Open Code Review
AI code quality gate that detects and auto-fixes issues in AI-generated code
Visit codes.evallab.ai ↗What is Open Code Review?
Open Code Review is a free, open-source CI/CD tool designed to catch defects that traditional linters miss in code generated by AI assistants like Copilot, Cursor, and Claude. It detects hallucinated packages, stale APIs, logic gaps, security vulnerabilities, and over-engineered patterns across six languages. The tool works with GitHub Actions and GitLab CI, and can be run locally or self-hosted.
Beyond detection, Open Code Review automatically generates fixes for identified issues, previews changes in dry-run mode, and applies patches with a single command. The maker built it using AI coding tools including Cursor and Windsurf. It supports any LLM provider and includes a free GLM option, making it accessible for teams of any size.
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 Open Code Review automatically. Evidence: GitHub raye-deng/open-code-review; repo has .cursor, .windsurfrules, .github/copilot-instructions.md; repo topic "ai-generated-code". View source.
Similar vibe-coded apps
TypeScript framework for building AI agents without library dependencies
In-browser behavior tree execution engine for AI agents at ~60Hz
Privacy-first MCP server for semantic code search and AI-ready repositories
Local context engine that prepares task-focused file packs for AI coding agents
Local plugin that makes AI coding agents provide evidence and resist flattery
Cut your AI coding agent's token bill by half with terse output and compression