Grepathy - Auto-document AI coding agent decisions in your repo
Show HN: Grepathy – Claude made a decision nobody approved
Grepathy solves the mystery of unapproved coding decisions made by AI agents like Claude Code. By automatically analyzing local session transcripts, it extracts the 'why' behind specific code changes and commits them as Markdown files directly into your repository. This ensures that reasoning, risks, and agent-initiated actions are preserved forever, surviving the default 30-day transcript deletion. Future reviewers and AI agents can instantly access this context, making codebases self-explanatory and preventing knowledge loss without requiring any server or account setup.
Now the repo can answer 'why' on its own, for reviewers, teammates, and future agents.
- ballenf
Good catch on CTOs part. That scenario is one that keeps me awake at night -- that some large PR of mine has come functionality or feature that I didn't ask for and didn't notice.
How did the CTO respond to "Claude did it and I didn't catch it"? Did the AI PR summary mention it? Or did the CTO just read the code?
- q3k
> I didn't know! I didn't make that decision!
Thanks for today's dose of impostor syndrome cure.
- sixtyj
Well done.
This is not just Claude’s behaviour :)
It could be used for every agentic coding as well, because I have experienced such mess so many times in last three years.
One issue repaired, another one touched and changed…
- trjordan
100% important. But what decisions do you care about seeing?
The whole point of the agent is to make decisions for you. If you want to make every little detailed decision, just write the code.
The whole art of this problem is figuring out which decisions matter to you, and how to surface them.
(Disclosure: we're working on this too. https://tern.sh)
- vanyaland
Your .ai/why/main.md is at 97KB and 148 entries. Does anything prune that, or does a long-lived branch keep growing?