Lineage Lens
Track which lines of your code came from AI
Start new thread
Praveen

LineageLens - AI wrote it. LineageLens proves it.

by
Lineage Lens
•
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)

Add a comment

Replies

Best
Praveen
Maker
📌
Hey Product Hunt! 👋 I built LineageLens because I kept running into the same frustrating moment — something breaks in AI-generated code and there's zero record of what prompt produced it, which model wrote it, or what context surrounded the decision. Git blame tells you who committed it. It doesn't tell you what the AI was asked. LineageLens fixes that by sitting between your AI tools and their providers via a local proxy. Every insertion of 4+ lines gets captured with the full prompt, model identity, session context, and risk signals — automatically, across Cursor, Claude Code, Copilot, Aider, Continue, and 6 more tools. The part I'm most excited about: the MCP server. Once wired into Claude Code or Cursor, you can ask "what prompt wrote this auth function?" or "which files have the highest AI risk density?" directly inside your chat — no tab switching, no reconstructing context from memory. Everything is self-hosted. Your prompts and code never leave your infrastructure. Would love brutal feedback from this community — what's missing, what's confusing, and whether this solves a problem you've actually felt. Happy to answer any questions below.