Skip to content
JevDirectory.org
CommunityTools & Integrations79 starsVerified 2026-09-20

pg_typesafe

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.

Category
Tools & Integrations
Published by
Community
Author
giuliosmall
Added
2026-09-20
Tagscommunitypostgressqlclassification

Highlights

  • Functions cover Noul, Choice, Score, and batched typesafe_detect_many and typesafe_classify_many variants.
  • The demo classifies 38 unique NYC 311 resolution strings in two TypeSafe requests.
  • typesafe_detect_many ran in 0.86 s versus 23 s calling typesafe_detect per row.
  • typesafe.mock_response returns a canned body for offline tests.

Watch out

Pre-alpha and tested on PostgreSQL 16 and 17; installation needs write access to pkglibdir and the key lives on the server.

More like this

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.
Tools & Integrations#community#postgres#sql
Communitypg-jev
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
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.

Trading bot, one decision per block

Classifying 1,500 real emails

this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply