Jev in production › Agent guardrails and approvals

Jev Guard (leepokai)

Risk-scores every coding-agent tool call as deny, ask, or allow with Jev across Claude Code, Codex, Copilot, Gemini and Cursor; vendor claims about $0.00004 per call (leepokai).

Open on GitHub ↗

$0.00004measured, as published by the source
Use
Agent guardrails and approvals
Industry
Developer tools
Form
Open-source tool
Stage
In production
Listed
2026-09-25
Found via
github
Repository
leepokai/jev-guard
Stars
63
Forks
9
Last push
2026-10-02
Language
JavaScript
License
MIT
Jev Guard (leepokai) screenshot
assets/launch-poster.jpg in the leepokai/jev-guard README, MIT; shown from GitHub.

The README opens with

jev-guard A security hook for coding agents, powered by Jev .

Claude Code's auto mode is described as: "A separate classifier model reviews actions before they run, blocking anything that escalates beyond your request, targets unrecognized infrastructure, or appears driven by hostile content Claude read." That is exactly the job jev-guard does — as three typed questions to Jev (risk, userrequested, fromuntrusted) instead of a proprietary classifier — and it does it for Codex, Copilot, Gemini, Cursor, pi, OpenCode and ACP editors too, with the same policy and the same session memory everywhere. If you want auto mode outside Claude Code, or a second opinion inside it, this is the build.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent guardrails and approvals