Work

AI we have built into real products with partner teams. Our own projects live in the lab.

PixaLabs
PixaFind
Offline AI search that finds documents by meaning and photos by description. We worked on the search pipeline, GPU inference and architecture with the PixaLabs team.
Search pipeline, GPU inference, Architecture
Read the case study

In the lab

What we are building in the open.

Released: v0.2.2
tunekeep
Keep a fine-tuned model working when its provider retires the base model: record it, test a replacement, retrain on open weights if needed.
Released: v0.2.0
Crosscheck
A second opinion for AI photo descriptions: several local vision models describe a photo, and you hear where they agree and where they disagree.
Released: v0.1.0
rerankd
Rerank for Ollama: adds the rerank endpoints apps expect, using the reranker models you already pulled, and passes everything else through.
Released: v0.1.0
Rush Index
One local search over your documents and photos: type what you are looking for and get matching files and pictures together, on any laptop or an NVIDIA GPU.
Research: v0 baseline
Rush Small
A small, cleanly licensed reranker you can reproduce with one command: a 0.6B model taught by a 4B one, on permissively licensed data only.