

Self-Hosted AI Starter Kit:
Pre-loaded local RAG example workflow on first launch
Plain n8n Self-Hosted:
Starts with a blank canvas; templates are available separately from n8n's template library

Best for

Self-Hosted AI Starter Kit:
Getting a fully local AI workflow environment running in minutes, without manually wiring services together
Plain n8n Self-Hosted:
Teams that already run their own model or vector infrastructure and only need the automation layer

If you already have Ollama or a vector database running elsewhere in your infrastructure, installing plain n8n and connecting to your existing services may be simpler than adopting the starter kit's bundled versions. If you are starting from zero, the starter kit removes the integration work.

Who Should Use the Starter Kit?

Whether the starter kit fits depends on whether you want a ready-made local AI workflow environment versus assembling the same components yourself.

Starter Kit vs. Other Local AI Workflow Tools

The Self-hosted AI Starter Kit sits in the workflow-automation and RAG-framework space alongside several other self-hostable options. Here is how it compares to nearby tools β€” see the Local LLM Software Directory for the full catalog, and the dedicated Starter Kit vs. plain n8n comparison above for the closest head-to-head.

  • n8n β€” the workflow-automation platform this kit is built on top of; see the dedicated comparison section above and the full n8n review for its own standalone install and licensing detail.
  • LangChain-Chatchat β€” a self-hosted RAG and knowledge-base application with its own built-in UI, rather than a general-purpose workflow-automation canvas; see the LangChain-Chatchat review if a dedicated document-chat app fits your need better than a workflow builder.
  • RAGFlow β€” a deep document-understanding RAG engine focused on parsing complex documents (tables, layouts) more thoroughly than a general workflow tool; see the RAGFlow review.
  • Haystack β€” a Python-first RAG framework for developers who want to write pipeline code directly rather than use a visual workflow builder; see the Haystack review.

Common Mistakes When Evaluating the Starter Kit

Most confusion about the Self-hosted AI Starter Kit comes from treating it as a standalone application, misunderstanding what it actually bundles, or picking the wrong Compose profile.

Frequently Asked Questions

What is the Self-hosted AI Starter Kit?

It is an open-source Docker Compose template, curated by n8n, that bundles n8n, Ollama, Qdrant, and PostgreSQL into one command for building local AI workflows and RAG pipelines with no cloud dependency required.

Is the Self-hosted AI Starter Kit free?

Yes. The template itself is licensed under Apache-2.0, and it costs nothing to run. Its bundled components (n8n, Ollama, Qdrant, PostgreSQL) are each free for self-hosted use under their own respective licenses β€” see the pricing table above.

What does the Self-hosted AI Starter Kit actually bundle?

Four separately maintained open-source projects: n8n (workflow automation, 400+ integrations), Ollama (local LLM inference), Qdrant (vector database), and PostgreSQL (relational database backing n8n's own data). It is a docker-compose configuration, not new software.

Does the Self-hosted AI Starter Kit require a cloud account or API key?

No. Every bundled service runs locally by default, and the pre-loaded example RAG workflow uses only the bundled Ollama and Qdrant services. You can optionally add cloud provider API keys inside an n8n workflow later if you choose to.

How do I install the Self-hosted AI Starter Kit?

Clone the repository (git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git), copy the environment file (cp .env.example .env), then run docker compose --profile cpu up (or gpu-nvidia/gpu-amd for GPU acceleration). See the install table above for the full sequence.

Does it support GPU acceleration?

Yes, via separate Docker Compose profiles: gpu-nvidia for Nvidia GPUs and gpu-amd for AMD GPUs on Linux, alongside the default cpu profile for CPU-only inference.

Is this the same thing as n8n?

No. n8n is one of the four bundled components. The starter kit is a pre-configured environment that installs n8n alongside Ollama, Qdrant, and PostgreSQL β€” see the Self-Hosted AI Starter Kit vs. Plain n8n comparison above for the exact differences.

What license does n8n itself use inside this kit?

n8n is source-available under its own Sustainable Use License, which is not OSI-approved, for self-hosted use β€” distinct from the Apache-2.0 license covering this starter-kit template itself. See the n8n review for full licensing detail.

How many stars does the Self-hosted AI Starter Kit have on GitHub?

The GitHub repository shows roughly 15,300 stars and around 3,800 forks as of September 2026 β€” check the live repository for the current count, since it changes continuously.

Who maintains the Self-hosted AI Starter Kit?

It is curated and maintained by n8n, the company behind the n8n workflow automation platform, as a companion resource showcasing local AI workflows built with n8n's AI and LangChain nodes.

Sources

← Back to Power Local LLM