Save this plugin to Following and return to review observed changes. Follow up to 10 plugins free.
Description
From the marketplace listing
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.
Language: English · Automatically detected from descriptions.
Nutrition values come from Kalori's catalog of Japanese convenience stores and restaurant chains: 460+ chains (Seven-Eleven, Lawson, FamilyMart, Saizeriya, Sukiya, McDonald's Japan and more), refreshed nightly from official chain sources...
After
Nov 3, 2026 · 00:12 UTC
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 th...
Listing and tool update; adds read access to sleep and heart data that the user chooses to import, and saved review notes.
- Renamed the listing to "Kalori: Chat Nutrition Tracker" and changed the subtitle to the chain catalog; the description now explains the opt-in Apple Health import and its data handling, and a test case covers get_sleep and get_heart_rate_summary.
- Added get_sleep and get_heart_rate_summary: read the nightly sleep summaries (time asleep and sleep stages) and the daily resting heart rate and heart rate variability that the user chose to import from Apple Health in the Kalori iPhone app. Import is off by default and chosen per category; only daily summaries are stored, they are not used for goal calculations, and both tools are read-only within the linked account.
- Added save_review_note and get_review_notes: keep the key points of a review only when the user asks or agrees, and read them back in a later chat. A saved note can be undone from its result card and is deleted with the account.
- Clarified the descriptions of search_foods, log_meals, and get_food_details; their inputs still accept the previous forms.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package author
KALBI LIMITED LIABILITY COMPANY
Listing translations
ja-JP
Commerce declaration
Does not support commerceThis does not establish whether access is free or paid.
Review scenarios
5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
Log meals by describing what was eaten or by picking catalog items
Correct a logged meal's portion, date, or components in plain language
Review a day's or week's calories and PFC against personal targets
Record weight and exercise and review the weight trend
Log strength workouts with exercises and sets, and review past sessions
Register daily supplements so their label nutrients count toward each day
Save meal sets and repeat past meals exactly as logged
Change goals and meal budgets, applied only after the user confirms
Find meals that fit the remaining calorie or PFC budget
Search 460+ Japanese convenience-store and restaurant chains, filtered by calorie and PFC ranges
Look up several dishes in a single call when planning a meal or a shopping list
Render a meal-plan card whose totals are computed server-side from catalog values
Match a packaged food's nutrition label to the catalog product
Label every value as published by the chain, partially estimated, or fully estimated
List supported chains and re-fetch the exact nutrition of a catalog item by id
Read sleep and heart summaries the user chose to import from Apple Health (read-only)
Keep the key points of a review, only when the user agrees, and continue from them in a later chat
