Skip to content
JevDirectory.org
CommunityTools & Integrations234 starsVerified 2026-09-20

pg-jev

A PostgreSQL extension that filters, ranks, and classifies table rows with plain-language conditions judged by Jev, batching 20 rows per request and caching answers per session.

Open github.comrealZachi/pg-jev
Category
Tools & Integrations
Published by
Community
Author
realZachi
Added
2026-09-20
Tagscommunitypostgressqldatabase

Highlights

  • jev(), jev_prob(), jev_choice(), and jev_score() work inside WHERE, ORDER BY, and GROUP BY.
  • Batches 20 rows per request; a 2,000-row first run measured about 3.5 seconds and $0.012.
  • Read-ahead streams the table in physical order so LIMIT stops early work.
  • Per-row answers are cached for the session, making re-runs and threshold tweaks free.

Watch out

Managed hosts that withhold superuser or plpython3u, including Supabase, Neon, and RDS, cannot run it; needs PostgreSQL 14 to 17.

More like this

pg_typesafe
79
A pre-alpha PostgreSQL extension for categorical work in SQL: Noul, Choice, and Score functions plus batched variants that classified 38 strings in two requests.
Tools & Integrations#community#postgres#sql
Communitypg_typesafe
Search Postgres in Plain Language
The pg-jev author demos jev(), a PostgreSQL extension that filters table rows with natural-language conditions and no index or embeddings, judging 129 rows in about a second.
Tools & Integrations#community#x#video
Community
Foreman
419
A Python asyncio runtime that puts Jev in a supervision loop above Codex or OpenCode workers: it judges completion, test sufficiency, and stuck loops, then steers, retries, or stops the job.
Tools & Integrations#community#python#coding-agent
Communityforeman
Back to all resources

From the community

Posts from builders shipping with Jev right now.

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 162 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 138 replies