jevbooks

← All projects

jevql

kylemclaren/jevql · Homepage

Semantic SQL for vanilla Postgres, powered by Jev

Data Labeling & Curation0.47Runner-up: Scoring & RankingFunnel
Automated README summary

Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A psql-shaped CLI and Go/TypeScript/Python SDKs that run plain SQL on vanilla Postgres (no extension), then ask Jev questions about each surviving row so clients can filter, sort and group semantically.

How it uses Jev

jev(), jev_prob(), jev_choice(), jev_score(), jev_confidence() and jev_eval() take a FROM alias (or column list) and a question; the CLI packs that relation's columns into a JSON row object, sends it to TypeSafe's System One model, and attaches the returned boolean, probability, choice or score in process before filtering, grouping, sorting and limiting.

Primitives:choicescorenoul

Technique worth stealing

Strip jev predicates, GROUP BY and jev-dependent ORDER BY/LIMIT from the SQL, send the rest to Postgres, then judge only the surviving rows and project the answers back in process.

Try it

brew install kylemclaren/tap/jevql, export TYPESAFE_API_KEY and DATABASE_URL, then run jevql -c "SELECT * FROM people WHERE jev(people, 'could work from home')".

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.90
  • Shows a System One patternFound in material0.61
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalunclear0.55
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale0.98 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.90Shows a System One pattern0.61Describes handling uncertainty0.05Reports measured numbers0.05Is a runnable tool0.98Top-10 learning shortlist signal0.55Is a replica of the model0.0400.51Solves a common problem (0–2)0.98 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.77Viewfinder0.2700.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.