Private AI Chat

A fully capable AI that runs inside your browser. No servers, no accounts, no data collection — ever.

100% On-Device Zero Data Sent Works Offline Always Free

WebGPU not available. Your browser doesn't support WebGPU, which is required to run AI models locally. Please use Chrome 113+ or Edge 113+ on desktop for the best experience.

Choose a Model

Qwen3.5 0.8B ~0.4 GB · Fastest Ministral 3 3B ~1.9 GB · Balanced Qwen3.5 4B ~2.4 GB · Smartest

Initializing…

Your private AI is ready. Ask me anything — all processing happens on your device.

How it works

The AI model downloads to your browser cache (~0.4–2.4 GB depending on the model, one time only) — subsequent visits are instant.
All inference runs on your GPU or CPU using WebGPU — nothing is transmitted to any server.
Closing the tab clears all conversation history from memory.
No account, no API key, no tracking, no subscription — completely free forever.