Open WebUI — open source GitHub project

Open WebUI is a self-hosted AI interface for Ollama, OpenAI-compatible APIs, RAG, tools, users, and local LLM workflows.

What Open WebUI is

Open WebUI is a self-hosted AI platform with a user interface for Ollama, OpenAI-compatible APIs, and local LLM workflows. It combines chat UI, users/groups, permissions, RAG, web search, document libraries, model builder, tools, PWA, and enterprise-oriented deployment options.

It became popular as a usable shell around local models. If Ollama provides runtime, Open WebUI adds the product layer: accounts, history, files, retrieval, functions, administration, and a familiar web UI.

What is inside and how it is used

Docker run

This example shows the project shape and the usual way it is used.

Language: Bash

docker run -d -p 3000:8080 \
  -v open-webui:/app/backend/data \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

Its strength is breadth: Ollama, OpenAI-compatible endpoints, vector databases, web search providers, speech-to-text/text-to-speech, image generation engines, pipelines, plugin framework, and observability integrations.

Strengths and limits

Operational limits matter. A self-hosted AI UI needs updates, user permissions, API-key protection, storage management, RAG quality work, and clarity about which data goes to which model or endpoint.