Show HN: Local embedding and ranking for tech feeds

Category: other

Tags: local-first, recommendation-system, embeddings, rss-reader, privacy

Score: 6.0/10 (Innovation: 6, Technical: 6, Documentation: 7, Utility: 5)

Okaeri is a local-first personal homepage that aggregates tech and science feeds and ranks stories using a private, on-device embedding model. It learns from your clicks and hides to build a personalized recommendation feed without sending data off your machine, with a configurable ranking algorithm and curated source catalog.

Target audience: developers, researchers, tech enthusiasts

Repository: https://github.com/DBvdHeijden/okaeri · Python · AGPL-3.0 · 5 stars

View on Hacker News