Quickstart

Install, register a backend, initialize, generate. The same four steps everywhere.

Swift
Kotlin
React Native
Flutter
Web

1. Install

Add the package in Xcode via File → Add Package Dependencies… with the URL https://github.com/RunanywhereAI/runanywhere-swift, or declare it:

Package.swift

dependencies: [
    .package(url: "https://github.com/RunanywhereAI/runanywhere-swift", from: "0.20.24")
],
targets: [
    .target(
        name: "YourApp",
        dependencies: [
            .product(name: "RunAnywhere", package: "runanywhere-swift"),
            .product(name: "RunAnywhereLlamaCPP", package: "runanywhere-swift"),
        ]
    )
]

Requires iOS 17.5+ or macOS 14.5+.

2. Register a backend, then initialize

Register backends before initialize(). The C++ plugin registry has to know which engines exist before the first model load, otherwise loading fails with “No provider could handle the request”.

import RunAnywhere
import RunAnywhereLlamaCPP

LlamaCPP.register()
try RunAnywhere.initialize(apiKey: "", baseUrl: "", environment: .development)

3. Generate

let result = try await RunAnywhere.llm.generate(
    prompt: "Explain on-device AI in one sentence",
    options: LlmOptions(model: "qwen3-0.6b", maxOutputTokens: 100)
)

print(result.text)

4. Stream

for try await event in try await RunAnywhere.llm.generateStream(prompt: "Write a haiku") {
    if case .token(let token) = event { print(token.text, terminator: "") }
}

Full Swift guide →

1. Install

build.gradle.kts (Module: app)

dependencies {
    implementation("io.github.sanchitmonga22:runanywhere-sdk:0.20.24")
    implementation("io.github.sanchitmonga22:runanywhere-llamacpp:0.20.24")
    implementation("io.github.sanchitmonga22:runanywhere-onnx:0.20.24")
    // QHexRT stops at 0.20.19; it is not published past that
    implementation("io.github.sanchitmonga22:runanywhere-qhexrt-android:0.20.19")
}

Requires API 24+, JDK 17.

2. Import both packages

import com.runanywhere.sdk.public.RunAnywhere
import com.runanywhere.sdk.public.api.*

The namespaces are extension properties. Without the second import, RunAnywhere.llm does not resolve.

3. Initialize

class App : Application() {
    override fun onCreate() {
        super.onCreate()
        RunAnywhere.initialize(apiKey = "", baseUrl = "")
    }
}

4. Generate

val result = RunAnywhere.llm.generate(
    "Explain on-device AI in one sentence",
    LlmOptions(model = "qwen3-0.6b", maxOutputTokens = 100)
)

println(result.text)

Streaming:

RunAnywhere.llm.generateStream("Write a haiku").collect { event ->
    if (event is GenerationEvent.Token) print(event.text)
}

Full Kotlin guide →

1. Install

npm install @runanywhere/core @runanywhere/llamacpp @runanywhere/onnx
cd ios && pod install

Requires React Native 0.83.1, iOS 17.5, Android API 24.

2. Register a backend, then initialize

import { RunAnywhere } from '@runanywhere/core';
import { LlamaCPP } from '@runanywhere/llamacpp';

await LlamaCPP.register();
await RunAnywhere.initialize({});

3. Generate

const result = await RunAnywhere.llm.generate('Explain on-device AI in one sentence', {
  model: 'qwen3-0.6b',
  maxOutputTokens: 100,
});

console.log(result.text);

4. Stream

for await (const event of RunAnywhere.llm.generateStream('Write a haiku')) {
  if (event.type === 'textDelta') setText((t) => t + event.text);
}

Note that input constructors are plural here: AudioInputs, ImageInputs.Full React Native guide →

1. Install

pubspec.yaml

dependencies:
  runanywhere: ^0.20.24
  runanywhere_llamacpp: ^0.20.24
  runanywhere_onnx: ^0.20.24
  # QHexRT publishes at 0.20.19
  runanywhere_qhexrt: ^0.20.19

Requires Dart >=3.12.0, iOS 17.5, Android API 24.

2. Register a backend, then initialize

import 'package:runanywhere/runanywhere.dart';
import 'package:runanywhere_llamacpp/runanywhere_llamacpp.dart';

await LlamaCpp.register();
await RunAnywhere.initialize(apiKey: '', baseUrl: '');

3. Generate

final result = await RunAnywhere.llm.generate(
  'Explain on-device AI in one sentence',
  options: LlmOptions(model: 'qwen3-0.6b', maxOutputTokens: 100),
);

print(result.text);

4. Stream

await for (final event in RunAnywhere.llm.generateStream('Write a haiku')) {
  if (event is GenerationEventToken) setState(() => _text += event.text);
}

For a conversation, call generateChat, not generate. Dart has no overloading.Full Flutter guide →

1. Install

npm install @runanywhere/web @runanywhere/web-llamacpp @runanywhere/web-onnx @runanywhere/proto-ts

2. Serve the isolation headers

Cross-Origin-Opener-Policy: same-origin
Cross-Origin-Embedder-Policy: require-corp

Without these there is no SharedArrayBuffer and nothing loads.

3. Register a backend, then initialize

import { RunAnywhere } from '@runanywhere/web';
import { LlamaCPP } from '@runanywhere/web-llamacpp';

await LlamaCPP.autoRegister();
await RunAnywhere.initialize({ environment: 'development' });

4. Generate

const result = await RunAnywhere.llm.generate('Explain on-device AI in one sentence', {
  model: 'qwen3-0.6b',
  maxOutputTokens: 100,
});

console.log(result.text);

Streaming:

for await (const event of RunAnywhere.llm.generateStream('Write a haiku')) {
  if (event.type === 'textDelta') output.textContent += event.text;
}

Full Web guide →

What happens on the first call

Generation auto-loads whatever it needs. When options.model names a model that is not on disk, the SDK downloads it first, so the first call is slow and later calls are not. To control when that cost is paid, download and load explicitly:

for try await event in try await RunAnywhere.models.download(id: "qwen3-0.6b") {
    if case .progress(let p) = event { progress = p.fraction ?? 0 }
}

SDK overview

What differs between platforms

Tool calling

Let the model call your functions

Getting Started

Swift SDK

Kotlin SDK

React Native SDK

Flutter SDK

Web SDK

Electron SDK

Vibe Coding

1. Install

2. Register a backend, then initialize

3. Generate

4. Stream

1. Install

2. Import both packages

3. Initialize

4. Generate

1. Install

2. Register a backend, then initialize

3. Generate

4. Stream

1. Install

2. Register a backend, then initialize

3. Generate

4. Stream

1. Install

2. Serve the isolation headers

3. Register a backend, then initialize

4. Generate

What happens on the first call

Next

SDK overview

Tool calling

​1. Install

​2. Register a backend, then initialize

​3. Generate

​4. Stream

​1. Install

​2. Import both packages

​3. Initialize

​4. Generate

​1. Install

​2. Register a backend, then initialize

​3. Generate

​4. Stream

​1. Install

​2. Register a backend, then initialize

​3. Generate

​4. Stream

​1. Install

​2. Serve the isolation headers

​3. Register a backend, then initialize

​4. Generate

​What happens on the first call

​Next

SDK overview

Tool calling

1. Install

2. Register a backend, then initialize

3. Generate

4. Stream

1. Install

2. Import both packages

3. Initialize

4. Generate

1. Install

2. Register a backend, then initialize

3. Generate

4. Stream

1. Install

2. Register a backend, then initialize

3. Generate

4. Stream

1. Install

2. Serve the isolation headers

3. Register a backend, then initialize

4. Generate

What happens on the first call

Next