jev-firewall
Real-time firewall for AI coding agents: a PreToolUse hook checks every Claude Code / Codex tool call with deterministic shell-aware rules, and unmatched actions go to Jev for a calibrated allow/ask/block that fails closed.
A real-time firewall for AI coding agents: every Claude Code / Codex tool call is checked before it reaches your machine
How it uses Jev
AI agents like Claude Code and Codex run shell commands, read files, and hit the network on your machine. jev-firewall sits between the agent and your system as a PreToolUse hook: every action is checked by deterministic rules plus the Jev decision model, which answers exactly one of allow / ask / block with calibrated confidence. Confident answers act instantly; uncertain ones go to a human.
Getting started
1. Asks which provider serves your Jev key — TypeSafe direct ( TYPESAFE API KEY from console.typesafe.ai) or the Vercel AI Gateway ( AI GATEWAY API KEY , vck … from the Vercel dashboard). 2. Validates the key with one live Jev call — a rejected key is never saved. (A key that is valid but behind a billing gate still s…
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.