Open WebUI
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports a wide range of LLM runners including Ollama and OpenAI-compatible APIs, with a built-in inference engine for Retrieval Augmented Generation (RAG). With over 146,000 GitHub stars, it has become the go-to interface for running local AI models on your own infrastructure.
Key Features
- Effortless Setup — Install via pip, uv, Docker, or Kubernetes, with :ollama and :cuda tagged images for container deployments
- Broad Model & API Integration — Connect any OpenAI-compatible API alongside local Ollama models, supporting LMStudio, GroqCloud, Mistral, OpenRouter, vLLM, and more
- Granular RBAC & User Groups — Define detailed roles, groups, and permissions for secure, tailored multi-user access
- Local RAG Integration — Retrieval Augmented Generation backed by 9 vector databases with hybrid search (BM25 + vector), reranking, and full-context mode
- Web Search for RAG — Search the web through dozens of providers including SearXNG, Google PSE, Brave Search, DuckDuckGo, and Bing
- Multi-Model Conversations — Engage several models at once, harnessing their individual strengths in parallel
- Plugin Support — Extend with Filters, Actions, Pipes, Tools, and Skills via MCP, MCPO, and OpenAPI tool servers
- Image Generation & Editing — Create and edit images with OpenAI DALL·E, Gemini, ComfyUI, and AUTOMATIC1111
- Voice/Video Calls — Hands-free communication with multiple Speech-to-Text and Text-to-Speech providers
- Responsive Design & PWA — Seamless experience across desktop, laptop, and mobile devices
Why Use Open WebUI?
Open WebUI eliminates the need for expensive cloud AI subscriptions by letting you run powerful language models on your own hardware. It combines an intuitive chat interface with enterprise-grade features like user management, RAG pipelines, and plugin extensibility — all fully offline if desired. Whether you are an individual experimenting with local LLMs or a team deploying AI infrastructure, Open WebUI provides a polished, production-ready experience.
Use Cases
- Self-hosted AI assistant for private, offline interaction with local language models
- Team collaboration hub with shared model access, channels, and persistent memory
- RAG-powered document analysis using private knowledge bases
- Multi-provider AI gateway combining local and cloud models
Platform
Linux · macOS · Windows · Docker · Kubernetes
Licence
Custom permissive (BSD-style with branding clause)