Drift
Quality control layer that detects structural issues in AI-generated Python code
Visit mick-gsk.github.io ↗What is Drift?
Drift is a code coherence monitor designed to catch problems that AI coding tools introduce silently—pattern fragmentation, architecture violations, and near-duplicate code that pass linters and type checkers. It analyzes Python codebases deterministically using AST analysis and git history, without requiring an LLM. The tool works as a Claude Code plugin with a two-line install and no dependencies, or as a standalone analyzer via pip.
Built for developers using AI agents to generate code, Drift provides 24 signals across analyzed files and achieves 77–95% precision. It integrates agent-natively as an MCP tool, runs in-browser for public repositories, and can be installed locally. The maker built it as a Claude Code plugin that answers in under 100 milliseconds.
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 Drift automatically. Evidence: GitHub mick-gsk/drift; repo has AGENTS.md, .github/copilot-instructions.md; repo topic "ai-generated-code". View source.
Similar vibe-coded apps

Frontend framework that stops AI agents from generating generic UIs

Open source AI gateway routing across 350+ providers through one endpoint

Open-source AI job search agent that runs locally in your CLI

Context optimization layer that compresses LLM inputs to reduce token usage

CLI proxy that cuts noise from command output before it reaches AI

LLM-driven stock analysis system for A-share, Hong Kong, and US markets

Dependency-aware issue tracker for AI coding agents that survive context loss

Local code graph for AI-assisted reviews with 63x context reduction