AI assistants and search decision
ChefGPT
A focused web replacement (photo→ingredient→recipe→nutrition + meal plans) is buildable by a competent developer using existing vision and LLM APIs and the listed open-source tracker, but full parity with the mobile app's polished native UX, community Discovery feed, and platform integrations would be time-consuming to match.
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-off52 h to build
$75/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 ChefGPT alternatives, with the arithmetic →
What a replacement has to do
- Collect user profile and goals → accept ingredient list or photo → call vision/LLM to generate recipe and nutrition breakdown → save meals and update daily calories and meal plans → produce shopping list and analytics.
What it still won’t have
- App Store distribution and native iOS integrations (Live Activities, lockscreen widgets)
- Built-in community Discovery feed of user-submitted recipes
- Polished mobile UX and ongoing app-store oriented QA
- Apple Health integration and platform-level tracking
What remains hard
- Integration maintenance
Apple Health Tracking
- Integration maintenance
Calendar Integration for Meal Plans
- Execution quality
We’ve stirred the pot and seasoned the code! This update brings new features, fresh improvements, and bug fixes making sure everything runs smoother than melted butter:
First-year cost
No published price
ChefGPT 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 single-tenant web replacement for ChefGPT using Next.js (React) frontend, Node.js + Express backend, Postgres for data, and deployed on Vercel (frontend) + Fly.io or Render (API). Core features in scope: 1) onboarding UI collecting lifestyle and dietary preferences, 2) photo upload endpoint that forwards images to a vision API (e.g., hosted vision provider) and returns detected ingredients, 3) integrate an LLM API for recipe generation with prompt templates supporting ingredient swaps and portion scaling, 4) nutrition calculation using an open nutrition DB (import CSV), 5) meal-plan builder that generates weekly plans and a consolidated shopping list, 6) simple analytics page for daily calories and macros. Out of scope: native iOS app, App Store distribution, image-generation for recipe images, and advanced community feed. Include authentication, per-user data isolation, input validation, error handling, and automated tests for API endpoints and core UI flows.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 3 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score64
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 · 3
Every page the run actually retrieved.
- official productChefGPT: AI Calories Tracker App - App Store
- open sourceTandoorRecipes/recipes
- open sourcemealie-recipes/mealie
Integrity checks
What held up, and what did not.
