Docs / source reviewed

signal-radar

Screen information with Jev before enriching the highest-ranked items

damian87x · Sources checked 2026-09-27

Added to this collection 2026-09-27

How this project uses Jev

Input: X posts, TikTok search items, recent creator information or a local mail JSON export, with lane-specific scoring rubrics
Jev decides: An external jev CLI answers scoring questions and local rules rank items; call or parsing failures retain errors without a valid rank
Code executes: SQLite deduplicates items; Grok adds context only to high-ranked candidates fetched in the current run, followed by local Markdown, HTML and outbox files

Evidence and limitations

MIT source, CLI calls and file delivery were reviewed without logging into third-party platforms or running model calls. Mail input is a local export, not a live Gmail connection; content is sent through external model calls. Separate jev, Grok and collection tools are required. An outbox file is not proof of a sent notification; author cost and quality figures remain unverified.

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 →