Image and video decision
FaceKit
A competent developer can build a useful self-hosted FaceKit-lite (scanning, metrics, progress tracking) in a few weeks, but reproducing FaceKit's polished mobile UX, device-specific TrueDepth reliability, user base, and community features is expensive and time-consuming.
Visit website↗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 FaceKit alternatives, with the arithmetic →
What a replacement has to do
- 1) Capture TrueDepth-style 3D face scan on iOS and stream landmarks; 2) Compute face metrics (symmetry, jawline, posture) from landmarks; 3) Store scans and progress in a backend (Postgres) and expose a JSON API; 4) Mobile UI to show live feedback, guided routines, and a shareable FaceCard export (image/PDF); 5) Simple global leaderboard and comparison endpoint.
What it still won’t have
- Polished consumer UX, onboarding, and cross-platform app polish
- Proprietary product analytics and training datasets claimed by FaceKit
- Apple App Store presence and handling of device-specific edge-cases
- Community features and moderation for Face Battles and rankings
What remains hard
- Brand trust
Trusted by 120k+ users
First-year cost
No published price
FaceKit 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 an iOS-focused FaceKit-lite using React Native (or SwiftUI) for the client, Node.js + Express backend, and PostgreSQL. Use an on-device face-tracking library (ARKit TrueDepth on iOS or vladmandic/human via WebView as fallback) to capture landmarks; implement metric computations (symmetry, jawline, posture) as reusable functions; expose authenticated REST endpoints for saving scans, retrieving progress, and leaderboards; implement mobile screens for live feedback, guided daily routines, and a shareable FaceCard image/PDF export. Out of scope: training large proprietary ML models, cross-platform Android TrueDepth parity, and community moderation. Include error handling, input validation, unit tests for metric calculations, and end-to-end tests for API flows.
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 productFaceKit official site
- official productFaceKit official site
- open sourceOpenSeeFace
- open sourceDeep-Live-Cam
Integrity checks
What held up, and what did not.
