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 Show more
jev-commit
A pre-commit hook that answers five Jev questions about the commit message and staged diff together, warning on mismatches and blocking only on a credential-shaped line.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- valentynkit
- Added
- 2026-09-22
Tagscommunitypythoncoding-agentguardrailssecuritycli
Highlights
- Five questions in one request flag filler messages, claims absent from the hunks, debug leftovers, unmentioned work, and secret-shaped values.
- Over a 152-commit corpus the median cost was $0.000044 per commit, about four cents per thousand commits.
- Warnings never block; only a credential on an added line stops the commit, and --strict blocks on findings past the threshold.
- Needs pre-commit install --hook-type commit-msg, since a plain pre-commit install will not run it.
- Python 3.10+ with no dependencies, and the hook itself takes 240 ms median, 21 ms of it a loopback call.
Quickstart
bash
pipx install git+https://github.com/valentynkit/jev-commit
printf '#!/bin/sh\nexec jev-commit "$1"\n' > .git/hooks/commit-msg
chmod +x .git/hooks/commit-msgWatch out
MIT-licensed. Needs a TypeSafe API key, and pre-commit refuses to install while core.hooksPath is set, so the hook must be added by hand there.
More like this
34GitHub stars
A CLI that turns Jev into Unix pipeline primitives: is, choose, score, filter, and guard commands return typed verdicts, stable exit codes, and versioned JSON without prompt or parsing glue.
Tools & Integrations#community#python#cli
Communitysemdecide
17GitHub stars
Agent-ergonomic CLI following the AXI conventions that gives coding agents Jev judgments for blocking risky tool calls, screening fetched content for prompt injection, triaging logs, flagging risky diffs, and ranking many items. Routine commands are decided locally at no cost.
Tools & Integrations#community#typescript#cli
Communityjev-axi
1GitHub stars
A tool-call gate for Claude Code, Codex, Cursor, and other harnesses backed by Jev: deterministic rules and a read-only allowlist run first, then one request answers allow, ask, or deny in about 400 ms.
Tools & Integrations#community#python#guardrails
Communityjev-engineering
From the community
Posts from builders shipping with Jev right now.
The launch post
Trading bot, one decision per block
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
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
@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
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@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
LLM-as-a-judge, sped up
Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)
@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
Instant compaction with Jev
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