Every "AI writing assistant" promises privacy then quietly streams your drafts to someone else's server. RephrAIs flips that script by running entirely offline in your browser, using compact open source models like Llama and Phi 3 accelerated on your local hardware. No prompts, emails, or DMs ever hit a remote API which is either incredibly reassuring or totally overkill, depending on how paranoid you are about data.

I'm curious where PH builders land on this:

Is true on device AI (no cloud, no logs) a must have or a nice to have?

If you're a lawyer, doctor, founder, or handle sensitive client work, would you actually switch from Cloud AI to something like a RephrAIs bookmarklet that lives in your browser?

Most of us casually paste raw emails, negotiations, and even investor updates into AI tools and then just hope the privacy policy is as strong as the landing page copy. RephrAIs takes the opposite extreme: everything runs locally inside your browser with a credit-based system, no account-level data mining, and no text ever leaving your device. You still get professional/creative rephrasing modes for emails and social posts just without the invisible "thanks for your training data" tax.

I'd love to hear from the PH crowd:

Where's your personal line for "too sensitive to paste into ChatGPT/Claude/etc." or do you have no line?

Would you trade a bit of "GPT-level magic" for a fully offline, hardware-accelerated rephraser you can trigger via a bookmarklet anywhere you write?