ServerAvatar

Open WebUI on your own server, in one click.

Give yourself or your team a ChatGPT-style AI chat with Open WebUI, on a server you own. You pick the models: OpenAI, Anthropic or any OpenAI-compatible API. ServerAvatar runs it in Docker, creates the admin account and turns HTTPS on for you.

  • One container
  • Admin account created for you
  • Your server, your chats
open-webui0.12HTTPS

Section 01What is Open WebUI

What is Open WebUI?

Open WebUI is a self-hosted AI chat interface. It works like ChatGPT in your browser, but you choose the models: connect OpenAI, Anthropic, any OpenAI-compatible API or your own Ollama server, and switch between them in one place.

It is built for more than one person. Each user gets their own chat history, and the admin decides who can sign in and which models they can use. Your chats, users and settings stay in a database on your server; messages go only to the model provider you choose.

  • Free to use, with its code on GitHub
  • No model bundled: bring your own API or Ollama
  • Users, groups and per-model access

Section 02Features

What you can do with Open WebUI

  • Any model, one interface

    Chat with OpenAI, Anthropic, any OpenAI-compatible provider or Ollama from one model selector, and switch models mid-conversation.

  • Multi-model chats

    Send the same prompt to two models at once and compare their answers side by side.

  • Custom models

    Wrap any model with a system prompt, tools, knowledge and parameters, and share it with the users or groups you choose.

  • Users and permissions

    Roles, groups and per-model access, with SSO, LDAP and two-factor sign-in when you need them.

  • Tools and MCP

    Add capabilities with Python tools, MCP servers or OpenAPI endpoints, or import extensions from the community.

  • Organized history

    Keep chats in folders, tag and pin them, search your history and share a chat by link.

Section 03Requirements

What you need

A fresh Ubuntu server you can log in to as root. The installer checks all of this before it changes anything.

Open WebUI on Docker
RequirementOpen WebUI on Docker
Operating systemUbuntu 24.04 or 26.04 LTS (x86-64)
CPU1 core or more
RAM1 GB or more
Disk10 GB or more (25 GB recommended)
ContainersOpen WebUI 0.12 (slim image)
Ports80 and 443 open

Open WebUI publishes no CPU or RAM minimum; 1 GB is Ubuntu's minimum for a server. Open WebUI's docs measured the slim image at about 300 MiB of RAM at idle. Disk: about 7 GB is in use once the panel and Open WebUI are installed on our test server; 25 GB is Ubuntu's recommendation.

Section 04Install

How to install Open WebUI

Every step happens in the ServerAvatar panel. No terminal needed.

  1. Pick Open WebUI in 1-Click Recipes

    On your server, open Applications, click Create application and search for Open WebUI under 1-Click Recipes.

  2. Name it, choose a domain and enter the admin email

    Give the app a name and use your own domain, or a temporary one that works right away. Fill in the Admin email field: that address becomes your Open WebUI login. The panel creates a system user for it.

  3. Create it

    Click Create application. The panel starts Open WebUI, turns HTTPS on and shows your admin email with the password it generated. Copy them somewhere safe.

  4. Sign in and connect a model

    Open the app's domain and sign in with the admin email and the generated password. No model is bundled: go to Admin Settings, Connections and add OpenAI, Anthropic, any OpenAI-compatible API or your own Ollama URL. Sign-up is already closed, so nobody else can register.

Section 05FAQ

Questions,answered.

Can't find the answer you're looking for? Reach out to our customer support.

Contact support

Risk free

Deploy your first appin 10 minutes.

Connect a server, pick an application and go live, with SSL and backups already in place.

  • No credit card required
  • Free 4-day trial
  • Deploy in the next 10 minutes