← All research

Open source · Vector compression

Semafold

Report data checked: September 25, 2026

Download PDF ↓

Programme overview

Semafold is Mindtro’s open-source Python library for compressing the numerical representations used by AI systems. It helps teams reduce embedding storage and explore smaller attention-cache tensors, with the saved bytes and reconstruction error visible together.

  • Embedding and vector storage
  • Attention-cache tensor experiments
  • Measured size and quality trade-offs

Experiments by research track

About this report

This technical report is not peer reviewed. Figures were transcribed from the repository’s 0.1.0 benchmark report and were not rerun for this website. Code, examples, benchmark runners and the API stability policy are public under Apache-2.0.

Request the research materials →
← All research
Semafold | Mindtro | Intelligence, Engineered