pi-jev — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by y0usaf · Agent Tool · ★ 106

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is pi-jev safe to install? View the security audit →

About pi-jev

pi-jev TypeSafe Jev as a decision layer for the Pi coding agent. Jev answers typed questions about a piece of state. Ask whether something is true and you get a probability. Ask it to pick from a list and you get the option plus a distribution over the alternatives. It does not write prose, so nothing here parses sentences. The answers arrive as numbers your code branches on. Three things use it. A gate judges , , and calls before they run. An output judge reads what a call printed. A tool lets the model ask for the same kind of judgement itself. Install The extension needs an API key. Without one it loads, says so once, and stays out of the way. The gate All four go in one request, so a judgement costs one round trip of roughly 300 ms instead of four. Shadow mode is the default. A flagged call produces a notification and a footer status. In enforce mode a flagged call asks you to confirm before it runs. Headless runs (, RPC) can

guardrailsjevpi-extensionpi-packagetypesafe

Quick Facts

Stars106
Forks3
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score73.9034611087187/100
Open Issues1
Last Updated2026-09-19
Created2026-09-16
Platformsnode
Est. Tokens~6k

Compatible Skills

These tools work well together with pi-jev for enhanced workflows:

  • pi-codex-goal — semantic(0.51)+complementary+rare_topics+same_lang+similar_pop+shared_platform (77%)

pi-jev alternative? Top 6 similar tools

Looking for a pi-jev alternative? If you're comparing pi-jev with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pi-warden by DevMortimer · ⭐ 100

    Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversib

  • awesome-typesafe by AbdelStark · ⭐ 372

    A curated list of official resources and community projects for TypeSafe, System One models, and Jev.

  • pi-cursor-sdk by fitchmultz · ⭐ 330

    Run Cursor's agent loop inside the pi coding agent via local Cursor SDK agents, with native model selection, t

  • pi-agent-browser-native by fitchmultz · ⭐ 225

    pi extension that exposes agent-browser as a native tool for browser automation

  • pi-codex-goal by fitchmultz · ⭐ 190

    Codex-style goal tracking and continuation for pi.

  • awesome-jev by AnotiaWang · ⭐ 96

    A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is pi-jev?

pi-jev is TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers. It is categorized as a Agent Tool with 106 GitHub stars.

What programming language is pi-jev written in?

pi-jev is primarily written in TypeScript. It covers topics such as guardrails, jev, pi-extension.

How do I install or use pi-jev?

You can find installation instructions and usage details in the pi-jev GitHub repository at github.com/y0usaf/pi-jev. The project has 106 stars and 3 forks, indicating an active community.

What license does pi-jev use?

pi-jev is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to pi-jev?

The top alternatives to pi-jev on Agent Skills Hub include pi-warden, awesome-typesafe, pi-cursor-sdk. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools