jevbooks

← All projects

jevsql

EugeneBoondock/jevsql

SQL with natural-language predicates, powered by TypeSafe's Jev.

Scoring & Ranking62%Runner-up: Infra / SDKs / Integrations

What it is

JevSQL adds TypeSafe Jev judgments to SQLite, letting you compare records by meaning, select exact evidence from text, rank retrieved passages, route uncertain results to review, and detect when a changed source invalidates an earlier decision. It runs as a Node library or CLI with zero runtime dependencies.

How it uses Jev

JevSQL uses Jev to make decisions on database rows: jev_choice classifies rows into categories, jev_noul returns a yes-probability, jev_bool returns a boolean, jev_match estimates entity equivalence, and jev_pick selects an exact source span. Results are used in SQL queries and materialized as ordinary SQLite tables.

Primitives:choicescorenoul

Technique worth stealing

Materialize Jev decisions as ordinary SQLite tables with incremental refresh, caching, and cost guards.

Try it

npm test; npm run workflows; node bin/jevsql.mjs demo

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.90
  • Shows a System One patternyes0.63
  • Handles uncertaintyunclear0.49
  • Measuredno0.05
  • Runnableyes0.78
  • Worth recommendingunclear0.42
  • Model replicano0.09
  • Problem scopescore on a 0–2 scale1.48
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.