HN Showcase
Back to browse
GitHub Repository

🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more. MCP Server + CLI + CI/CD Action.

26 starsTypeScript

AI Code Validator – CI/CD quality gate for AI-generated code

by aneyadeng·Mar 6, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My Problem

AI-specific linting catches hallucinated packages; but static analysis won't catch logic gaps reliably.

Strengths
  • •Identifies failure modes traditional linters miss (phantom npm packages, undefined functions, empty catch blocks).
  • •Integrates into CI/CD (GitHub Actions, GitLab CI) and offers self-heal prompts for immediate feedback to AI.
  • •Real npm package (27 commits, active development, badges showing maintenance).
Weaknesses
  • •Logic gap detection via static analysis is inherently noisy—hard to distinguish incomplete AI code from intentional stubs.
  • •No benchmarks or public adoption data; unclear if detection accuracy justifies adding another gate to CI.
Target Audience

Teams using AI coding assistants (Copilot, Cursor, Claude) who want CI/CD safeguards against AI-specific failure modes.

Similar To

ESLint · SonarQube · Semgrep

Similar Projects