Jev in production › Agent guardrails and approvals

pi-reply-guard

Pi agent plugin uses Jev by default to score each reply against installed skills on a 0-1 scale and triggers a rewrite when the score falls short.

Open on GitHub ↗

The source publishes no measured number.
Use
Agent guardrails and approvals
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
Pi
Listed
2026-10-08
Found via
github
Repository
amalavet/pi-reply-guard
Stars
4
Forks
0
Last push
2026-10-08
Language
TypeScript
License
MIT

The README opens with

Checks each agent reply against a list of skills. A classifier model (Jev by default) determines if the reply adheres to the skill on a scale of 0-1. If a reply does not adhere to the skill, the agent is prompted to edit their reply to adhere to the skill.

https://github.com/user-attachments/assets/c8c65cf3-3030-44af-88e1-03f897d86447

Run /reply-guard in Pi to open the settings menu. Select a setting to change it, or choose “Edit JSON” to edit the full configuration. Each change saves to ~/.pi/agent/reply-guard.json and applies to the next reply:

Badge

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

Listed in Jev in production

Also used for agent guardrails and approvals