Open WebUI: a private AI chat on your server
One familiar chat window for the models you pay for, with accounts for your colleagues and conversations stored on a server you rent.
About Open WebUI
Open WebUI is an open-source web interface for large language models. It looks and works much like the chat apps people already know, but it is not tied to one vendor: you connect API keys for OpenAI, Anthropic or any OpenAI-compatible service, or point it at a local Ollama instance.
Beyond chat it offers multiple user accounts with roles, shared prompts, file uploads with document search, web search and image generation through connected services. It is one of the most active self-hosted AI projects on GitHub, and it works well on phones as an installable web app.
Teams self-host it to give everyone access to strong models through a single company key, without separate subscriptions per person, and to keep chat history off third-party chat apps.
What people use it for
One AI chat for a whole team
Create accounts for colleagues and let them use the same connected models, with the administrator deciding who sees which model.
Comparing models side by side
Send the same prompt to two models in one conversation and pick the answer that fits.
Questions about your own files
Upload documents to a chat or a knowledge collection and ask about their contents.
After you order
Open WebUI is installed on your server on its first start. It is available at http://your-server-address:3000/ — port 3000 is opened in the firewall for it. Sign in with the email and password shown in the Rivervo panel; this account is the administrator. Then add your model API keys in the admin settings and create accounts for other users.
How it works
- Choose Open WebUI on the server order page and pick a plan with enough memory.
- The app is installed on the server on its first start, usually within a few minutes.
- Open the server in your panel: the address and the sign-in details are there.