Skip to content

Jev directory

Jev Superpowers

An agentic software-development skill set built on obra/superpowers, where Jev in the cloud or open-weight Laya locally gates architecture choices, package vetting, shell commands, and completion checks.
Stars
35
Language
HTML
License
MIT
Reading time
3 min
Published by
Community
Author
AkashPriyadarshii
Last verified
Sep 2026

Highlights

  • Upgrades five superpowers phases: jev-brainstorming, jev-writing-plans, jev-executing-plans, jev-systematic-debugging, and jev-verification.
  • Backend-agnostic: TypeSafe cloud (jev-1.13.0) with TYPESAFE_API_KEY, or a fully offline Laya 421M ModernBERT server via TYPESAFE_BASE_URL.
  • Reported design targets: near-zero package hallucination, 33-38 ms local gate latency, about $0.00001 per cloud decision, 24/24 offline tests.
  • Ships a toolchain suite: git-jev for pre-commit gates, jev-scout for package vetting, jev-axi, jev-guard, supercov, and jev-seo.
  • The README labels its benchmark table design targets measured on the maintainer's setup and asks users to reproduce them first.

Quickstart

bash
export TYPESAFE_API_KEY=YOUR_API_KEY
bash install.sh

Watch out

MIT-licensed. A community project, not affiliated with TypeSafe; needs a TypeSafe API key for the cloud backend or a local Laya server, and its benchmark numbers are maintainer-measured design targets.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Decision outputs in Grep

X: Standard One SH (StandardThinking)

LinkedIn: What multimodal decision models actually change, and what they do not.

LinkedInJevDirectory.org

From the Jev guides

Original write-ups on what this entry is for.

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai