Health, home and travel decision
SuperShrimp
A competent developer can reproduce SuperShrimp's core (local pose inference, real-time alerts, and local analytics) in a few dozen to a few hundred hours using existing JS pose projects; the vendor's polish, installers, and social features are what you'd give up.
Visit website↗Built by Marc Lou, who ships 32 products in this index
Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off110 h to build
$0/mo3 h/mo upkeep
No published price to break even against.
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
- Continuously capture webcam frames, run on-device pose estimation, compute a posture score and heuristics, notify the user on slouch events, and persist local analytics and XP for progress over time.
What it still won’t have
- The vendor's polished UI/UX and installers
- Hosted leaderboard and matchmaking for global leaderboards (social features)
- Any proprietary, pre-trained model weights or labeled datasets the vendor may use
- A ready-made one-click paid installer and refund handling
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
SuperShrimp 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 cross-platform Electron (or Tauri) desktop app using Node.js + React for UI and TensorFlow.js or MediaPipe for on-device pose estimation. In scope: (1) webcam capture and permission flow, (2) integrate an on-device pose model and compute a 0–100 posture score with configurable heuristics, (3) background process that monitors posture and sends native desktop notifications when score falls below thresholds, (4) local database (SQLite) recording per-minute samples and generating daily/weekly analytics and XP accumulation, (5) simple local leaderboard view and user settings, (6) cross-platform packaging and auto-update mechanism, (7) error handling for camera failures, permissions, and missing GPU support, and unit/integration tests for model inference, scoring, notifications, and storage. Out of scope: hosted leaderboards, server-side analytics, payment gateway integration beyond a single-device license file. Require automated tests, CI build for installers, and clear runtime privacy behavior (no images saved, model runs locally).
How we checked
How the score was reached
- Partly verdict base52
- 3 cited sources+3
- Price verified on pricing page+3
- Evidence score58
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 productSuperShrimp — Fix your posture
- official pricingSuperShrimp — Pricing
- official productSuperShrimp — Privacy/local processing claim
Integrity checks
What held up, and what did not.
