AI Code Rating
Three-character rating system for AI code disclosure in repositories
Visit aicoderating.com ↗What is AI Code Rating?
AI Code Rating is a specification and validation tool for labeling how much AI was used to write a project's code. It uses a three-character format (letter-digit-letter) published in an ACR.md file at a repo's root to show maintainer expertise level, percentage of AI-generated code, and human review rigor. The system separates three distinct questions: who can approve changes (A–E scale), how much code AI wrote (0–4 quarters), and how thoroughly humans checked AI work (a–e levels). Readers interpret ratings according to their own standards rather than receiving judgment about AI use.
Built for developers, maintainers, and project users who want transparent disclosure of AI involvement. The site includes a spec, validation tool, FAQ, and comparison with other AI disclosure standards. Built with Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered AI Code Rating automatically. Evidence: Trending on git-trends.github.io: agent files (claude-code) in ai-code-rating/aicoderating.com. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
Clone viral videos with AI agents, generate 100 variants in one command
Ad-free home screen for Google TV with trending picks and live weather
Clean Android TV launcher inspired by tvOS, ad-free with aerial screensavers
Remove ads and bloatware from Android TV and Google TV over Wi-Fi
Desktop app for DeepSeek Harness with built-in model provider support
