I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
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
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
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
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


