Docs / source reviewed

pm-jev

Suggest project-item types, priorities and duplicate matches

unbraind · Sources checked 2026-10-12

Added to this collection 2026-10-12

How this project uses Jev

Input: Item titles, descriptions, bodies and tags, plus duplicate candidates shortlisted by code; bounded input excludes comments and history
Jev decides: Choice proposes a type or duplicate, Score proposes priority, and Noul flags human input and sensitive material. Code validates answer types, probabilities and allowed options
Code executes: Proposals are read-only by default. Explicit --apply updates qualifying type or priority fields and appends a receipt. Dedupe does not create or delete items, and failures are not treated as no match

Evidence and limitations

The MIT license, TypeSafe SDK integration, response validation and mutation boundary were reviewed without running the project or model. The default is local Ollama tev1, not Jev. Hosted Jev requires explicit TypeSafe selection, external-transfer opt-in and an API key. The author has not completed hosted acceptance and this remains a development version. A sensitive-data flag is not pre-transfer redaction.

This project has not been run independently here. Author-reported results are not independently verified results.

Original sources

Explore related use cases

Browse this category →