Projects

Open hardware and software infrastructure for AI inference, training, and systems development.

ML Framework

Foundry

Pure C machine learning framework. Zero dependencies, full tensor operations, quantization, and training. Embeddable anywhere.

Learn more → Inference

Inference Engines

Two approaches to running AI locally: a universal model server and a bare-metal boot environment. Both zero-dependency.

Learn more → Hardware + Kernel

Barswap

GPU multiplexer for dense compute systems. Unlock all your GPU hardware on commodity motherboards.

Learn more →