neuryn
v1.2.0
Published
Local AI runtime and developer platform
Maintainers
Readme
Neuryn
Neuryn is a local AI runtime and model management CLI built around llama.cpp.
Features
- Browse available GGUF models.
- Download and verify models.
- Automatically install the Windows CPU runtime.
- Start, stop, and monitor a local AI server.
- Configure the default model and server port.
Requirements
- Node.js
- curl
- Internet connection for initial downloads
Installation
npm install -g neuryn
Usage
neuryn --help neuryn available neuryn install neuryn models neuryn start neuryn status neuryn stop
Configuration
neuryn config neuryn config set server.port 8080
Current limitations
The automatic runtime installer currently targets Windows x64 CPU. GPU selection and broader cross-platform support are planned.
License
ISC
