Quick confession: this started as "let me stop babysitting my tests and just make them stay green," and it turned into something a lot bigger. I want to be upfront about where I'm actually trying to take it.
I built Claude Basecamp, and as of today it's open source. The reconciliation loop (declare "tests always green," it holds that true) is the part you'll notice first, but it's not really the point. The point is I want this to become the operating system for everything you do with Claude Code, one place that knows about every repo, every session, every routine, every connector, every skill, and every mistake it's ever made, instead of all of that living scattered across terminal windows and dead transcripts.
Right now it already covers a decent chunk of that:
npx claude-basecamp
No install, no config. It finds the projects Claude Code already knows about and opens at http://localhost:4747.
Standing checks, the reconciliation loop. "Tests always green," "dependencies current," "the README documents every CLI flag" — say it once, Basecamp keeps it true, dispatches a fix run when it drifts, and only bugs you for the decisions that actually need a human.
Reflexes. It goes back through your old transcripts, finds every time you said "no, don't do that," and turns it into a standing memory that every Claude Code session on your machine checks before touching Bash, Write, or Edit. A mistake made once doesn't get to happen a third time.
Session Rescue. Resumes the actual dead session, same session ID, full context, when Claude Code dies mid-task, instead of starting over from scratch.
A manager for every repo you just talk to: "keep the tests green," "track this goal," "what's the state of this repo?" Plus routines, background runs, an activity feed, stats, GitHub issue and PR hooks, notifications, webhooks, and a one-click catalog for connectors and skills.
That's where it is today. What I actually want it to become is the default place you open whenever you're working with Claude on your machine, across every repo and every workflow, instead of a pile of disconnected tools and tabs. That's a much bigger project than one person building alone in a corner, which is exactly why I'm putting this out now instead of polishing it quietly for another six months.
Why I'm comfortable running this unattended: zero dependencies, about 4,000 lines of plain Node you can read in an evening. Everything's local, binds to 127.0.0.1, no telemetry, nothing phones home. Read-only on your Claude data except one explicit, confirmed, backed-up write path. Sandboxed by whatever permission mode you already run Claude Code in. Public domain under the Unlicense, so there's nothing to negotiate if you want to fork it or vendor it.
Where I need help: pretty much everywhere past this first slice. A resource governor for token budgets across repos, cost guardrails, more routine templates, more catalog entries, and honestly just people running it against their own weird repo setups and telling me what breaks or what's missing. If the idea of an open-source OS for Claude resonates with you at all, I'd love collaborators, not just users.
Repo: https://github.com/graybyrd13/claude-basecamp
npx claude-basecamp
to try it, npm test
if you want to dig into the code. Issues and PRs both genuinely welcome, let's see how big we can make this.