> Source: https://meetrix.io/store/openwebui/
> Markdown copy of that page. Cite the URL above, not this file.

[Store](https://meetrix.io/store/)  OpenWebUI

Self-hosted ChatGPT-style UI

# Self-hosted OpenWebUI with Ollama on AWS

Give your team a private AI assistant with OpenWebUI and Ollama, running from a pre-configured AMI in your own AWS account. Chat with local or remote models while your prompts and documents stay on your infrastructure.

 [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-gg6fmefxg7gds)

-   Ready in 5-10 minutes
-   Local models with Ollama
-   Runs in your own account

![OpenWebUI with Ollama deployed on AWS by Meetrix](https://meetrix.io/assets/store/openwebui/openwebui.webp)

## What are OpenWebUI and Ollama?

OpenWebUI is a team-friendly chat interface for large language models, and Ollama runs open models such as Llama, Mistral and Gemma locally. Together they give you a ChatGPT-style assistant you host yourself, with remote providers available too.

-   ### Chat interface

    A clean UI for talking to local and remote LLMs.

-   ### Local models

    Run Llama, Mistral, Gemma and GGUF or GPTQ variants with Ollama.

-   ### Knowledge bases

    Built-in RAG over your own documents.

-   ### Team workspaces

    User accounts with granular permissions, managed by an admin.

-   ### Plugins

    Extend chats with functions and pipelines.

-   ### Private by design

    Keep conversations inside your own AWS account.

## What's in the Meetrix OpenWebUI AMI

The AMI ships OpenWebUI and Ollama wired together, ready for the first admin account.

-   OpenWebUI and Ollama running in Docker
-   Admin account creation on first visit
-   Automatic SSL when your domain is hosted on Route 53
-   A certificate script for issuing SSL manually otherwise
-   A CloudFormation template for your own AWS account
-   Email support from Meetrix at aws@meetrix.io

## How to set up a self-hosted OpenWebUI server

1.  ### Launch the stack

    Subscribe on AWS Marketplace and launch the CloudFormation stack with your domain and admin email.

2.  ### Point your domain at it

    After 5-10 minutes, create a DNS record with the PublicIp from the stack outputs.

3.  ### Create the admin account

    Open the DashboardUrl and create the admin account with a strong password.

4.  ### Pick a model and invite your team

    Pull or connect a model, then add team members from the admin panel.

## Deploy on AWS

### OpenWebUI on AWS

An AMI on AWS Marketplace, launched into your own AWS account with a CloudFormation stack.

Deploys with

CloudFormation

Recommended size

t3.medium or larger

Ready in

5-10 minutes

#### Setup guides

-   [**Developer guide** Launch, DNS, admin, SSL](https://meetrix.io/blogs/open-webui-developer-guide/)
-   [**OpenWebUI with Ollama on AWS** Use cases and benefits](https://meetrix.io/blogs/deploy-openwebui-ollama-aws-meetrix/)
-   [**Video walkthrough** Watch the deployment on YouTube](https://www.youtube.com/watch?v=t1h-Tz5BfzA)

 [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-gg6fmefxg7gds)

## OpenWebUI vs LibreChat

|  | OpenWebUI | LibreChat |
| --- | --- | --- |
| Licence | Open WebUI License (since April 2025) | MIT |
| Branding requirement | Yes, at 50+ users | None |
| Ollama integration | Deep, native | Through the OpenAI-compatible API |
| Built-in RAG | Yes | Through configuration |
| Providers out of the box | Ollama and OpenAI-compatible | OpenAI, Anthropic, Gemini, Bedrock and more |

OpenWebUI is source-available rather than OSI-approved open source. [Read OpenWebUI vs LibreChat →](https://meetrix.io/blogs/openwebui-vs-librechat/)

## Video: deploy OpenWebUI with Ollama on AWS

## OpenWebUI FAQ

Which models can I use?

Local open models through Ollama, such as Llama, Mistral and Gemma, and remote models through compatible providers.

Is OpenWebUI open source?

It is source-available. Since April 2025 it uses the Open WebUI License, which requires keeping its branding once a deployment reaches 50 or more users.

How do I create the admin account?

Open the DashboardUrl from the stack outputs and fill in the form. Later accounts are created from the admin panel.

Can I run it in a private VPC?

Yes. It works with standard AWS VPC setups, including isolated environments.

Which instance size should I choose?

t3.medium or larger. Larger local models need more memory and CPU.

Is my data private?

Conversations and documents stay on your instance. Anything you send to a remote model provider goes to that provider.

How do I upgrade?

Back up your server data, remove the old stack and launch the new version from AWS Marketplace.

## OpenWebUI guides and articles

### [OpenWebUI vs LibreChat: Self-Hosted ChatGPT UI Compared](https://meetrix.io/blogs/openwebui-vs-librechat/)

Features, providers and the licensing change most reviews miss.

### [Best Open Source LLMs to Self-Host in 2026](https://meetrix.io/blogs/best-open-source-llms-self-hosted-2026/)

Pick a model to run behind your chat interface.

### [Deploy OpenWebUI with Ollama on AWS](https://meetrix.io/blogs/deploy-openwebui-ollama-aws-meetrix/)

A private AI assistant in minutes.

## Need a hand with OpenWebUI?

We build and run self-hosted AI infrastructure every day, from model selection to RAG. Tell us what you need.

[Contact us](https://meetrix.io/contact-us/)