Whelk: Private AI Platform - Your hardware. Your models.
by•
Existing local-AI tools are developer utilities or web wrappers. Whelk is a native iPhone, iPad, and Mac client for AI you run yourself, on-device with Apple Silicon or on your own servers over VPN. What stands out: any chat can be armed into a full agent work session in place, with live tools and approvals. Your models. Your agents. Your network. The trust model is the architecture, not a policy: no accounts, no telemetry, no cloud. Nothing leaves hardware you own. Free for individuals.
Replies
More people than ever run AI on their own hardware, for privacy, for control, for cost. The apps for actually using those models have been an afterthought. Whelk is the company I am building to fix that.
Whelk is a native client for iPhone, iPad, and Mac that talks to your own models, on-device with Apple Silicon or on your own servers over a VPN (like Tailscale). Any chat can be armed into a full agent work session in place, with live tools and approvals. Your models. Your agents. Your network. The trust model is the architecture, not a promise: no servers of mine, no accounts, no telemetry. Nothing leaves hardware you own.
Background: I was CTO at Weedmaps, a public company, VP of Engineering at ShopKeep (acquired by Lightspeed for $440M), and most recently Chief AI Officer and CTO at BuildOps. Private inference is the next platform. Whelk is the app I am building to win it.
Free for personal use, and Enterprise is coming soon. I am here all day, including for the hard questions. Whelk is open core.