open-webui
A polished chat window for your own models, served from your own machine.
What it is
Open WebUI is a self-hosted chat interface — the browser window you actually type into — built to sit in front of local models and hosted APIs. It looks and behaves like the commercial chat products, but the whole thing runs on your hardware and keeps its conversations in your own database.
It talks to Ollama out of the box and also speaks the OpenAI-compatible API, so the same interface can mix a local model, a cloud model and anything in between. On top of plain chat it adds model switching, document upload with retrieval, prompt presets, user accounts and an admin panel for controlling who can reach which model.
Pick it if you already have models running somewhere and want a real front end for them, or if a small team needs shared access without every person installing anything on their laptop. If you are one person talking to one model, the command line may be all you need.
Why we recommend it
It turns a raw model into something you can hand to other people
A model behind a terminal is fine for one person. A browser UI with accounts, saved chats and permissions is what you need the moment a colleague or a client has to use it. This gives you that without building it yourself.
One interface for local and hosted models
Because it speaks the OpenAI-compatible API, you can register a local Ollama model, a paid cloud model and an internal endpoint side by side. Switching between them is a dropdown, not a rewrite.
Your chat history stays on your disk
Conversations, uploaded documents and user data live in your own database rather than a vendor account. That matters when the chats contain client work or anything you would rather not leave with someone else's service.
Document chat without extra plumbing
Upload a PDF or a set of notes and ask questions against it — the retrieval pipeline is built in. You get the useful part of a retrieval setup without wiring a vector store together first.
How it scores
These are our editorial ratings, not benchmark results. We score on how the project behaves in practice — how long it takes to get running, how good the documentation is, how responsive the maintainers are, and how well it holds up over time. The licence and star count above are read from GitHub and are a snapshot.
Pros and cons
Strengths
- Polished interface that non-technical users pick up quickly
- Works with local Ollama models and any OpenAI-compatible API
- Built-in accounts, persistent chat history and an admin panel
- Very active project with frequent releases and a large user base
- Runs as a single container, so deployment is repeatable
Trade-offs
- The recommended install is Docker — there is no desktop app to double-click
- Needs a separate model server behind it before it does anything useful
- The feature surface is large, and the admin settings take time to learn
- Heavier than a plain chat client: it wants a database and a server that stays up
How to get it
One-line install
Prefer the terminal? Copy a command and you are done.
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
pip install open-webui
Source and documentation
At a glance
| Category | Local AI |
|---|---|
| Licence | See repo |
| Written in | Python |
| GitHub stars | 151,523 |
| Repository | open-webui/open-webui |
Licence and star count were read from the GitHub API when this page was generated and are a snapshot. Check the repository for the current figure and the authoritative licence text.
Other Local AI tools
We are not affiliated with open-webui or its maintainers. We list it because it is genuinely useful and genuinely free. If you plan to build a commercial product on top of it, read the licence on the repository first.