Health, home and travel decision
MyTrainer
A capable developer can build a useful AI-backed workout planner and tracker, but reproducing the polished mobile UX, media library, and ongoing AI/chat quality of the paid app is multi-week work and would lack the production polish and App Store readiness the commercial product provides.
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-off80 h to build
$100/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 MyTrainer alternatives, with the arithmetic →
What a replacement has to do
- User onboarding chat -> generate personalized plan -> present workout session with exercises/video/timings -> track session results and progress -> adjust plans (monthly check-in or on-demand) -> sync with Apple Health and send reminders
What it still won’t have
- Polished, production-quality mobile UX and App Store distribution work
- Curated exercise video library and in-app media hosting
- Ongoing app updates, localization, and small-bug polish evident in release notes
- Existing user reviews, brand and developer support channels
- Refinements in AI conversation quality and training/tuning not included in a quick build
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
MyTrainer 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-developer iOS app (SwiftUI + Combine, backend Node.js + Postgres on a small VPS) that provides an AI-driven personal trainer prototype. In scope: (1) a chat-style onboarding that stores user profile, equipment and goals; (2) a rule-based plan generator that emits a week's workouts (exercise id, sets, reps, rest) and simple meal/macros targets; (3) a workout session screen with exercise list, timers, and ability to log sets; (4) a Postgres schema for users, workouts, sessions, and progress and a monthly check-in job to adjust plan parameters; (5) Apple HealthKit read (steps/sleep/activity) and write (workout summaries) integration; (6) push/local reminders. Out of scope: exercise video production and hosting, advanced ML model training, multi-user billing, App Store release tasks, and complex nutrition recipe management. Include error handling, authentication, unit tests for plan generation and API routes, and end-to-end tests for the onboarding -> plan -> session flow.
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 productMyTrainer: AI Coach & Trainer - App Store
- official pricingMyTrainer: AI Coach & Trainer - App Store (pricing listing)
- open sourceSnouzy/workout-cool
Integrity checks
What held up, and what did not.
