Been deep in AI-assisted dev work and kept hitting the same wall: something breaks in AI-generated code and there's no way to answer "which prompt wrote this, which model, and what was the context?" Root cause analysis becomes guesswork. Built LineageLens to fix that. It runs a local proxy on port 8788 that sits between your AI tools and their providers. Every time an AI writes ≥4 lines into your codebase, it captures the exact prompt, the model and tool that produced it (Cursor, Claude Code)