Open WebUI: A Beautiful Interface for Local AI

ChatGPT's Interface, Your Own Server

Running AI models locally with Ollama is great, but chatting in a terminal gets old fast. Open WebUI gives you a polished, ChatGPT-like web interface that connects to your local models.

It looks and feels like the best commercial AI chat apps, but everything runs on your own hardware.

Features That Matter

Multi-model support. Switch between Ollama models, OpenAI, Anthropic, and any OpenAI-compatible API. All in one interface.

Document upload. Drag PDFs, Word docs, or text files into a conversation. Your local AI reads and analyzes them without the files ever leaving your machine.

Image generation. Connect to Stable Diffusion or DALL-E and generate images directly in your chat interface.

Conversation management. Folders, search, tags, export. Better organization than most paid AI chat apps.

User management. Set up accounts for your family or team. Everyone gets their own conversation history and preferences.

Custom model files. Create AI personalities with specific system prompts and model settings. Save them as presets for quick access.

RAG built in. Upload documents to create a knowledge base. Your AI references them when answering questions. All local, all private.

Who Should Use This

Families who want to give everyone access to AI without paying for multiple subscriptions. Install Open WebUI on a home server and everyone connects through their browser.

Small teams who need AI but have data privacy requirements. Lawyers, therapists, accountants — anyone handling sensitive client information.

AI enthusiasts who want to experiment with different models and configurations. Open WebUI makes switching models and testing prompts frictionless.

Teachers who want to provide students with AI access in a controlled environment. Set up accounts, monitor usage, and keep everything on school infrastructure.

Getting Started

If you already have Ollama running, Open WebUI installs with one command:

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main

Open port 3000 in your browser and create your admin account. Connect to your local Ollama instance and start chatting.

The whole setup takes under 10 minutes. The interface is immediately intuitive — if you have used ChatGPT, you already know how to use Open WebUI.

Browse AI interface tools on a-gnt