Your issue tracker is filling with AI slop.
Screen it.

SlopScreen flags likely AI-generated pull requests and issues on GitHub, right on the page. One click, comments scored, reasons shown. Built for maintainers who read contributions for a living and are tired of burning review time on generated ones.

Get it for Firefox Privacy policy
SlopScreen scanning a pull request: a red badge flags the AI-generated description with the signals that fired, a green badge marks the human review comment as clean
One click. Every comment scored, with the reasons shown.

Why maintainers use it

Codeberg, Godot, OpenJDK, Rust, and Ghostty all restricted AI-generated contributions this year, and enforcing a policy means someone has to read every submission twice. SlopScreen does the first read: a scan button on every PR and issue, a badge on every comment, and a breakdown of exactly which signals fired so you can judge for yourself.

SlopScreen batch mode on a repository's pull request list, with a small badge next to each open PR showing its AI score
Batch mode scores a repo's open pull requests at a glance.

Honest by design

The classifier is calibrated to a 5% false-positive operating point and abstains on text too short to judge. Every result is labeled a signal, not a verdict. Flagging a real person's writing as AI is worse than missing one bot, and the tool is built around that. The corpus, the calibration, and what it gets wrong are all written up on the measurement page, with a command to reproduce the numbers.

Private by design

Nothing leaves your browser until you click scan. Scanned text is scored and discarded, never stored. No accounts, no tracking. The whole policy fits on one page.