The Curious AI Guy

Library / Local AI

Open WebUI

A ChatGPT-style interface for local and API models.

Replaces
LicenseOpen WebUI License (custom)
GitHub stars155k
Last code update12 October 2026
SetupIntermediate about 15 minOur estimate
Paid version costs aboutnot verified

New to this? What open source means and how to read this page.

What it is

A self-hosted chat interface that works with Ollama and OpenAI-compatible APIs, with accounts, history and document chat.

Good for

Giving yourself or a small team one clean chat screen across local and cloud models.

The catch

The license is custom, not a standard open-source one, so read it before you use it commercially. It is the interface only: you still need a model behind it.

Open WebUI versus

Open WebUI
PriceFreeThe software is free. The computer or server to run it is yours to provide.Price not verified
LicenseOpen WebUI License (custom)Commercial license
Source codePartly public, partly under a different licenseNot public
SetupIntermediate, about 15 minSign up and pay
Where it runsOn a computer or server you controlThe vendor's app or service, under their terms

The paid product's own plans and terms change. Check its site before you decide.

Install it with an AI assistant

Paste this into Claude, ChatGPT or another assistant that can work on your computer (Claude Code or Claude Desktop, for example). It is written from the project's official repository and tells the assistant to show you every command first. Setup time is our estimate: about 15 min.

I want to install and try Open WebUI on my own computer.

Official repository: https://github.com/open-webui/open-webui
Official site: https://openwebui.com
License: Open WebUI License (custom)

Before you do anything:
1. Read the README and install notes in the official repository above, and nothing else. Do not follow third-party tutorials or mirrors.
2. Tell me in plain words what will be installed, what it needs (operating system, memory, graphics card, disk space, accounts) and what it will cost me, if anything.
3. Check my computer against those needs and tell me honestly if it will not work well.

Run it with Docker. First check whether Docker is installed and running, and if it is not, guide me through installing Docker Desktop. Use the official Docker or compose instructions from the README, keep the data in a volume so it survives updates, and tell me the address to open in my browser. Tell me how much memory and disk it will use, and how to remove it cleanly.

Rules:
- Show me each command before you run it, and say what it does.
- Ask before anything that deletes files, changes system settings, opens a network port or needs an administrator password.
- Never put my passwords or keys on a command line, or in a file I did not choose.
- When it is installed, help me check it with one small test, and tell me how to start and stop it.
- If something goes wrong, explain it in plain words and do not guess your way around it.

Good to know before you start: The license is custom, not a standard open-source one, so read it before you use it commercially. It is the interface only: you still need a model behind it.

We have not run this prompt ourselves yet. Read what the assistant plans to do before you say yes.

Facts checked on 12 October 2026. We have not yet run a hands-on test of this tool. When we do, it gets a "Tested" mark here. Approximate US list prices for an individual plan, from third-party price trackers checked on 12 Oct 2026. Monthly billing where it exists. Regions, taxes and promotions change them. Confirm at the vendor before you decide.

More in Local AI

Local AIOpen source

Run AI models on your own computer.

Replaces:

Beginnerabout 5 min

saves ~$20/moDetails →
Local AIOpen source

A desktop chat app that runs models offline.

Replaces:

Beginnerabout 5 min

saves ~$20/moDetails →
Local AIOpen source

The engine behind a lot of local AI.

A project worth knowing about

Advancedabout 20 min

free projectDetails →