The first app that actually reads
your knitting pattern

What the other apps don't do

Also works in landscape on any iPhone — even the standard models. Turn your phone sideways and the split view activates automatically.

We're building this for crafters, not shareholders

Every dollar from credit packs goes back into expanding the curated pattern library — more patterns, better extraction quality, and a better app for you. We want to build the best crafting companion we can afford.

No venture funding. No ads. No subscription. Just a small team that knits.

Exactly what we send — nothing more

This is the complete payload for a single extraction. What you see below is what we receive. There is no hidden data, no secondary collection, no device fingerprinting.

{
  "timestamp": "2026-04-08T22:30:00Z",
  "score": 94,
  "dimensions": {
    "stitch_math": 23,
    "section_integrity": 15,
    "size_consistency": 12,
    "chart_honesty": 9,
    "instruction_quality": 15,
    "shape_data": 10,
    "metadata": 10
  },
  "craft": "knitting",
  "category": "sweater",
  "pieces": 4,
  "sections": 12,
  "total_rows": 198,
  "parser": {
    "cast_on_found": true,
    "gauge_found": true,
    "multi_size": true,
    "pieces_detected": 4,
    "checkpoints": 27,
    "shaping_blocks": 9,
    "measurements": 6,
    "charts_referenced": 2,
    "atst_detected": true,
    "amigurumi_rounds": 0,
    "trajectory_built": true
  },
  "errors": ["chart_honesty_warning"],
  "prescreen_score": 4.3
}

Notice what's not here: no pattern name, no designer, no PDF content, no row instructions, no stitch counts from your pattern, no user ID, no device ID, no IP address. We can't identify you or your pattern from this data. We can only see: "a sweater with 4 pieces scored 94/100 and the chart dimension was slightly low."

The academic attempts

In 2019, MIT's CSAIL published "Neural Inverse Knitting" — a system that could look at a photograph of knitted fabric and reverse-engineer the machine knitting instructions. Impressive, but it solved image-to-machine-code, not human-pattern-to-structured-data.

Other efforts formalized knitting as a topological problem — modeling yarn as curves in 3D space, building formal grammars for notation. Beautiful mathematics. None of it helps a knitter follow a DROPS pattern on a Tuesday night.

Why the apps gave up

KnitCompanion, Row Counter, StitchFiddle — every existing app requires manual entry. They're PDF readers with counters bolted on. One startup, Knitrino, attempted interactive patterns in 2020. Their founders said it plainly: "Each pattern has to be manually built by us." The problem beat them.

The seven hard problems

What changed

Large language models. Not as a magic wand — raw AI makes mistakes on stitch math. What works is a hybrid approach: a deterministic parser extracts every verifiable fact from the PDF (cast-on counts, gauge, checkpoints, shaping math), then feeds those as anchors to the most advanced AI models available. The parser keeps the AI honest. The AI handles the ambiguity the parser can't.

We validate every extraction across seven quality dimensions and score it out of 100. Today, 98% of patterns in our library score A or A+. The hardest patterns — DROPS sweaters with 8 charts and simultaneous shaping — went from failing grades to 97/100.

Two modes, one honest approach

Simple Mode — Default

What works today

Your original pattern text, organized by section, with a clean row counter and your PDF always visible beside it. The AI identifies your sections, row counts, gauge, and sizing — you follow your own pattern words. The app just keeps your place.

This is reliable, battle-tested, and works on every pattern we've thrown at it. Most knitters will be completely comfortable here.

Advanced Mode — Available

Where we're headed

Row-by-row extracted instructions with computed stitch counts, shaping events highlighted, and a live garment schematic that tracks your position. Every row validated against the parser's checkpoints.

This works great on many patterns already. Stitch math validation is still being refined for the most complex designs — charts, parallel shaping, unusual notation. It's available now and improving with every pattern we see.

Both modes use the same AI extraction and the same credit. You choose which view fits your workflow — and you can switch between them anytime.

We think we're close. We need your help.

No one has shipped automated pattern extraction at this level before. We're confident in the engine, but every pattern is different — every designer has their own style, notation, and quirks. The more patterns our system sees, the better it gets.

That's where you come in. Import your patterns. Tell us when something doesn't look right. Every piece of feedback makes the extraction better for everyone.

You can also opt in to share anonymous quality metrics — just scores, error types, and pattern categories. No PDFs, no instructions, no personal data. This telemetry is how we see what's working and what's not at scale: which pattern types struggle, which validator dimensions fail most, where the parser needs tuning. It's the difference between guessing and knowing. As a thank you, every credit pack includes a bonus extraction when sharing is on.

You're not just using an app — you're helping solve a problem that researchers and developers have been working on for decades.