Show HN: I built an AI that generates clean docs for vibe-coded apps (superdocs.cloud)
Every time I shipped something fast with Cursor / Replit / Antigravity, docs became the bottleneck. GitBook felt heavy, manual writing felt dishonest (the code kept changing), and most AI doc tools wanted me to “explain” my own code.
So I built a small tool that does the opposite:
Connects to a repo
Reads the code + structure
Infers architecture, flows, APIs, and components
Outputs GitBook-style documentation automatically
This started as a personal hack while shipping a side project. The first version was rough (hallucinated edge cases, weak on frontend state), but it already saved me hours per project.
What surprised me:
Repo structure matters more than comments
Vibe-coded apps are harder to document than “clean” ones
Docs don’t need to be perfect to be useful—they need to be current
What’s still broken:
Complex monorepos
Heavy frontend logic
Long-running background jobs
I’m sharing this mostly to learn: How are others handling documentation for fast, AI-assisted builds? Do you write docs manually, skip them, or automate somehow?
Link is in the comments for anyone curious.
2 comments
[ 0.23 ms ] story [ 18.7 ms ] threadAlso add example that can be seen without entering an email address.
a. You don't need to let any LLM index your code. b. I am focused more on the consumer facing product side.. Yes, right now it scans codes but my goal is to soon use computer use to work on the interface-side user flow (like onboarding, etc.). Maybe, create an agent for your customers to never get stuck coz of UX again. c. I made it public, you can check out docs, demos, etc.. Maybe I will also just open source this version once I am done with the CUA stuff..
Bonus stuff- I just built a CLI version so no interface needed at all, just 2 terminal command and get your docs ready.