open-webui/open-webui

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

What it solves

Open WebUI provides a self-hosted, provider-agnostic interface for interacting with AI models. It eliminates the need to rely on a single AI provider by allowing users to mix and match local models (via Ollama) and cloud-based models (via OpenAI-compatible APIs), all while offering a feature-rich environment that can run entirely offline for maximum privacy and sovereignty.

How it works

The platform acts as a central hub that connects to various model providers like Ollama, LMStudio, GroqCloud, and vLLM. It provides a comprehensive web-based frontend with built-in support for RAG (Retrieval Augmented Generation), image generation, and voice/video calls. It can be deployed via Docker, Kubernetes, or pip, and supports a wide range of vector databases for document storage and retrieval.

Who it’s for

It is designed for individuals and teams who want a professional, self-hosted AI interface with granular access controls, enterprise-grade authentication (LDAP/SSO), and the ability to run models locally or in the cloud.

Highlights

  • Broad Integration: Supports Ollama and any OpenAI-compatible API.
  • Local RAG: Integrated retrieval augmented generation with support for 9 different vector databases and multiple OCR engines.
  • Extensibility: Plugin system supporting Filters, Actions, Pipes, Tools, and Skills, including MCP and OpenAPI tool servers.
  • Enterprise Ready: Includes RBAC, user groups, LDAP/Active Directory integration, and SCIM 2.0 provisioning.
  • Multimodal Capabilities: Built-in support for image generation (DALL-E, ComfyUI, AUTOMATIC1111) and voice/video calls with multiple STT/TTS providers.
  • Productivity Tools: Features a dedicated notes workspace, shared team channels, and AI-managed calendars with native function calling.

Related

  • Project
    ParisNeo/lollms-webui

    A unified local web interface for accessing hundreds of LLMs and multimodal AI models for text, image, video, and music generation.

  • Project
    rag-web-ui/rag-web-ui

    An intelligent dialogue system that allows users to build custom Q&A services by combining their own document knowledge bases with LLMs using Retrieval-Augmented Generation.

  • Project
    the-open-agent/openagent

    An open-source personal AI assistant platform that combines LLMs, RAG, and autonomous agent loops into a single, self-hostable binary.

  • Project
    swuecho/chat

    A self-hosted chat platform that supports multiple LLM providers like OpenAI, Claude, and Ollama, featuring a built-in API gateway and conversation management.

  • Project
    mlc-ai/web-llm

    A high-performance in-browser LLM inference engine that uses WebGPU to run language models locally without a server.