coderqh

Grubora — Flutter AI Calorie Tracker App Template

Photograph a meal, let a vision model name the foods, and get calories computed from a bundled USDA table.

Grubora — Flutter AI Calorie Tracker App Template

The live preview on CodeCanyon is this app compiled for the web: the real build, not a video.

Grubora splits the work between the model and the device. A vision model reports what is on the plate and roughly how much; the app then looks each food up in 1,200 bundled USDA FoodData Central entries and does the arithmetic itself. The reply format has no calorie field at all. Results land as editable rows with grams, computed figures and a five-dot confidence mark, and the total updates as portions change.

The day is shown as a measuring beaker with the target line below the rim, followed by four meal sections with subtotals. Macro balance is plotted on a triangle where each day is a point. Intermittent fasting appears as a sash window tied to the clock. Daily targets come from Mifflin-St Jeor, and the targets screen shows every step.

Features

  • Plate breakdown rows with editable grams, device-computed figures and a five-dot confidence mark
  • Bundled table of 1,200 USDA SR Legacy foods with seven nutrients per 100 g and household measures
  • Day ledger drawn as a measuring beaker, with per-meal subtotals underneath
  • Macro triangle that plots each day as a point and your target as a region
  • Eating window drawn as a sash window, based on clock times
  • Targets from Mifflin-St Jeor, an activity factor and a goal, with each step shown
  • Barcode lookup against Open Food Facts by typing or pasting the digits
  • Unmatched foods are flagged with a search prompt, never swapped for a lookalike
  • Google Gemini by default, plus OpenAI and Anthropic Claude, with a Demo mode that runs the full pipeline locally

What it looks like

8 images
Setup summary table comparing what it takes to run the app — Grubora
Setup summary table comparing what it takes to run the app
Meal photo broken into editable food rows — Grubora
Meal photo broken into editable food rows
Food details sourced from the bundled USDA table — Grubora
Food details sourced from the bundled USDA table
Day ledger beaker with meal sections and subtotals — Grubora
Day ledger beaker with meal sections and subtotals
Macro triangle plotting days against a target region — Grubora
Macro triangle plotting days against a target region
Eating window drawn as a sash window — Grubora
Eating window drawn as a sash window
Food search, targets, barcode lookup and other screens — Grubora
Food search, targets, barcode lookup and other screens
Summary of what the download package contains — Grubora
Summary of what the download package contains

Who it is for

  • You are building a calorie or nutrition logging app and want figures that trace back to reference data.
  • You want photo logging from Gemini, OpenAI or Claude while keeping the arithmetic in your own code.
  • You need a populated demo diary that responds on every screen before any key is entered.

In the box

from the shipped zip
  • Full Flutter source at the top of the zip, no obfuscation and no licence server
  • Offline HTML documentation: setup, re-theming, app name and bundle id, troubleshooting
  • 9 Dart test files in the app

Run it after download

the app
# unzip the download, then
# the app is at the top of the zip
$ flutter pub get
$ flutter run

Setup, including any keys or services the app talks to, is covered step by step in the bundled documentation.

Spec

measured
Screen widgets14
Dart files93
Tests in the package9
Dart SDK^3.7.0
Back endNone bundled; the service layer is where yours goes
PlatformsiOS + Android, one codebase

Counted from grubora-v1.0.zip, the file uploaded to CodeCanyon. Screen widgets are the view, screen and page classes in the source, so the number can differ slightly from a count of routes.

Questions

Something else? Ask on the item's CodeCanyon page; the author answers there.

Does the AI decide the calorie numbers?

No. The model names the foods and estimates portions; calories and macros are calculated on the device from the bundled USDA table. Figures remain estimates drawn from reference data.

Which providers are supported, and what works without a key?

Google Gemini (default), OpenAI and Anthropic Claude, with keys supplied by you or your users. Demo mode is on out of the box and runs the whole flow against the bundled food table.

Is this a medical or diet tool?

It is a logging tool. It does not replace professional medical advice, diagnosis or treatment, and it applies a floor to the daily calorie target it sets.

More AI app templates

same author
See Grubora on CodeCanyon →

Sold on Envato's CodeCanyon marketplace, which handles payment, VAT, invoices and the download.