local-ai

runanywhere-sdks: Deploy AI on Any Device with 10k+ GitHub Stars

Name: runanywhere-sdks: Deploy AI on Any Device with 10k+ GitHub Stars
Author: RunanywhereAI

Runanywhere-sdks lets founders ship on‑device AI—mobile, edge, or web—using C++ bindings for Android, iOS, Flutter, React‑Native, and more. Ideal for startups needing fast, offline inference across platforms.

From the repo · “Production ready toolkit to run AI locally”

10,332 stars+11★ this week395 forksC++Guide quality 9/10 · reviewed Oct 18Updated 10/21/2026100% free · open source

What it does

Runanywhere-sdks allows you to run AI models directly on your device, eliminating the need for cloud services and enhancing data privacy and security

When to use it

•When developing applications that require edge AI capabilities
•When needing to run AI models on devices with limited or no internet connectivity
•When prioritizing data privacy and security by keeping AI processing on-device

Ready-to-paste prompt

Run a pre-trained object detection model on a local image file: ./runanywhere-sdks/example -m examples/models/object_detection -i path/to/image.jpg

Heads up: Ensure your development environment meets the minimum C++ compiler version requirement (C++14 or higher) to successfully build and run the Runanywhere-sdks toolkit

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/runanywhere-sdks && curl -fsSL https://workflowstacks.com/api/skills/runanywhere-sdks/claude-skill -o ~/.claude/skills/runanywhere-sdks/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How runanywhere-sdks: Deploy AI on Any Device with 10k+ GitHub Stars works

Codeflow

Free to inspect

Runanywhere-sdks: Deploy AI on Any Device with 10k+ GitHub Stars is a very large C++ project (~506k lines across 2047 code files, plus 371 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size

Very large codebase

~506k lines · 2047 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js

No API keys detected

C++ 37%TypeScript 19%Dart 8%Swift 8%Kotlin 7%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
package.json
Dependencies and the commands it exposes
4
core/README.md
Inside core/ — the main logic begins here

What's in each folder

core/Core code — the actual logic595 files

bindings/web/Frontend / UI286 files

docs/Documentation13 files

bindings/react-native/Folder604 files

bindings/flutter/Folder377 files

bindings/swift/Folder358 files

bindings/kotlin/Folder270 files

bindings/electron/Folder167 files

READMEHas testsDocumentedCI checksOther licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/runanywhere-sdks && curl -fsSL https://workflowstacks.com/api/skills/runanywhere-sdks/claude-skill -o ~/.claude/skills/runanywhere-sdks/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

RunanywhereAI

Language

C++