# Open WebUI

Open WebUI is a self-hosted web interface for using large language models. It is open source and self-hosted, installable on Umbrel, Proxmox, TrueNAS, Unraid, Kubernetes (Helm) and ZimaOS.

Canonical page: https://ourlocalhost.com/app/3575/open-webui

## Description

Open WebUI is a self-hosted web interface for using large language models. It lets you chat with local models through Ollama or connect to hosted models with API keys, giving homelab users a private, browser-based LLM workspace.

## Platform availability

Available on 7 of 10 platforms: Unraid, TrueNAS, Umbrel, ZimaOS, Proxmox, Helm, Any server.

## Health score

84/100 (Excellent), based on 4 of 4 factors.
- Maintained: 100 (last commit 18 days ago)
- Popular: 100 (157,775 GitHub stars)
- Easy to install: 85 (7 install platforms, install notes, Docker image)
- Light to run: 10 (16 GB minimum RAM)

## Links

- Documentation: https://docs.openwebui.com/
- Umbrel: https://apps.umbrel.com/app/open-webui
- Proxmox: https://community-scripts.github.io/ProxmoxVE/scripts?id=openwebui
- TrueNAS: https://apps.truenas.com/catalog/open-webui/
- Unraid: https://ca.unraid.net/apps/open-webui-0z497h31ntbiab?q=open-webui
- Kubernetes (Helm): https://artifacthub.io/packages/helm/open-webui/open-webui
- GitHub: https://github.com/open-webui/open-webui
- Official website: https://www.openwebui.com/
- ZimaOS: https://github.com/IceWhaleTech/CasaOS-AppStore/tree/main/Apps/OpenWebUI

## Common questions

### Which Open WebUI image tag should I use if my models run on a separate Ollama instance?

Use the :slim tag, also called :main-slim, when your models run through a hosted API, your own model server, or a separate Ollama instance. The default database and file storage still work, but knowledge search and voice need external services.

### Can Ollama handle several simultaneous connections when used with Open WebUI?

Yes, Ollama can be run as an HTTP server so several connections can be made at the same time, which fits well with an Open WebUI setup.

### Can I securely access Open WebUI from a phone?

A self-hosting setup using OpenVPN provides private LLM access and includes RAG and phone access.

### Can a PCIe riser be used to connect multiple GPUs for LLM work?

One setup used a PCIe 1x to 4x16 adapter to connect graphics cards. Bandwidth is reduced, but the user reported slow model load times with stable performance for LLM use.

## Alternatives

- Alpaca - Ollama Client: Alpaca is an Ollama client where you can manage and chat with multiple models, Alpaca provides an easy and begginer friendly way of interac…
- AnythingLLM: AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-aug…
- Ensu: Private offline on-device local LLM app by Ente, open source code, no accounts or tracking, and works cross-platform on mobile and desktop…
- Google AI Edge Gallery: A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
- Jan.ai: Open-source offline AI chat software supporting local LLMs, cloud model connections, custom assistant creation, OpenAI-compatible API, and…
- LM Studio: LM Studio is an application for running and experimenting with local large language models (LLMs) such as gpt-oss, Llama, Gemma, Qwen, and…
- LibreChat: LibreChat is an open-source, self-hosted, multi-provider AI chat interface that provides a ChatGPT-style experience for teams or individual…
- Ollama App: A modern and easy-to-use client for Ollama.
- SillyTavern: SillyTavern is a self-hosted, open-source front-end that provides a single unified interface for multiple large language model (LLM) APIs.
- Text generation web UI: A Gradio web UI for Large Language Models.
- local.ai: 🎒 local.ai - Run AI locally on your PC!.

---
Source: Our Local Host (https://ourlocalhost.com/app/3575/open-webui), the self-hosted and open-source app directory.
