Open WebUI

Open WebUI is an extensible, feature-rich, self-hosted AI platform designed to run entirely offline. It connects to Ollama and OpenAI-compatible APIs, giving a single interface for chatting with local or remote models while keeping everything on hardware you control.

A built-in inference engine powers local RAG across 9 vector databases, and you can load documents into chat or search the web and browse pages inline. Build custom models and agents, add native Python functions, store persistent artifacts, generate and edit images, and write with full Markdown and LaTeX support. Role-based access control, granular permissions, many-model conversations, and hands-free voice and video chat round it out.

Install with Docker or Kubernetes via kubectl, kustomize, or Helm. The app is responsive across desktop and laptop and ships a mobile PWA with offline access, backed by SQLite or PostgreSQL.