PocketAgent — local chat

A minimal WebLLM chat page that loads a small model into your browser tab (first time is a big download, then cached). Your installed PocketAgent is prepended to the system prompt automatically. Zero server, zero API key, nothing leaves the tab.

Model

not loaded

first time? The model weights are fetched from the MLC WebLLM CDN and cached in your browser. Subsequent loads are local. Plan for 0.3–2.4 GB on first use. Needs WebGPU — Chrome/Edge on desktop, Safari 16.4+, Firefox 113+ with flag.

Active agent

(no agent installed)

Install an agent from the gallery, paste a #pa=… URL, or train your own on EML-Foundation.

Chat

PocketAgent landing · Ollama bridge · spec