Open WebUI

What is Open WebUI?

Open WebUI is an extensible, self-hosted web interface for running AI models locally. It works with Ollama and any OpenAI-compatible API, and supports RAG document chat, model management, image generation and multi-user access. Everything runs on your own hardware.

Best for

Anyone running Ollama or local models who wants a proper chat UI

Why choose Open WebUI

Open WebUI is the friendliest way to get a private ChatGPT experience. It looks and behaves like the interface everyone already knows — chats, folders, model switching, document uploads — but it talks to whatever backend you point it at, including models running entirely on your own machine. If your hesitation about AI assistants is that every prompt leaves your network, this removes that objection without asking you to give up the interface you are used to.

Replaces

• ChatGPT
• Claude
• Google Gemini

Key features

• Works with Ollama and OpenAI-compatible APIs
• RAG over your own documents
• Multi-user with role management
• Model builder and fine-tuning support

What to watch out for

The quality of your experience is entirely determined by the model behind it. A small local model on consumer hardware will feel noticeably less capable than a hosted frontier model, and no amount of interface polish fixes that — be realistic about which tasks you are actually asking it to do. The project also moves quickly, with frequent releases and occasional breaking changes in configuration. And if you connect it to a paid API instead of a local model, you have solved the interface problem but not the data-residency one.

How to deploy

• Docker
• Kubernetes
• pip

Getting started

The simplest path is Docker alongside Ollama, with the two containers able to reach each other — point Open WebUI at Ollama's endpoint and it will discover your local models automatically. Pick models by your hardware, not by benchmark charts: a 7B model at good speed beats a 70B model that takes two minutes per reply. Enable authentication before exposing the instance to anything, because an open instance lets anyone spend your compute. If you plan to keep chat history long-term, decide up front where it lives and back it up accordingly.

Project health

• GitHub stars: 153,674
• Last code push: 2026-10-01
• Open issues: 296
• Status: actively developed

Figures pulled from the GitHub API and refreshed periodically.