open-webui

Why we included this project

Open WebUI is the self-hosted chat interface most teams end up installing when they want a proper front end for their models. One web app connects to local Ollama models and any OpenAI-compatible API, so you can point it at vLLM or Groq alongside local models without switching between tools. It goes beyond plain chat: per-user roles and permissions, memory that persists across conversations, document uploads with local RAG, web search, and image generation are all built in. Because it runs fully offline and deploys with Docker or Kubernetes, it suits teams that need to keep data on their own hardware. You can stand up a private ChatGPT-style workspace quickly and extend it later with plugins and custom agents.