✨ Build AI agents and web apps — with a single binary.

A powerful and easy-to-use Go development framework that enables you to effortlessly build stable, reliable, and high-performance backend services with a "low-code" approach.

Open-source PR gate for Python, TS/JS, Java, and Go. Stop merging dead code, secrets, security flows, and AI-code regressions. For first timers refer to https://duriantaco.github.io/skylos/repo-map/

Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides comprehensive security rules that guide AI assistants to generate more secure code automatically.

SwiftUI projects for my YouTube tutorials and Medium article.

Security checklist for vibe coded apps. AI rules file + automated audit + manual verification.

Detect and patch vulnerabilities in AI-generated Python code — VS Code extension

Stop shipping AI slop. Detects empty functions, fake documentation, and inflated comments in AI-generated code. Production-ready.

⚡ The AI Slop Index linter inspired by @karpathy. Detects hallucinated imports, any-type abuse, vibe coding, and soul-less patterns in TypeScript/JavaScript/React. Fast (~4s), educational, CI-ready. npx karpeslop@latest

Anti-slop linter for AI-assisted codebases

An experimental, 100% AI-generated, high-performance code intelligence server providing AI assistants with a graph-based understanding of codebases.

Language Agnostic Ultra Fast Best Practice Analyzer

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

🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing.

Julia interface to the Giac computer algebra system

Battle-tested Claude Code skills for hardening vibe-coded projects. Audit, clean, and ship AI-generated codebases with confidence.

GitHub Manager Pro is a powerful web application for managing your GitHub followers and following relationships. It helps you discover users who don't follow you back (Unfollowers) and non-reciprocal relationships, while providing smart tools to manage your following list safely and efficiently.

Production-grade quality assurance framework for AI-generated code. Validates testing, security, performance, and maintainability in your CI/CD pipeline.

Unified solution for SemEval-2026 Task 13: GenAI Code Detection & Attribution. A modular framework covering Subtasks A (Detection), B (Authorship), and C (Mixed-Source Analysis), designed to distinguish and analyze LLM-generated vs. Human code with a centralized pipeline.

Detect architectural erosion from AI-generated code. Static analyzer for pattern fragmentation, architecture violations & mutant duplicates.