HN Explorer

Show HN: Ccgs – Collaborative Claude Code sessions, stored in Git branches (github.com)

6 points by scrollaway ↗ HN
My team uses Claude Code daily, and the sessions have become some of the most useful artifacts we produce. But they're trapped in ~/.claude/projects/ on whichever laptop they happened on. There's no good way to hand a colleague "the session where I untangled the migration" so they can claude --resume it and keep going from where I left off. Enter ccgs: Share Claude Code sessions through an orphan branch (@ccgs/<name>) in your existing repo's remote

- Session files carry the author's absolute paths. On pull, ccgs rewrites the working dir back to your path so resume actually works — surgically editing only the structural cwd field, not a blind find-and-replace that would happily corrupt the transcript.

- Everything goes through git plumbing (hash-object/commit-tree/update-ref) against a throwaway index. It never touches your working tree, index, or current branch, and it's fine with a dirty tree. It will not git checkout something behind your back.

To try it without installing: `npx claude-git-sessions`. This also incidentally allows you to move a directory and carry the claude code transcripts with it (just push first, then move the directory, then pull)

IMPORTANT CAVEAT: Unless you have a very good security hygiene, your Claude Code sessions are likely full of sensitive information such as environment secrets. Use with caution and avoid using on public repositories. Branches used by ccgs are prefixed by `@ccgs/` so you can easily filter them out.

This project was written by and with Claude Code. This Show HN was not.

(Reposted with URL fixed)

4 comments

[ 2.5 ms ] story [ 23.1 ms ] thread
AG342
I like the idea, but this does raise a larger question about sensitive information (that you've alluded to, but I think it's more of a systemic/cultural problem). Everyone knows you shouldn't be pasting env secrets and customer data into Claude, but many do it anyway because the perceived productivity gains offered by tools like Claude Code are just too high to ignore (and the payoff is instant and the potential risk is later).

What this does though is make that visible. If someone partakes in that bad practice, then the secrets are already sitting in the transcripts on their laptop - this just moves them somewhere shared and permanent. Maybe that's enough to discourage the practice, idk. Still, not strictly your problem, but an interesting one nonetheless.

jazzen
The portability angle is compelling. The interesting design problem to me is whether a resumable session artifact has to be identical to the raw transcript.

I'd love a middle layer that preserves enough state to resume and debug while aggressively quarantining obvious secret classes and high-risk blobs. Right now the tradeoff is basically perfect replayability versus shareability, and it feels like there should be a useful middle ground there.