appleroll/kernelgpt

Ring-0 GPT inside MooseOS.

33
/ 100
Emerging

This project is a bare-metal implementation of a Generative Pre-trained Transformer (GPT) designed for deeply embedded systems and specialized hardware environments. It allows developers to explore the fundamental mechanics of neural network training without relying on standard operating systems or high-level libraries. You input raw training data in a simplified format, and it outputs a trained GPT-style neural network directly within a minimal kernel environment. It's built for systems programmers, kernel developers, and researchers focusing on the low-level aspects of AI.

Use this if you are a systems programmer or researcher interested in understanding or building AI models from the ground up, on bare-metal hardware, without the overhead of an operating system or extensive libraries.

Not ideal if you are an AI practitioner who wants to train large-scale models, use existing deep learning frameworks, or deploy models on standard computing infrastructure.

embedded-systems kernel-development low-level-ai systems-programming neural-network-research
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

C

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/appleroll/kernelgpt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.