Skip to content
JevDirectory.org
CommunityTools & Integrations22 starsVerified 2026-09-22

jev-guard

A security hook for coding agents that asks Jev three typed questions before every tool call and scans tool results for prompt injection, with adapters for Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, pi, OpenCode and ACP.

Open github.comleepokai/jev-guard
Category
Tools & Integrations
Published by
Community
Author
leepokai
Added
2026-09-22
Tagscommunityjavascriptagentscoding-agentsecurityguardrailsclaude-codecodex

Highlights

  • Before a tool runs, Jev scores the harm, whether the user requested it, and whether it came from untrusted content; destructive calls are denied.
  • After a tool returns, results are scanned for prompt injection and canaries, and hits are remembered for the rest of the session.
  • Instruction files such as skills and CLAUDE.md are checked for exfiltration, covert execution, instruction override, and canaries.
  • A typical call is about 1k tokens, roughly $0.00004 per tool call, with measured p50 around 580 ms through the Vercel AI Gateway.
  • On a machine with 662 installed skills, none crossed the flag line, while planted exfiltration samples scored 0.99.

Quickstart

bash
npm i -g jev-guard
jev-guard key YOUR_API_KEY
jev-guard install claude

Watch out

MIT-licensed. Needs Node.js 20.3+ and a TypeSafe or Vercel AI Gateway key; it is a guardrail, not a sandbox, and tool results can contain anything the agent read.

More like this

jev-belay
17GitHub stars
A Claude Code Stop hook that reads the turn transcript locally and spends one four-question Jev call only when files changed with no passing check since, blocking unverified done claims.
Tools & Integrations#community#javascript#claude-code
Communityjev-belay
pi-warden
132GitHub stars
Pi extension that supervises a coding agent with Jev judgments: it holds risky tool calls, checks writes against project Markdown rules, and feeds most issues back to the agent as a steer instead of interrupting you. The conscience is beta and off by default.
Tools & Integrations#community#typescript#guardrails
Communitypi-warden
AI Agent Skills
89GitHub stars
A collection of 26 production-ready agent skills for Claude Code, Cursor, Kiro, Windsurf, and OpenCode; four skills call TypeSafe Jev for calibrated Score and Noul judgments and fall back to heuristics when it is unavailable.
Tools & Integrations#community#python#skills
Communityskills
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Fast browser use with Stagehand

Kyle Jeong
Kyle Jeong
Browserbase
@kylejeong
·

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

Watch on X
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

Watch on X
Reply
Read 30 replies

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

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.)

Image
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

Watch on X
Reply
Read 94 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

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

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter