Agent PR Gatekeeper

A repo-side gate that filters AI-flavored PRs and issues for open source maintainers

Problem

Maintainers increasingly receive PRs from bots and AI agents—one post describes a suspiciously well-formatted CVE fix PR that turned out to come from an automated security scanner. They also get flooded with AI-flavored duplicate issues. Manual triage is getting expensive, and existing GitHub workflows can't tell human-quality contributions from AI-generated noise.

Solution

A GitHub App / CI action installed on the repo: scores every new PR and issue on provenance and quality (commit pattern, diff entropy, template reuse, account behavior), auto-labels, notifies maintainers, and can downrank or auto-reply to obvious low-quality content. Rules are versioned so maintainers can "set the rules upfront."

Users

Open source maintainers and tech leads at small teams

MVP

GitHub App that reads new PRs/issues; 0-100 trust score from commit patterns and diff features; configurable thresholds to auto-label or comment; rules stored as YAML in the repo; simple rule editor page

Revenue

Free for public repos, subscription for private repos or advanced rules; enterprise tier for team-level rule auditing.

Why now

AI agents have driven the cost of opening a PR to near zero, but maintainer-side tooling is still manual—a clear gap for an indie developer.