An AI assistant whose working box runs in your cloud.

A hosted AI tool can put another company between you and the model provider. Wetlether removes that extra hop: the assistant runs on a machine you own, and your conversations stay there rather than on Wetlether's servers. Your chosen AI provider still receives the requests you send it, under that provider's terms.

Where your data actually goes with most AI tools

With a typical hosted assistant, an extra tool company may receive your prompts and files before sending them to the model provider. Wetlether doesn't: your prompts go from your box straight to the model provider, not through us, and we keep no copy. The chosen AI provider still receives your requests, the same as when you use it directly. For a fully local path where no cloud model provider receives them, you would need to run a local model.

How Wetlether is built instead

Wetlether is a thin app plus a "box" — a small server that runs in your own cloud account, signed into your own AI keys. The app just talks to your box.

• Your conversations, code, and files live on your box, under your accounts. Not on ours.
• We run no AI model ourselves and keep no copy of your conversations — so there is nothing on our side to read, mine, or train on. (We do hold your account and billing details, like any paid app.)
• Your prompts go from your box straight to the AI provider on your own key, the same as if you called them yourself.

The limits

Private doesn't mean magic, so here's the straight version. Your AI provider (Claude, GPT, and so on) still sees the prompts you send it on your key — that's true of any tool, because they're the one running the model; Wetlether just doesn't add itself as a second party on top. And your cloud provider hosts the box. What you're removing is the middleman in between — the extra company that would otherwise sit on your data.

See how it works →

Wetlether — a private AI on a box you own. Plans run from free to $59.99/month.

Keep reading