bhvbhushan

bhvbhushan / vibecop

Public

AI code quality toolkit — deterministic linter for the AI coding era. 22 detectors, GitHub Action PR gate, zero LLM required.

ai ai-code-quality ast ast-grep ci-cd
14
2
100% credibility
Found Apr 03, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Vibecop is a code quality scanner that detects antipatterns commonly introduced by AI-generated code, such as god functions, N+1 queries, unchecked database results, and security vulnerabilities, in JavaScript, TypeScript, and Python projects.

How It Works

1
🔍 Discover vibecop

You find vibecop, a friendly tool that spots common slip-ups in code written with AI help, like overly big functions or security gaps.

2
🧪 Try the playground

Paste some code into the free online playground and instantly see what issues it catches, feeling excited about the clear results.

3
💻 Set it up on your computer

Download vibecop to your machine so you can check your own projects anytime.

4
🚀 Scan your project

Choose your project folder and run a quick check to uncover hidden problems in your code.

5
📋 Review the report

Read the easy-to-understand list of issues, with tips on how to fix them, making your code stronger.

6
🔄 Add automatic checks

Connect it to your online code storage to automatically review changes before they go live.

🎉 Code feels solid

Your project now runs smoothly with fewer bugs and better security, thanks to catching AI mistakes early.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is vibecop?

vibecop is a TypeScript code quality toolkit that scans JS/TS/Python repos for 22 AI-generated antipatterns like god functions, N+1 queries, unchecked DB mutations, and SQL injection risks. It acts as a deterministic linter—no LLMs needed—using fast AST parsing to deliver reproducible results via CLI (`vibecop scan .`), GitHub Action PR comments, or an online playground for instant code github ai checks. Outputs include text, JSON, SARIF, or GitHub markdown for code quality analysis.

Why is it gaining traction?

Unlike ESLint or Pylint, vibecop targets Copilot-style bugs (debug logs in prod, excessive any types) with PR-inline code github comments and configurable gates (request changes, label, auto-close). Benchmarks on 10k+ star repos uncover 4k+ findings, proving value for code quality tools in AI-heavy workflows. Zero LLM dependency keeps scans fast and CI-friendly, even for code github repository diffs.

Who should use this?

Fullstack devs using GitHub Copilot on Node/Python backends, needing code quality checks for N+1s or god components in PRs. Teams migrating from vague code quality metrics to automated gates, or frontend folks spotting token-in-localStorage in React/Next.js. Ideal for monorepos enforcing quality assurance code before merge.

Verdict

Grab it for PR gates if AI code floods your github python code—playground lets you test risk-free. At 14 stars and 1.0% credibility score, it's early (0.x, no npm publish yet), but thorough docs and real benchmarks beat most code quality analysis tools at this stage.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.