#3636th of 82 in Agent frameworks and SDKs
runanywhere-sdks
On-device LLM, speech, vision and RAG SDKs for mobile, web and desktop
- Stars
- 10.3k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- C++
9,777 on 10 Apr 202610,334 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Eight SDKs (Swift, Kotlin, Flutter, React Native, Web, Electron, Python, and the wally CLI) over one C++ core. A capability registry picks an engine per device: QHexRT on Snapdragon Hexagon NPU, MLX on Apple silicon, llama.cpp, sherpa + ONNX, or Core ML. It covers LLM chat, VLM, STT, TTS, voice agents, embeddings, RAG and image generation, all run locally.
Who it is for: App developers embedding local AI in mobile, web and desktop apps
Strengths
- One API across Swift, Kotlin, Flutter, React Native, Web, Electron and Python
- Engine routing per device: Hexagon NPU, MLX, llama.cpp (Metal, CUDA opt-in, WebGPU)
- Covers LLM, VLM, STT, TTS, VAD, embeddings, RAG, structured output and tool calling
- wally CLI serves an OpenAI-compatible API on :8080
Weaknesses
- Maturity varies: Flutter, React Native and Web are beta, Electron preview, Python alpha
- Python SDK has stubs for voice agent, image generation and LoRA
- Wake-word detection is not implemented in any SDK
- Custom license (NOASSERTION detected); terms need review before commercial use
What it needs
- GPU optional
- Models: GGUF, safetensors (MLX), ONNX, Core ML
- port 8080
Quick answers
Is runanywhere-sdks open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Does runanywhere-sdks need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Agent frameworks and SDKs
See all 82| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 90 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #5 | tradingagentsMulti-agent LLM framework that simulates a trading firm's analysis process | 89 out of 100 |