[Script request]: browser-use, allow local LLM to utilize your desktop

[Sedation6612]

Application Name

web-ui

Website

https://github.com/browser-use/web-ui

Description

Given that we have Ollama and OpenWebUI, I think this would pair perfect!

This is a custom web UI that utilized an in-house Ollama instance, or cloud AI to control a browser to do tasks for you!

It's basically ChatGPT Operator but free.

There's a CLI version, and a UI version.

Would also be neat if during the installation, it allows you to point the config file to your already created Ollama container.

https://github.com/browser-use/browser-use
https://github.com/browser-use/web-ui

Due Diligence

• I have searched existing scripts and found no duplicates.
• I have searched existing discussions and found no duplicate requests.

[2runX]

https://github.com/open-webui/open-webui?tab=readme-ov-file#installing-open-webui-with-bundled-ollama-support

Meine Erfahrung
OpenWebGui in Docker / & Ollama getrennt bei CPU only .
Max. CPU Kerne (echte -1) für Ollama eingestellt werden + >8GB RAM +50% Swap wegen dem Workload.
Ollama Modelle gemma3:4b / qwen3:4b laufen ohne Probleme im RAM 8GB ohne zu swap zu brauchen.