DOALocal AI › Open WebUI
Open WebUI: what it is, how to install it and requirements
Self-hosted, ChatGPT-style web interface that connects to Ollama or OpenAI-compatible APIs.
Checked on 13 Oct 2026. Versions change every week: check the official site before installing.
| Operating systems | Any system with Docker or Python (source) |
|---|---|
| Licence and price | Open WebUI License (BSD-3 style with a branding clause) · free |
| Ease of use | Medium |
| Current version | v0.12.0 (10 Oct 2026) |
| Official site | openwebui.com · GitHub |
How to install it
- With Python:
pip install open-webuiand thenopen-webui serve, and openhttp://localhost:8080. With Docker and Ollama on the same machine, the README gives: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:mainand then openhttp://localhost:3000. The same README has variants for GPUs and for Ollama on another server.
Install guides by system: Windows · Mac · Linux. Which model to download: Which local AI model to pick for your RAM: 8, 16, 24, 32 GB.
Other local AI tools
- Ollama: Engine and app to download and run language models with a single command. It includes a local API so other apps can connect to it.
- LM Studio: Desktop app with a graphical interface to find, download and chat with models in GGUF or MLX format. It also has a local server.
- Jan: Open-source desktop app to chat with models offline, ChatGPT-style.
- GPT4All: Nomic's desktop app to chat locally and ask questions about your own documents (LocalDocs).
- llama.cpp: C/C++ library and command-line tools that many apps are built on and that define the GGUF format. The most technical option.
- ComfyUI: Node-based interface to generate images and video with open models on your own computer.