Health, home and travel decision

FitCal

A capable developer can build a useful calorie tracker and diary (photo/voice/text logging) using open-source prior art and third-party model APIs, but reproducing FitCal's full paid product—AI coach, community, and polished iOS features—would require more effort and data than a small DIY replacement reasonably provides.

Visit website
SubscriptionCustom pricing
Initial build64 hours
Monthly upkeep6 hours + $100
Evidence3/3 runs agree

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All FitCal alternatives, with the arithmetic →

What a replacement has to do

  • Capture a meal (photo / voice / text) → run inference to identify foods and portions → calculate calories/macros → save entry in a diary → show daily progress.

What it still won’t have

  • AI Coach that answers based on your diary
  • Public community groups and streak leaderboard
  • Built-in Live Activity and polished App Store UX
  • Any proprietary/undisclosed training data or models used by the vendor

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

FitCal does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying

Subscription price × seats × 12

Build it

AI build APIs + hosting

Time you would spend

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal iPhone calorie-tracking app in SwiftUI with a small backend (FastAPI + Postgres) hosted on a single VPS. In scope: (1) iOS SwiftUI app with camera/photo upload, voice dictation input, and text entry; (2) user profile and daily calorie/macro targets; (3) food database (Postgres) with create/search/edit and barcode-scanning import; (4) integration with an external inference API for image-to-food and text/voice parsing; (5) saving meals to a diary, viewing daily totals, and exporting a PDF report for a selected date range; (6) Apple Health weight/water sync and a Today widget. Out of scope: social/community features, leaderboard, commercial subscription handling, and training custom ML models. Require: error handling on network/API failures, unit tests for backend endpoints, basic end-to-end UI tests for core diary flows, and documentation for deployment (Dockerfiles, systemd/unit, and migration steps).
How we checked2 sources · 3/3 runs agreed · evidence score 62

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 2 cited sources+1
  • 3/3 assessment runs agreed+4
  • Evidence score62

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded