Shevinu's Digest

Shevinu’s Digest is an automated Python pipeline that distills 500+ daily tech stories into a ranked 9-item read. It uses a four-stage relevance filter (model2vec embeddings, trafilatura extraction) followed by an LLM pass using 3 models.

Built with Python, Groq + OpenRoute, model2vec, trafilatura, sumy and numpy.

The live digest is at digest.shevinum.dev, and the source is at github.com/ShevinuM/daily-tech-digest.