About Bein
Bein is a health company.
It makes apps that measure how your own body handles what you eat, where most apps estimate it from a formula built on averages. Burnin works out your real daily calorie burn from what you log and what you weigh. Cookin keeps the recipes most of your meals come from.
Who makes it
One developer.
Bein is one developer, who writes the apps, the blog and the videos. Both apps are free and need no account. Why Bein exists, in full: Why Bein builds Burnin and Cookin.
On the name
Bein stands for Being Intelligent, about what you eat and what your body does with it.
The apps are named the same way, from a verb with the g dropped: Burnin from burning, Cookin from cooking, Bein from being.
The apps
Burnin and Cookin
| Burnin | Cookin | |
|---|---|---|
| What it is | Adaptive calorie tracker | Recipe keeper |
| Its side of the loop | What your body does with what you eat | The recipes your meals come from |
| What it does | Measures your real metabolic rate from what you log and how your weight moves, instead of a formula | Turns TikToks, links and cookbook photos into structured recipes |
| Platforms | iOS, Android | iOS, Android |
| Price | Free (one banner, profile tab only) | Free, no ads |
| Account required | No | No |
| Works offline | Yes, including AI | Yes, including AI |
| Store | App Store · Play | App Store · Play |
For press
One AI model, shared by two apps.
Take anything on this page without asking. For a build, a demo, an interview or detail on the architecture, email dan@bein.ltd.
A solo developer shipped two consumer apps that share a single 2.4 GB AI model on the device, so users only download it once. Neither app has a backend of its own or an account system. The AI features run on the phone and work in airplane mode.
The model is downloaded to the phone and runs there. When both apps are installed, the second one finds the first one's copy of the model and uses it, so the multi-gigabyte download happens once. On Android the app holding the model runs the inference for the other; on iOS the model file sits in a shared App Group. On Android only apps signed with the same certificate can call it; on iOS only apps from the same developer account can open the App Group.
Phones too weak to run the model do not get a cloud fallback. They do not get the AI features, and the manual tools keep working. No device is sent to a cloud model instead.
Boilerplate
Boilerplate
Bein is a health company that makes apps to measure how a person's own body handles what they eat. Its apps are Burnin, which measures a person's metabolic rate from logged food and weight, and Cookin, which turns TikToks, links and cookbook photos into recipes. Their AI runs on the device; they have no backend of their own and no user accounts, and they are free. Bein is the work of one developer.
Technical facts
Technical facts
- Model: runs on LiteRT-LM, roughly 2.4 GB, downloaded once by the user.
- Android sharing: AIDL bound service that accepts calls only from apps signed with the same certificate.
- iOS sharing: shared App Group between the two app sandboxes.
- Vision across apps: on Android, an app without the model can pass a photo's file descriptor to the sibling that has it and still log a meal from a photo.
- Fallback: on incapable devices the AI features are unavailable rather than served from a cloud; manual entry is unaffected.
- Telemetry: anonymous product analytics only, with no identity, no user content and no location. Diaries, recipes, photos and AI prompts stay on the phone, except Cookin's voice dictation on some Android phones.
- Built with: React Native (Expo) and TypeScript, with native Kotlin and Swift modules for the inference layer.
Press kit & contact
Contact
Assets
App icons and device-framed screenshots (iPhone and Android) for each app, cleared for editorial use.
For a particular screen, a different aspect ratio or a screen recording, ask and it will be sent the same day.
Talk to us
Bein is one developer. Email dan@bein.ltd and it goes straight to the person who wrote the code.
Available to go into detail on running a multi-gigabyte model on the device in React Native, or to send a build.