Open WebUI

⭐ 140.7k MIT Python/TypeScript 0.6.0

The most feature-rich self-hosted AI platform, supporting Ollama/OpenAI APIs and featuring a built-in RAG engine.

📋 Info

GitHub Stars⭐ 140.7k Stars
LicenseMIT
LanguagePython/TypeScript
Version0.6.0
Updated2026-06-02

📖 Overview

Open WebUI is currently the most feature-rich self-hosted AI frontend platform available. It serves not only as the ideal companion for Ollama—offering a ChatGPT-like conversational experience—but also includes advanced features such as an RAG engine, multimodal support (image recognition, voice input/output, and video understanding), and online search capabilities. It supports multi-user management, permission controls, and SSO authentication, making it suitable for both personal use and team deployments. Thanks to PWA technology, it can be accessed on mobile devices, providing an experience close to that of a native app. An Agent workflow engine was added in 2026, enabling the orchestration of multi-step AI tasks. If you’re looking for a fully functional and aesthetically pleasing local AI hub, Open WebUI is the top choice.

✨ Features

  • ChatGPT-style interaction with 10 times more features
  • It comes equipped with a built-in RAG engine supporting 9 different vector databases.
  • Multimodal: speech recognition / ASR, text-to-speech / TTS, and video processing.
  • Integrated online search capabilities (Google/Bing/DuckDuckGo, etc.)
  • Multi-user management + SSO + RBAC

Advertisement

🚀 Quick Start

pip install open-webui
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

🔗 Related Tools