Health, home and travel decision
Pandish
A technical user can reasonably build a narrow self-hosted replacement (photo upload + vision API + basic calorie mapping) using prior open-source calorie trackers as a base, but reproducing the full polished mobile experience, App Store distribution, and any proprietary AI tuning is non-trivial.
View on the App Store↗$9.99/mo
$120/yr
Read off the official pricing page.
$100one-off50 h to build
$20/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 3 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- User takes photo -> image model identifies foods -> map items to calorie/macronutrient estimates -> store meal entry and update progress charts
What it still won’t have
- App Store presence, ratings, and distribution handled by the published iOS app
- Any proprietary, tuned model or internal food-recognition heuristics used by the vendor
- Polished mobile UX and animations visible in the App Store listing
- Built-in barcode scanning and any integrated food database licensing
- Customer support and account/revenue features tied to the published app
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 3 seats.
Money you would actually spend
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
Build a minimal Pandish-like service: backend in Node.js (Express) + Postgres, mobile progressive web app (React) or simple React Native client, and use a hosted vision API (e.g., Google Vision or an image-classification model served via Replicate/OpenAI) for food detection. In scope: photo capture and upload, vision API integration to return detected food labels, mapping of labels to a simple food database (CSV-backed) to estimate calories/macros, store meal entries and weight history in Postgres, session-based user auth, subscription gating (Stripe for web; assume App Store for native builds), and UIs for meal entry and progress charts. Out of scope: training custom vision models, App Store submission process, large-scale food database licensing, and advanced portion-size inference beyond simple heuristics. Include error handling, input validation, automated tests for endpoints, and deployment scripts (Docker + small cloud VM).
How we checked
How the score was reached
- Partly verdict base52
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score59
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 →Integrity checks
What held up, and what did not.
