Open WebUI

License	FOSS problems	Maintenance	SSO	Users	Tested
MITPermissive license. Preserve the copyright notice. Applies only to the covered code — your surrounding project can stay under any license.	—	Active	✅	Unlimited	✅

Evaluation

What it is

Open WebUI is a self-hosted chat interface for large language models. It connects to locally running models via Ollama or to any OpenAI-compatible API. Think ChatGPT-style UI, but running on your own infrastructure against models you choose.

Why it could be useful

A single interface for multiple AI models — local or remote. Useful for a team that wants access to AI tools without sending data to OpenAI or relying on individual accounts. Conversations stay on your server, models can be swapped, and access is managed centrally. Works well as a shared tool for members who want to experiment with AI without a per-seat subscription.

Why not to go for it

Open WebUI is just the interface — the models still need to come from somewhere. Running local models via Ollama requires serious hardware (a GPU, or a lot of RAM for CPU inference). Without that, you're proxying to an external API anyway, which reintroduces the dependency on a third-party service. For a small association without GPU hardware, this is more useful as a shared gateway to external APIs than as a truly self-contained AI setup.

Setup

1. Add DNS records pointing ai.<domain> to the server:

   • A record: ai → <ipv4>
   • AAAA record: ai → <ipv6>

2. In Coolify, go to New Resource → Service, search for Open WebUI, set the domain on the open-webui container (inside the container settings), then deploy.

3. Open https://ai.<domain> and create the admin account.