Logo
Deploy Now

Stars

144707

Forks

20931

Watchers

634

Developer links

Open WebUI

Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.

Open WebUI

Benefits

  • Runs Fully Offline
  • Paired with Ollama on the same host, the entire stack, models, embeddings, and chat history, operates with no external network dependency, which suits air-gapped and privacy-critical environments.
  • Local and Cloud Models Side by Side
  • Test a prompt against a local Llama model and GPT or Claude in the same interface, then route each use case to whichever backend balances cost, quality, and privacy.
  • Team-Ready Access Control
  • User groups, role-based permissions, and SSO make one instance serve a whole organization, with admins controlling which models and knowledge bases each group can reach.
  • Your Apps Get an AI API
  • The instance exposes an OpenAI-compatible endpoint, so internal applications can call your self-hosted models through Open WebUI instead of a metered cloud API.

Features

  • Ollama and OpenAI-Compatible Backends
  • Manage and pull Ollama models from the UI, and connect any OpenAI-compatible endpoint: LM Studio, vLLM, GroqCloud, Mistral, OpenRouter, and more, simultaneously.
  • Built-In RAG with Hybrid Search
  • Knowledge bases backed by nine vector database options, eight content-extraction engines, BM25 plus vector hybrid retrieval, reranking, and a full-context injection mode.
  • Web Search Integration
  • Inject live results from SearXNG, Google PSE, Brave, Kagi, Tavily, DuckDuckGo, and dozens of other providers directly into conversations.
  • Python Tools, Pipelines, and MCP
  • Write Python tools with the built-in code editor, build pipeline filters for rate limiting or translation, connect OpenAPI tool servers, and use MCP servers over streamable HTTP.
  • Voice, Vision, and Image Generation
  • Speech-to-text input, text-to-speech output, multimodal image understanding, and image generation through supported backends.
  • Multi-User Administration
  • RBAC with user groups, SSO integration, usage controls, and per-model access rules for running a shared organizational instance.