Open WebUI is a self-hosted AI platform that supports various LLM runners and offers extensive features for AI deployment. It provides installation options via pip and Docker, with a focus on user-friendly interfaces and integrations.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
Open WebUI is an extensible, user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG.
How it works
Open WebUI integrates with multiple AI models and APIs, allowing users to connect any OpenAI-compatible API alongside local Ollama models. It features a granular Role-Based Access Control (RBAC) system, plugin support for extending functionality, and persistent memory for context retention across conversations.
Getting started
Open WebUI can be installed using pip or Docker. For pip installation, use:
pip install open-webui
To run Open WebUI after installation:
open-webui serve
For Docker installation, use:
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
Recent releases
- v0.10.2 (2026-07-01): Added streamed reasoning display for models.
- v0.10.1 (2026-06-29): Fixed issue with shared folder read-only chats.
- v0.10.0 (2026-06-29): Introduced folder sharing with access control.
- v0.9.6 (2026-06-01): Added official knowledge base sync tool.
- v0.9.5 (2026-05-10): Implemented redirect-based SSRF protection.
Traction
- Stars: 145091
- Forks: 21017
- Open issues: 403
Caveats
- License: none listed
- Open issues: 403
- Created: 2023-10-06
- Last push: 2026-07-10