LocalWebAgent
/
WebGPU
The agent plans and runs commands on a Debian machine inside this tab. The model and the computer both run on your device, offline.
LocalWebAgent runs a whole Linux machine and keeps your models and files in your browser. Inside the Hugging Face page it can't save them properly or sign you in, so open it on its own page.
Open LocalWebAgentLocalWebAgentA real Debian computer running inside this browser tab. Install it once (about 440 MB) and it keeps working without an internet connection. Next you'll choose a language model in the Model Manager: download one that runs on your GPU, or connect an API.
Language models are added afterwards and load straight from their Hugging Face repositories under their own licenses. CheerpX is free for personal and open-source use; it loads from Leaning Technologies' CDN and is cached by your browser.