PRIVATE AI, RUN BY NO ONE
Type a question and a stranger's idle GPU answers it. The network forgets you the moment it replies.
Because no one is. There's no signup and no session to tie a question to — it leaves your machine already stripped of you.
No datacenter to knock on. Idle machines around the planet pick jobs off the wire — you never learn whose GPU, they never learn it was you.
A prompt lives exactly as long as its answer takes to stream. Nothing to leak, nothing to subpoena, nothing to train on.
Open models on independent hardware — no corporate layer deciding which questions are acceptable. What you may ask is up to you.
The question is stripped of anything that points home before it leaves.
The network grabs whichever idle machine is closest to free.
A stranger's GPU does the thinking and streams straight back to you.
Job done, job gone. No copy exists anywhere on the network.
One command turns any machine with Ollama into a worker. It answers for strangers in the background and keeps 70% of every job, paid in $PINCH — points pegged to $1, withdrawable as $CLAW whenever you like. setup guide →