How Riffn works vs Wattfare

Riffn links your iPhone to a coding agent running in a repo on your own computer, over Tailscale. Start a session, pocket the phone, and keep working by voice while you...

Users connect, set a spending cap, and you call any model through one SDK, charged to them, not you.

About How Riffn works

Riffn links your iPhone to a coding agent running in a repo on your own computer, over Tailscale. Start a session, pocket the phone, and keep working by voice while you drive, walk or do chores. Start a session in the app, lock the phone and put it away: the session stays active in the background, ready for your next spoken turn or a recognised command, while you drive, walk or do chores. The bridge is public source: @riffn/bridge is a ~100 KB Node helper with zero runtime dependencies, Apache-2.0, published from CI with npm provenance.

About Wattfare

Users connect, set a spending cap, and you call any model through one SDK, charged to them, not you. OpenAI-compatible Works with the Vercel AI SDK ~5-min integration. One button connects a user's inference budget to your app, metered, capped, and revocable. The problem AI costs are the one line item you can't predict. Every AI app makes the same uncomfortable bet: price high enough to survive your power users, ration usage so nobody hurts you, or quietly lose money on the heavy ones.