Launched this week
Cleq

Cleq

Score how well your team guards AI-generated code

6 followers

Visit website
AI Code Guardian is a GitHub App that scores every PR for security, performance, and quality. Track your team's Guardian Score to see who's catching AI mistakes. What we score: - PR Score (0-100) — How clean is this code? - Guardian Score (0-100) — How effective is this reviewer? - Team Health (0-100) — Is AI helping or hurting?
Cleq gallery image
Cleq gallery image
Cleq gallery image
Cleq gallery image
Cleq gallery image
Free Options
Launch tags:Productivity•Developer Tools•GitHub
Launch Team / Built With
Framer
Framer
Launch websites with enterprise needs at startup speeds.
Promoted

What do you think? …

Adoo Labs
Maker
📌
Hey Product Hunt! 👋 I'm Arya, and I built AI Code Guardian because I kept seeing the same problem: developers blindly accepting AI-generated code. Copilot suggests a function. Developer hits Tab. PR gets a quick "LGTM." Shipped to production. But was that code actually good? We had no way to answer that question at scale—until now. The insight: The real quality gate isn't the AI. It's the human reviewing the code. So we built a system that scores both the code AND the reviewer. What makes us different: - CodeMetrics tracks activity (commits, PRs). Activity ≠ quality. - CodeAnt scans for security. Security is just one dimension. - We score the entire loop: the code, the review, and whether feedback gets addressed. The Guardian Score is the metric I'm most excited about. It answers: "When this person reviews code, do their comments actually improve the codebase?" A reviewer with a 90 Guardian Score is catching real issues. A reviewer with a 40 is rubber-stamping. We're free for public repos and take 30 seconds to install. Would love your feedback-especially if you're an engineering manager trying to figure out if AI tools are actually working for your team.
Shiv

Thanks for focusing on guardrails. Running a compliance heavy b2b product, this is exactly the kind of visibility teams need as AI increases code output

Adoo Labs
Maker
Easy Tools Dev

The Guardian Score concept is brilliant—I've seen too many "LGTM" reviews that miss obvious issues. My biggest concern with scoring systems like this is calibration: how does it distinguish between a senior dev who catches subtle performance issues versus someone who nitpicks code style? Also, does the score account for false positives, or is a rejected suggestion counted as a negative even if the original code was actually correct?