RunanywhereAI/runanywhere-sdks

Production ready toolkit to run AI locally

What it solves

RunAnywhere provides a unified SDK for deploying AI models locally on a wide variety of devices, including phones, browsers, desktops, and servers. It eliminates the need for developers to write platform-specific code for different hardware accelerators (like NPUs, GPUs, or CPUs) by providing a single semantic API across multiple programming languages.

How it works

The project uses a single C++ core (runanywhere-commons) with a pure C ABI, which is then wrapped in eight different SDKs (Swift, Kotlin, Android, Flutter, React Native, Web, Electron, and Python). A capability registry routes AI tasks to the best available engine on the device. For example, it can utilize QHexRT for Snapdragon Hexagon NPUs, MLX for Apple silicon, or llama.cpp for general compatibility across Metal, CUDA, and WebGPU.

Who it’s for

It is designed for developers building cross-platform applications that require private, offline-first AI capabilities such as LLMs, vision, speech, and image generation without wanting to manage the complexities of hardware-specific optimization.

Highlights

  • Multi-modal support: Includes LLM chat, Vision Language Models (VLM), Speech-to-Text (STT), Text-to-Speech (TTS), RAG, and image generation.
  • Broad hardware acceleration: Supports Snapdragon Hexagon NPU, Apple Neural Engine, Metal, CUDA, WebGPU, and CPU.
  • Unified API: One consistent interface across eight different SDKs.
  • On-device privacy: Models run fully locally and offline by design.
  • Advanced AI features: Supports structured JSON output, tool calling, and LoRA adapters.

Related

  • Project
    huggingface/speech-to-speech

    A low-latency, modular voice-agent pipeline that coordinates VAD, STT, LLM, and TTS components to enable real-time voice conversations.

  • Project
    xybrid-ai/xybrid

    Xybrid is an open‑source, cross‑platform SDK that runs LLMs, speech‑to‑text and text‑to‑speech models locally on devices (mobile, desktop, Unity). It provides native bindings for Flutter, Swift, Kotlin, Unity, Rust and Python, supports many popular open‑source models, and lets you chain them together in a multi‑model pipeline—all without requiring cloud services.

  • Dispatch
    AnyLanguageModel: A Unified LLM API for Apple Platforms

    Hugging Face has introduced AnyLanguageModel, a Swift package that provides a unified API for integrating local and remote LLMs on Apple platforms by acting as a drop-in replacement for Apple's Foundation Models framework.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.

  • Project
    MaxBittker/rs-sdk

    RS‑SDK is an open‑source, TypeScript‑based starter kit that emulates a RuneScape‑style MMO for bot research. It bundles a server emulator, a web client, a gateway, and a typed SDK so you can write async scripts (or LLM‑generated code) that control bots, experiment with goal‑directed synthesis, multi‑agent competition, and market economics. The demo server runs out‑of‑the‑box; you can also host it locally with adjustable tickrates. MIT‑licensed and backed by a Discord community.