Desert Ant Labs

Shapes.

Shape recognitionAvailable

On-device shape recognition that turns one hand-drawn stroke into a rectangle, ellipse, triangle, star or line in under 10ms.

Get started Docs Model card

Demo

Rough sketch. Perfect shape.

Draw a rough circle and Shapes snaps it to a clean one. Shapes fits precise vector geometry, snaps to axes, circles, squares and 15-degree rotations, and rejects scribbles that are not shapes.

On Apple, one call adds Notes-style smart-shape snapping to a PencilKit canvas, and the live preview stays. Apple's own "Snap to Shape" is private API that third-party apps cannot call, so Shapes does the same job in one line.

The model is small enough to ship inside the app, with no download. In the browser, Shapes runs through LiteRT.js.

Under 10ms per stroke.

Under 10ms per stroke, from a 0.2MB model on Apple and 1.3MB on Android and the web.

0.2MB
On-device
<10ms
Per recognition
on device
5
Shape classes
rectangle, ellipse, triangle, star, line
1.3MB
In the browser
fetched once and cached

Internal measurements. Core ML on Apple, LiteRT.js in the browser, prebuilt native libraries on Node.

Notes-style smart shapes

Add snap-to-shape to a PencilKit canvas with canvasView.enableShapeSnapping(). Live preview, undo and redo preserved, filling the gap left by Apple's private Snap to Shape API.

Clean up a freehand diagram

Turn rough strokes into precise geometry in a diagram or whiteboard tool. Works with tldraw and Excalidraw stroke data.

Cross-platform drawing

One recognizer covers iOS, Android, and the web, so you write the snapping code once.

Ships in the app, not as a download

On Apple the recognizer is 0.2MB and ships inside the binary, and the Android package bundles it by default. In the browser the SDK fetches 1.3MB once and caches it.

Inspiration

Ideas to build with Shapes. Copy a prompt into your coding agent and go.

Shapes

Build a whiteboard that snaps rough sketches into clean shapes.

Shapes

Clean up a freehand diagram into crisp shapes.

Shapes

Add shape recognition to a web canvas with no download.

Shapes

Snap flowchart boxes and connector lines as you sketch them.

Shapes

Add smart-shape drawing to a kids' learning app.

Shapes

Recognize gesture shapes to trigger app actions.

What the model does

  • One stroke at a time, passed as its [x, y] points, from PencilKit, tldraw, Excalidraw, or your own canvas.
  • Recognizes rectangle, ellipse, triangle, star, and line, and rejects non-shapes.
  • Snaps to axes, circles, squares, and 15-degree rotations.
  • PencilKit live snapping via one call: canvasView.enableShapeSnapping().
  • Runs through LiteRT.js in the browser. Node uses prebuilt native libraries.

Getting started

Add shape recognition to your iOS or macOS, Android or web app in a few lines of code. Shapes docs.

iOS, macOS
Install
// Swift Package Manager
.package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core", from: "3.1.0")
// target dependency
.product(name: "Shapes", package: "desert-ant-core")
Example - Swift
import Shapes

let shapes = Shapes()
let shape = try await shapes.recognize(points: stroke)
// Shape? -> rectangle, ellipse, triangle, star, line
Example - PencilKit
import PencilKit
import Shapes

// Live smart-shape snapping on a PencilKit canvas, in one line.
// Pause after a stroke to preview the fit, lift to snap. Undo-safe,
// and it uses the same recognizer, bundled by default.
canvasView.enableShapeSnapping()
Build with a prompt
Add Shapes from Desert Ant Labs to this Swift project (iOS, macOS).

What it does: On-device Single-Stroke Shape Recognition.

SDK:

Swift (iOS, macOS)
Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme
// Swift Package Manager
.package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core", from: "3.1.0")
// target dependency
.product(name: "Shapes", package: "desert-ant-core")

Reference:
- Model page: https://desertant.com/models/shapes/
- Full catalog and other models: https://desertant.com/llms.txt

Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
SDK on GitHub
Android
Install
// build.gradle.kts (Maven Central)
implementation("ai.desertant:shapes:3.1.0")
Example - Kotlin
import ai.desertant.shapes.Shapes

val shapes = Shapes(context)
val shape = shapes.recognize(points)
// Shape? -> rectangle, ellipse, triangle, star, line
Build with a prompt
Add Shapes from Desert Ant Labs to this Kotlin project (Android).

What it does: On-device Single-Stroke Shape Recognition.

SDK:

Kotlin (Android)
Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme
// build.gradle.kts (Maven Central)
implementation("ai.desertant:shapes:3.1.0")

Reference:
- Model page: https://desertant.com/models/shapes/
- Full catalog and other models: https://desertant.com/llms.txt

Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
SDK on GitHub
Web, Node.js
Install
npm i @desert-ant-labs/shapes @litertjs/core
Example - TypeScript
import { Shapes } from "@desert-ant-labs/shapes";       // browser
// import { Shapes } from "@desert-ant-labs/shapes/native"; // server-side Node

const shapes = await Shapes.load();
const shape = await shapes.recognize(points);
// { kind: "ellipse", center: {...}, ... } or null
Build with a prompt
Add Shapes from Desert Ant Labs to this JavaScript / TypeScript project (Web, Node.js).

What it does: On-device Single-Stroke Shape Recognition.

SDK:

JavaScript / TypeScript (Web, Node.js)
Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme
npm i @desert-ant-labs/shapes @litertjs/core

Reference:
- Model page: https://desertant.com/models/shapes/
- Full catalog and other models: https://desertant.com/llms.txt

Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
SDK on GitHub

Specs

Shape classes
Rectangle, ellipse, triangle, star, line
On-device size
0.2MB Core ML (Apple); 1.3MB LiteRT (Android, web)
Speed
<10ms
Web runtime
LiteRT.js in the browser, native libraries on Node

Shapes reads one stroke at a time, so a shape drawn in two strokes is not recognized. Very rough or ambiguous strokes are rejected on purpose, so a scribble never snaps to a triangle.

Multi-stroke diagrams need your own grouping step first.

FAQ

What is Shapes?

On-device shape recognition that turns one hand-drawn stroke into a rectangle, ellipse, triangle, star or line in under 10ms.

Does Shapes run on device?

Yes. Shapes runs on the device, with no server call, so the data stays with the user.

Which platforms does Shapes support?

Shapes ships as a native on-device SDK for Swift, Kotlin, JavaScript / TypeScript.

How much does Shapes cost?

Every model is free up to 100k monthly active devices per SDK. Unlimited inference per user. Contact us for custom licenses.

How accurate or fast is Shapes?

Under 10ms per stroke, from a 0.2MB model on Apple and 1.3MB on Android and the web.

Resources