Ship Onde into Flutter apps.

The onde_inference plugin brings the full Onde engine to Flutter. One API, one pub.dev dependency, on-device inference across iOS, macOS, and visionOS.

GitHubRequest Access
pub.dev

Published at pub.dev/packages/onde_inference. Add with flutter pub add or pin the version in pubspec.yaml directly.

FFI bridge

The Dart layer calls into the compiled Rust library via dart:ffi. No server, no network — pure on-device inference.

Flutter-first

Designed for Flutter apps. OndeChatEngine matches the Swift SDK API. Load, prompt, stream — ship in an afternoon.

Current scope

Chat-focused: OndeChatEngine, model loading, history management, and streaming callbacks. More APIs ship with the engine.

pub.devcrates.ioRust SDK
ondeinference on GitHub

Quick Start

Install.

Add the package via the Flutter CLI or pin the version in pubspec.yaml. If you want to verify model downloads or GGUF output before you wire up the Flutter UI, use Onde CLI. If you want the product-level overview first, read What Onde Is.

# via CLI
flutter pub add onde_inference

# or in pubspec.yaml
dependencies:
  onde_inference: ^0.1.0

Coverage

Platform Matrix.

iOS and macOS. For the privacy argument behind local inference, read Privacy as a Feature, Not a Compliance Check.

PlatformABI / sliceStatus
iOSarm64 device, arm64 simulatorReady
macOSarm64Ready