Recommendation and personalisation with decision models

Runnable Jev samples: README checks, AGENTS.md readiness, PR triage, MovieLens next-watch ranking and issue triage, with measured runs.

Local-first feed that merges arXiv, GitHub, Hacker News and Bilibili results, with optional Jev title-relevance scores as a filter.

Go CLI for Jev that returns numbers to shell scripts, with threshold exit codes and a weighted multi-dimension rank command.

Chrome extension that badges X and LinkedIn posts READ, MAYBE or SKIP against your plain-English interest profile as you scroll.

Chrome extension that scores loaded X posts against your reading goal with Jev and ranks top matches pairwise.

Chrome extension that asks Jev typed questions about an article, video or feed item and says read now, skim, save or skip.

BYOK Chrome extension where Jev scores X posts for relevance, substance and bait, and the extension highlights, dims or hides them locally.

Python CLI that fetches recent arXiv papers, scores relevance to your research profile with Jev P(True) and writes daily rankings.

TypeScript framework for adaptive screens where Jev ranks, gates and picks existing UI items and code enforces thresholds and stability.

Tech reading feed from Hacker News, Dev.to, Hashnode and Lobsters, ranked by Jev scores against your skill summary.

GoodWatch movie and TV recommendation monorepo, listed for an experiment comparing Jev question designs for attribute scoring.

Pull request adding Jev to station-suggestion reranking in the TrainLCD transit app's Cloudflare Worker backend.

Map where you ask anything in plain words and Jev gives every nearby place a probability, lighting up those likely to match.

AutoTrust's vision version of JEV-27B, ranked first of 20 on the community Jev Decision Index vision board.

Profile matching that encodes preference criteria as Clef or Jev decision vectors, retrieves with HNSW and checks rules both ways.

Interactive page where HR tool logos rise out of a physics pile as Jev judges which fit a typed HR problem.

ChemIllusion post on Jev ranking RDKit-validated structure candidates as autocomplete cards in a chemistry sketcher, about 0.2 s each.