Exact text from the indicated source. A mention alone does not establish support for your task.
Publisher full description
Kalori is a nutrition-tracking app you use by chatting. Tell ChatGPT what you ate and Kalori logs it, then ask how much is left for today against your calorie and protein, fat, and carbohydrate targets, how your nutrition went this week, or what would fit the rest of your budget at dinner. Weight and exercise are logged the same way, and everything is saved to the linked Kalori account.
In the Kalori iPhone app, users can also choose to import sleep (time asleep and sleep stages) and heart data (resting heart rate and heart rate variability) from Apple Health. Import is off by default and is turned on per category in the app; only daily summaries are stored, ChatGPT reads them only through read-only tools, and they are not used for goal calculations. Users can turn import off at any time and choose to delete the records already imported.
Nutrition values come from Kalori's catalog of Japanese convenience stores and restaurant chains: 490+ chains (Seven-Eleven, Lawson, FamilyMart, Saizeriya, Sukiya, McDonald's Japan and more), refreshed nightly from official chain sources, plus generic dishes for home cooking and non-chain meals. Every item carries a nutritionSource marker: official means the chain publishes the value, partial means published values completed with AI estimates, and estimated means every value is AI-estimated.
A linked Kalori account is required. Personal-record features are available according to the linked account's existing access, and usage limits apply. The plugin does not offer purchases or subscription management.
Main workflows: (1) log what was eaten by describing it, and correct the portion, date, or components in plain language; (2) review the day's totals and what remains against personal calorie and PFC targets; (3) record weight and exercise, review the weight trend, and read imported sleep and heart data alongside meals; (4) find something that fits the remaining budget, for example high-protein and under 500 kcal at Seven-Eleven, and render the choice as a meal-plan card whose totals are computed server-side from catalog values, so the numbers shown are not model estimates.
Search terms, filters, and result counts are retained as the linked account's search history to improve catalog coverage; each call also records the IP address and user-agent in private operational logs that are deleted automatically after about seven days. The tools accept no precise location, chat transcripts, or third-party account identifiers, and personal records are only ever reached through the user's own linked account.