Jev in production › Agent guardrails and approvals

Canny

Hooks Claude Code and Codex CLI; Jev answers whether an edit breaks a CLAUDE.md or AGENTS.md rule and whether a message claims done, as notes only, while ledger checks block. A 25-pair Opus 5 A/B had 25 of 25 passes in both arms (author).

Open on GitHub ↗

25 of 25measured against a baseline, as published by the source
Use
Agent guardrails and approvals
Industry
Developer tools
Form
Open-source tool
Stage
Beta
Plugs into
Claude Code, Codex CLI
Listed
2026-09-21
Found via
github
Repository
qkal/Canny
Stars
135
Forks
18
Last push
2026-11-13
Language
TypeScript
License
MIT

The README opens with

A supervision layer for AI coding agents. It hooks into Claude Code and Codex CLI, keeps a ledger of what the agent actually did, and will not let it finish on a claim.

Latest release: v0.4.0. If you run 0.3.0 or earlier, update: in those versions a failing check followed later in the same command by (pnpm test && echo ok true) opened the done-gate, edits that skipped or deleted tests on Windows went through unasked, and the ledger recorded files a shell command never wrote, holding the done-gate on them.

Badge

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

Listed in Jev in production

Also used for agent guardrails and approvals