Health, home and travel decision
Mahlzait
A capable developer can build a useful, narrower replacement (core logging, barcode lookup, basic photo-based suggestions) using existing OSS (e.g., OpenNutriTracker) and third-party vision APIs; reproducing the polished native app, integrated chat, App‑Store UX, multi-channel integrations and ongoing AI improvements is more work and likely not worth reimplementing unless you only need the core workflow.
View on the App Store↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off48 h to build
$60/mo6 h/mo upkeep
No published price to break even against.
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 Mahlzait alternatives, with the arithmetic →
What a replacement has to do
- User logs a meal (photo/barcode/voice/text) → app identifies item(s) and nutrition → store entry in diary → update daily calories/macros and weight progress
What it still won’t have
- Polished native iOS UI/UX, widgets and Apple Watch support
- In-app purchase plumbing and App Store distribution polish
- WhatsApp integration and chat UX
- Proprietary AI model or tuned image-recognition accuracy and ongoing model improvements
- Ongoing AI web-search integration for missing foods
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Mahlzait 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
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 AI-assisted calorie-tracking web app using React (TypeScript) for the frontend, Node.js (Express) + Postgres for the backend, and deploy on Vercel (frontend) + Heroku or Railway (backend, Postgres). Core features in scope: user signup/login (JWT), meal diary CRUD, upload meal photo and submit to a vision API (e.g. OpenAI/other) for food identification, barcode scan endpoint that looks up nutrition entries in a seeded Postgres table, macros and calorie target calculation, weight history and simple fasting flag, and PDF export of a report. Out of scope: native iOS widgets, Apple Watch app, WhatsApp integration, advanced AI chat flows, and paid in-app purchase plumbing. Require server-side validation, error handling, basic tests for endpoints, and deployment scripts; include README with setup and migration steps.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 4 cited sources+3
- Evidence score60
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 · 4
Every page the run actually retrieved.
- official productCalorie Counter AI - Mahlzait
- official productCalorie Counter AI - Mahlzait (in-app purchases)
- official productMahlzait features list
- open sourcesimonoppowa/OpenNutriTracker
Integrity checks
What held up, and what did not.
