RunanywhereAI/runanywhere-sdks

One SDK. Every device.
LLMs, vision, speech, voice agents, RAG, embeddings, and image generation, running locally on phones, browsers, desktops, and servers.
Private by default. Offline by design. Accelerated by whatever silicon the device has.

_{Eight SDKs, one C++ core. A capability registry routes every call to the best engine on the device, and the Console manages your fleet from above.}

Every capability below runs fully on-device behind one semantic API across the eight SDKs. Call RunAnywhere.capabilities() (v4) to discover what the current package and device can actually execute — enum presence alone does not mean an engine is installed.

• LLM chat: Llama, Qwen, Gemma, Phi, LFM, SmolLM, DeepSeek, and more, with token streaming, multi-turn history, and LoRA adapters
• Structured output: schema-validated JSON; constrained decoding where the engine supports it (generateStructured + enforcement mode)
• Tool calling: local function tools with stable call IDs and an agent loop (parallel calls when the engine/capability reports support)
• Vision (VLM): image understanding, live camera description, and photo Q&A
• Computer-use action parser (CUA): parse Fara1.5-style action strings into viewport-scaled coordinates — not a full autonomous agent framework
• Speech-to-Text: Whisper and Moonshine transcription, batch and live frame streams
• Text-to-Speech: neural voices from Piper, Kokoro, Kitten, MeloTTS, and Magpie
• Voice agents: VAD, STT, LLM, and TTS in one pipeline with SpeechHandle-scoped playback (wake-word detection is not implemented)
• Embeddings: L2-normalized vectors for search and retrieval
• RAG: local document ingestion and retrieval-augmented answers, with streaming
• Image generation: Stable Diffusion on Core ML, plus inpainting on the Hexagon NPU (platform/backend gated)

Your code rarely picks hardware. Engines register what they can run, and the highest-priority engine that fits the device wins: QHexRT on the Snapdragon Hexagon NPU, MLX on Apple silicon, llama.cpp everywhere (Metal on Apple, CUDA on NVIDIA as an opt-in build, WebGPU in the browser), sherpa + ONNX for speech and embeddings, and Core ML for diffusion. LiteRT and ExecuTorch are reserved framework values only — they are not integrated runtimes yet.

Text Generation LLM inference, 100% on-device		Voice AI STT → LLM → TTS pipeline, fully offline
Image Generation On-device diffusion model		Visual Language Model Vision + language understanding on-device

The fastest way to feel it. Install, load, generate, all local:

pip install runanywhere

import runanywhere as ra
from runanywhere import LlmOptions

ra.initialize()
# downloads on first use
print(ra.llm.generate("Explain on-device AI in one sentence.",
                      LlmOptions(model="qwen2.5-0.5b")).text)

Prefer a terminal? Install the CLI from RunanywhereAI/wally — it consumes the C++ desktop kit this repo publishes:

curl -fsSL https://raw.githubusercontent.com/RunanywhereAI/wally/main/install.sh | sh
wally run qwen3 "Explain on-device AI in one sentence."

Building for mobile, web, or desktop? Every platform below speaks the same API.

import RunAnywhere
import LlamaCPPRuntime

// 1. Initialize
LlamaCPP.register()
try RunAnywhere.initialize()

// 2. Load a model
var load = RAModelLoadRequest()
load.modelID = "smollm2-360m"
load.category = .language
load.framework = .llamaCpp
_ = await RunAnywhere.loadModel(load)

// 3. Generate
var req = RALLMGenerateRequest()
req.prompt = "What is the capital of France?"
let result = try await RunAnywhere.generate(req)
print(result.text) // "Paris is the capital of France."

https://github.com/RunanywhereAI/runanywhere-sdks

import ai.runanywhere.proto.v1.ModelCategory
import ai.runanywhere.proto.v1.SDKEnvironment
import com.runanywhere.sdk.llm.llamacpp.LlamaCPP
import com.runanywhere.sdk.public.RunAnywhere
import com.runanywhere.sdk.public.extensions.*
import com.runanywhere.sdk.public.types.RAModelInfo
import com.runanywhere.sdk.public.types.RAModelLoadRequest

// 1. Initialize (in a coroutine scope)
LlamaCPP.register()
RunAnywhere.initialize(
    context = this,
    environment = SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT,
)

// 2. Download and load a model
val modelId = "smollm2-360m-instruct-q8_0"
RunAnywhere.downloadModelStream(RAModelInfo(id = modelId)).collect { /* progress */ }
RunAnywhere.loadModel(
    RAModelLoadRequest(model_id = modelId, category = ModelCategory.MODEL_CATEGORY_LANGUAGE),
)

// 3. Generate
val result = RunAnywhere.generate("What is the capital of France?")
println(result.text) // "Paris is the capital of France."

dependencies {
    implementation("io.github.sanchitmonga22:runanywhere-sdk:0.20.11")
    implementation("io.github.sanchitmonga22:runanywhere-llamacpp:0.20.11")
    // Optional: STT / TTS / VAD
    // implementation("io.github.sanchitmonga22:runanywhere-onnx:0.20.11")
}

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

// 1. Initialize
LlamaCpp.register();
await RunAnywhere.initialize();

// 2. Download and load a model
await RunAnywhere.downloadModel('smollm2-360m');
await RunAnywhere.llm.load('smollm2-360m');

// 3. Generate
final response = await RunAnywhere.llm.chat('What is the capital of France?');
print(response); // "Paris is the capital of France."

dependencies:
  runanywhere: ^0.20.11
  runanywhere_llamacpp: ^0.20.11  # LLM/VLM text generation
  # runanywhere_onnx: ^0.20.11    # STT, TTS, VAD, voice agent
  # runanywhere_mlx: ^0.20.11     # Apple-native LLM/VLM/STT/TTS/embeddings
  # runanywhere_qhexrt: ^0.20.11  # Snapdragon Hexagon NPU

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

// 1. Initialize
await RunAnywhere.initialize({ environment: SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT });
LlamaCPP.register();

// 2. Download and load a model
await RunAnywhere.downloadModel('smollm2-360m');
await RunAnywhere.loadModel('smollm2-360m');

// 3. Generate
const result = await RunAnywhere.generate('What is the capital of France?');
console.log(result.text); // "Paris is the capital of France."

npm install @runanywhere/core@0.20.11 @runanywhere/llamacpp@0.20.11
# optional backends: @runanywhere/onnx @runanywhere/mlx @runanywhere/qhexrt

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

// 1. Initialize
await RunAnywhere.initialize({ environment: SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT });
await LlamaCPP.register({ acceleration: 'auto' }); // WebGPU when available, WASM otherwise
await RunAnywhere.completeServicesInitialization();

// 2. Load a model
await RunAnywhere.loadModel({ modelId: 'qwen2.5-0.5b' });

// 3. Generate
const result = await RunAnywhere.generate({
  prompt: 'What is the capital of France?',
});
console.log(result.text); // "Paris is the capital of France."

npm install @runanywhere/web@0.20.11 @runanywhere/web-llamacpp@0.20.11
# @runanywhere/web-onnx for STT/TTS/VAD/embeddings in the browser

const { RunAnywhere } = require('@runanywhere/electron');

// 1. Initialize
RunAnywhere.initialize();

// 2. Load a model (catalog id or a local path)
const llm = await RunAnywhere.loadLLM('qwen2.5-0.5b');

// 3. Generate (streaming)
for await (const token of llm.generate('What is the capital of France?')) {
  process.stdout.write(token);
}

llm.unload();
RunAnywhere.shutdown();

import runanywhere as ra
from runanywhere import LlmOptions

# 1. One call brings the SDK up
ra.initialize()

# 2. Stream tokens (the model auto-downloads and auto-loads)
for event in ra.llm.generate_stream("What is the capital of France?",
                                    LlmOptions(model="qwen2.5-0.5b")):
    if event.is_token:
        print(event.text, end="", flush=True)

# 2b. Or async
# async for event in ra.llm.agenerate_stream("..."):
#     ...

# 3. Or grab the whole result, metrics included
result = ra.llm.generate("Capital of France? One word.")
print(result.text, result.tokens_per_second)   # "Paris" 41.2

pip install runanywhere==0.20.11

$ wally models pull qwen3
pulling qwen3-0.6b ▕████████████▏ 100%  639 MB/639 MB  32 MB/s
$ wally run qwen3 "Reply with exactly: RCLI WORKS" --no-think
RCLI WORKS
$ wally serve qwen3        # OpenAI-compatible API on :8080

curl -fsSL https://raw.githubusercontent.com/RunanywhereAI/wally/main/install.sh | sh

irm https://raw.githubusercontent.com/RunanywhereAI/wally/main/install.ps1 | iex

All SDKs ship on one version line, currently 0.20.29, from a single C++ core. Pin the same version across the core package and its backends. See Releases for what is published today.

* Web RAG may be limited to one session per process — check capabilities().rag.multiSession. Stub / Gated / Partial mean the verb is absent, preflight-fails, or only partially wired; call capabilities() for the installed build. | Hexagon NPU (QHexRT) | n/a | Yes | Yes | Yes | n/a | n/a | n/a | n/a | | MLX (Apple silicon) | Yes | n/a | Yes | Yes | n/a | n/a | n/a | Yes | | OpenAI-compatible server | n/a | n/a | n/a | n/a | n/a | n/a | Yes | Yes | | Model download + progress | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | | Connect (LAN host/client) | Host (macOS) / Client (iOS, iPadOS) | Client | — | — | — | — | — | — |

Connect lets a macOS Swift app host a loaded language model on the local network so iOS, iPadOS, and Android clients can discover it and stream generation without downloading that model. It is app-scoped (lives with the host app process), not an OS daemon.

• Discovery: Bonjour / NSD service type _runanywhere-connect._tcp
• Transport: framed TCP on the LAN; commons owns protocol version, role policy, session accounting, and generation validation (idl/connect.proto, rac_connect_*)
• Lifecycle: the host app selects and loads the model, starts hosting, and supplies generation; stopping the host disconnects clients
• Threat model: trusted LAN only — no TLS, pairing PIN, or mutual auth in this release. Do not expose Connect across untrusted networks. Future work may add TLS/pairing, Windows hosting, or a daemon; those change lifecycle and security and are out of scope here
• Electron note: RunAnywhereMain.connect() is local MessagePort / utility-process IPC inside one Electron app. It is unrelated to LAN Connect

CUA on Web is "API only": the prompt/parse scaffold ships, but the catalogued Fara1.5-4B does not fit the 4 GB WASM32 heap, so no CUA model is seeded there.

Every SDK is a thin binding over runanywhere-commons, a single C++ core behind a pure C ABI. Engines plug into a capability registry and declare, per modality, what they can run. At inference time the highest-priority engine that serves the modality on the current device wins. Same code, different silicon, no branching in your app.

MetalRT, RunAnywhere's proprietary GPU inference engine for Apple silicon, powers RCLI, our on-device voice assistant for macOS with local RAG and 40+ system actions at sub-200 ms latency. Signed binaries live at metalrt-binaries.

QHexRT is RunAnywhere's inference runtime for the Qualcomm Hexagon NPU. It runs LLM, vision, speech, and text-to-speech models directly on the Snapdragon NPU (Hexagon v75 / v79 / v81) and ships as a built-in accelerator: your app calls the same loadModel and generate, and it uses the NPU automatically on supported devices.

• Runs LLM, VLM, speech-to-text, and text-to-speech on the NPU, including text-to-speech, which other runtimes run on the CPU.
• Runs Mixture-of-Experts and hybrid-attention models on the NPU (Phi-tiny-MoE, Qwen3.5), plus the 1-bit Bonsai family up to Bonsai-27B (Hexagon v81).
• Runs NVIDIA's Cosmos3-Edge and Magpie-TTS Multilingual, and handles embeddings and image inpainting (LaMa) on the NPU as well.
• Hybrid streaming voice agents: LLM on the NPU, STT and TTS on the CPU, with sentence-by-sentence streaming playback.
• Fast prefill and low time-to-first-token, with context that extends past the compiled window.
• Prebuilt model bundles published on Hugging Face; the SDK downloads the one matching the device.

Measured on a Samsung Galaxy S25 (Snapdragon 8 Elite, Hexagon v79):

Available on the Kotlin, Flutter, and React Native SDKs. Snapdragon (Android arm64) only.

The Python SDK and wally both expose the local runtime as a drop-in OpenAI API, so anything that speaks the OpenAI client works against models running on your machine:

pip install "runanywhere[server]"
runanywhere serve        # http://127.0.0.1:8000

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")
reply = client.chat.completions.create(
    model="qwen2.5-0.5b",
    messages=[{"role": "user", "content": "Hello from the edge."}],
)

Endpoints: /v1/chat/completions (streaming and non-streaming, text and vision), /v1/completions, /v1/embeddings, /v1/audio/transcriptions, /v1/audio/speech, and /v1/models. wally serve is LLM-only: it serves one model on port 8080 with /v1/chat/completions and /v1/models.

The Console is the control plane for on-device AI fleets. SDKs authenticate with an API key, register the device with its hardware profile, pull their assigned models, and report per-modality telemetry.

• Deploy models over the air: assign catalog or bring-your-own models to an API key, and devices fetch them on their next sync. New models without an app release.
• Device fleet: every registered device with its chip, memory, and NPU capability.
• Analytics: usage, latency, and errors per modality across the fleet.
• Benchmarks: compare local models against hosted providers.

The Console is optional. Every SDK runs fully offline without an API key, and telemetry is scoped per modality when enabled.

Prebuilt bundles published on Hugging Face; the SDK downloads the one matching the device.

Browse all models on Hugging Face

Anything not in the catalog can be pulled straight from Hugging Face or a direct URL; the core infers format, framework, and category from the artifact.

Full consumer-assistant apps, one per platform, all built on the SDK. The iOS, Android, Web, and Electron apps live in their own repositories; the Flutter and React Native ones are still in this tree.

The Android, Flutter, and React Native apps include an NPU section that detects the device's Hexagon arch and runs LLM, vision, speech, and text-to-speech on the NPU.

Minimal examples, the in-repo harnesses SDK contributors use to check a change end to end. Each builds the SDK from local source, so an edit shows up without a publish step:

Starters, minimal projects to copy from: Swift · Kotlin · Flutter · React Native · Web

Real projects built on the stack:

• RCLI: on-device voice assistant for macOS with local RAG and 40+ system actions, powered by MetalRT

Business logic lives in the C++ core, so one fix lands on all eight SDKs at once.

runanywhere-sdks/
├── core/                           # Shared C/C++ core behind a C ABI — all business logic
│
├── bindings/                       # Thin language bindings over core/
│   ├── swift/                      # iOS/macOS SDK (XCFramework) + example/
│   ├── kotlin/                     # Android SDK (JNI) + example/
│   ├── flutter/                    # Flutter SDK (Dart FFI) + example/
│   ├── react-native/               # React Native SDK (Nitro/JSI) + example/
│   ├── web/                        # Web SDK (WebAssembly / WebGPU) + example/
│   ├── electron/                   # Electron SDK (N-API addon) + example/
│   ├── python/                     # Python SDK (pybind11) + example/
│   ├── proto-ts/                   # @runanywhere/proto-ts, the IDL's TypeScript binding
│   └── shared-apple/               # Apple transport shared by the RN + Flutter bindings
│                                   # (iOS/Android/Web/Electron consumer apps live in their own repos)
│
├── engines/                        # llamacpp, mlx, sherpa, onnx, neurt, qhexrt, cloud
├── runtimes/                       # cpu, coreml, onnxrt compute adapters
├── idl/                            # Protobuf schemas, generated bindings per language
└── docs/                           # Documentation

Hexagon NPU: Snapdragon with Hexagon v75 / v79 / v81, Android arm64. MLX: Apple silicon, physical devices. Memory: 2 GB minimum, 4 GB+ recommended for larger models.

We welcome contributions. See the Contributing Guide for setup and conventions.

git clone https://github.com/RunanywhereAI/runanywhere-sdks.git
cd runanywhere-sdks

# Doctor / setup helpers
./run doctor
./run setup

# Build the native XCFrameworks into bindings/swift/Binaries/.
# Required for local Swift development.
./bindings/swift/scripts/build-core-xcframework.sh

# Stream one completion through the minimal Swift harness
cd bindings/swift/example
RUNANYWHERE_USE_LOCAL_NATIVES=1 swift run

• Docs: docs.runanywhere.ai
• Discord: Join the community
• Issues: GitHub Issues
• Email: founders@runanywhere.ai
• X: @RunanywhereAI

RunAnywhere License (Apache 2.0 based, with additional commercial-use terms). See LICENSE for details.