RunanywhereAI/runanywhere-sdks
Production ready toolkit to run AI locally
This toolkit enables developers to embed AI capabilities like large language models (LLMs), speech-to-text, and text-to-speech directly into their mobile and web applications. It takes user input (text or voice) and provides generated text, transcribed speech, or synthesized voice responses, all processed on the user's device. This is for app developers who want to integrate AI features that work offline, maintain user privacy, and run quickly without relying on cloud services.
10,245 stars. Actively maintained with 26 commits in the last 30 days.
Use this if you are a mobile or web app developer building applications that need AI features to run directly on the user's device, ensuring privacy and offline functionality.
Not ideal if you need to integrate AI models that require extensive cloud infrastructure or are not suitable for on-device deployment due to their size or computational demands.
Stars
10,245
Forks
308
Language
C++
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
26
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/RunanywhereAI/runanywhere-sdks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related tools
containers/ramalama
RamaLama is an open-source developer tool that simplifies the local serving of AI models from...
av/harbor
One command brings a complete pre-wired LLM stack with hundreds of services to explore.
runpod-workers/worker-vllm
The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
foldl/chatllm.cpp
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)
FarisZahrani/llama-cpp-py-sync
Auto-synced CFFI ABI python bindings for llama.cpp with prebuilt wheels (CPU/CUDA/Vulkan/Metal).