Open WebUI
Self-hosted chat interface that connects to Ollama and OpenAI-compatible model servers.
Our verdict
What it does well
- Source code is public and free to self-host
- Installs with Docker, pip or Kubernetes; a desktop app is also in the works
- Works with Ollama and OpenAI-compatible APIs
Where it falls short
- Licence is not OSI-approved: it requires keeping the Open WebUI branding
- Branding can be removed only with 50 or fewer users, permission or an enterprise licence
- Desktop app is labelled 'Early Alpha' in its repository
Open WebUI is a self-hosted AI interface that you run on your own computer or server and use from a browser. It connects to Ollama and to OpenAI-compatible APIs. The docs recommend Docker, and also describe pip, Kubernetes and a desktop app (a separate repository labelled early alpha, with Windows, macOS and Linux installers).
The main repository's LICENSE is a custom licence based on BSD-3-Clause with an added clause forbidding removal or alteration of 'Open WebUI' branding, except for deployments with 50 or fewer end users in 30 days, with written permission, or under an enterprise licence. The project's own docs say this is not an OSI-approved open-source licence, while stating it is 'free and permissively licensed' for personal, business and teaching use if the branding is kept. Code up to v0.6.5 remains BSD-3-Clause.
There is no published price. Enterprise options (white-labelling, SSO, support) are sold through sales contact. The docs list no hardware minimums; the Python install supports Python 3.11 and 3.12.
Alternatives to Open WebUI
OpenAI's AI chat assistant for text, voice, images, research and coding, on web, desktop and mobile.
- Freemium
What users say
Write a reviewNo user reviews yet. If you’ve used Open WebUI, share what you used it for and how it went.
Last updated 16 October 2026. Facts checked against the official site on 16 October 2026. How we make money