Back to feed
Dev.to
Dev.to
6/28/2026
How I built a browser-only face-rating app with Next.js + MediaPipe (no upload, $0 per scan)

How I built a browser-only face-rating app with Next.js + MediaPipe (no upload, $0 per scan)

Short summary

Built PSLRate, a browser-only face-rating app using Next.js and MediaPipe that computes facial geometry scores entirely client-side for $0 cost per scan. Free tier uses deterministic landmark-based math (symmetry, thirds, fifths, canthal tilt, facial width-to-height ratio) with no uploads. Paid tier sends photo to vision LLM for personality readings; pushing deterministic, cheap compute to the client eliminates server costs and privacy concerns.

  • •Built production face-rating app using MediaPipe's client-side FaceLandmarker (478 3D landmarks per face)
  • •Free tier: deterministic geometry scoring entirely in browser, $0 per scan, no uploads
  • •Paid tier: optional LLM personality reading; only path where image leaves device

Generated with AI, which can make mistakes.

#ai-tools#open-source#product-launch
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The original title is: "We built a free AI face shape detector with Claude Vision and Vercel"
Dev.to
The original headline is "I Built an AI Face-Analysis Suite From Scratch — Here's What I Learned"
Dev.to
The original title is a "how I built" style article. Let me rewrite it as a news headline for a mobile feed.
Dev.to
How I Built a Free Image Toolkit : freeimgkit (Next.js + WebAssembly)
Dev.to