GitHub radar
Open WebUI: A self hosted interface for Ollama and OpenAI
Self hosted offline AI interface. Connect to local models using Ollama, OpenAI APIs (e.g., OpenRouter, LMStudio, GroqCloud, Mistral, vLLM, …) or any other compatible API. Use a beautiful web UI to interact with these models. One docker command to install!
Open WebUI is a self hosted AI interface. It has a rich set of features to interact with AI models. Connect to local models using Ollama or any OpenAI compatible API (e.g., OpenRouter, LMStudio, GroqCloud, Mistral, vLLM, …). Upload files & images. Use voice input. Perform RAG (search web, documents). Manage your models. View fine grained user roles & permissions. Extend functionality using plugins/tools. Install using Docker, Pip, Kubernetes. 150,000+ stars in 3 years. De-facto standard for self hosted AI interfaces.
Why a vibe-coder should care
Open WebUI allows you to use an elegant UI to interact with your local AI models. Say goodbye to the terminal. Centralize all your cloud based APIs (OpenAI, Anthropic, …) into one single interface. Keep track of your conversation history locally. Once installed, there’s no subscription fee!
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Deploy Open WebUI from https://github.com/open-webui/open-webui — follow the README (Docker required), start the container and open http://localhost:3000 in the browser. If Ollama is already installed, connect it. If not, show me how to add an external API. Ask me if you need any keys or permissions.
Runs on a regular laptop — just Docker needed. For local models, Ollama and 8 GB of RAM or more are also required (exact amount depends on the chosen model).
Open on GitHub▌ More finds