runanywhere-sdks

<p align="center">
  <img src="docs/logo.svg" alt="RunAnywhere Logo" width="130"/>
</p>

<h1 align="center">RunAnywhere</h1>

<p align="center">
  <strong>One SDK. Every device.</strong><br/>
  LLMs, vision, speech, voice agents, RAG, embeddings, and image generation, running locally on
  phones, browsers, desktops, and servers.<br/>
  Private by default. Offline by design. Accelerated by whatever silicon the device has.
</p>

<p align="center">
  <a href="https://apps.apple.com/us/app/runanywhere/id6756506307"><img src="https://img.shields.io/badge/App_Store-Download-0D96F6?style=for-the-badge&logo=apple&logoColor=white" alt="Download on App Store" /></a>&nbsp;&nbsp;<a href="https://play.google.com/store/apps/details?id=com.runanywhere.runanywhereai"><img src="https://img.shields.io/badge/Google_Play-Download-34A853?style=for-the-badge&logo=google-play&logoColor=white" alt="Get it on Google Play" /></a>
</p>

<p align="center">
  <a href="https://github.com/RunanywhereAI/runanywhere-sdks/stargazers"><img src="https://img.shields.io/github/stars/RunanywhereAI/runanywhere-sdks?style=flat-square" alt="GitHub Stars" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-RunAnywhere-blue?style=flat-square" alt="RunAnywhere License" /></a> <a href="https://docs.runanywhere.ai"><img src="https://img.shields.io/badge/Docs-docs.runanywhere.ai-000000?style=flat-square" alt="Documentation" /></a> <a href="https://huggingface.co/runanywhere/models"><img src="https://img.shields.io/badge/Models-Hugging%20Face-FFD21E?style=flat-square" alt="Hugging Face Models" /></a> <a href="https://discord.gg/N359FBbDVd"><img src="https://img.shields.io/badge/Discord-Join-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" /></a>
</p>

<br/>

<p align="center">
  <img src="docs/img/architecture.png" alt="RunAnywhere architecture: eight SDKs over one C++ core, a capability registry that routes to QHexRT, MLX, llama.cpp, sherpa + ONNX, Core ML, or Cloud, landing on the Hexagon NPU, Apple Neural Engine, Metal, CUDA, WebGPU, or CPU. The RunAnywhere Console deploys models and collects telemetry." width="100%"/>
</p>

<p align="center">
  <sub>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.</sub>
</p>

---

## What you can build

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 call