Kithra
People like you liked these.
What it is
Kithra is a recommendation engine built on item-item collaborative filtering, the approach Amazon scaled to production. The signature technique computes cosine or Pearson similarity over a ratings matrix and then makes a k-nearest, similarity-weighted prediction - no training, just similarity and a weighted mean - tested with the full "fan of Inception leads to Interstellar" scenario and an honest cold-start case. It is a from-scratch, dependency-light build you can download and run locally.
Item-item CF, the approach Amazon scaled: cosine/Pearson similarity over a ratings matrix, then a k-nearest similarity-weighted prediction. No training - just similarity and a weighted mean. 13 tests, including the full “fan of Inception → Interstellar” scenario and an honest cold-start.
What's inside
The full source, the tests, and CI. Open it, read it, change it. A zero-dependency core, free, in the MIT spirit.
Run it after unzip
pnpm install && pnpm dev