I Open-Sourced Claude Basecamp - Come Help Me Build a Reconciliation Loop for Claude Code

Kubernetes changed infrastructure forever with one idea: you declare desired state, and the system continuously reconciles reality to match it. I wanted that for my codebase, so I built Claude Basecamp and I'm open-sourcing it today.

If you're running Claude Code across more than one repo, I'd genuinely love for you to try it, break it, and help me build it out.

Try it in one command:

npx claude-basecamp

No install, no database, no config. It discovers the projects Claude Code already knows about and opens at http://localhost:4747. Runs on macOS, Linux, and Windows.

What it does

Standing checks, the reconciliation loop

Declare what must always be true, and Basecamp holds it:

• tests always green -> runs your suite on a cadence; failures dispatch a fix run that commits
• dependencies current -> npm outdated; safe updates applied, majors escalated to you
• issue backlog triaged -> gh-powered labeling and stale-closing
• anything in plain English -> "the README documents every CLI flag" checked read-only, fixed on drift

Checks run against deterministic local facts (your real test suite, real npm outdated) wherever possible, zero tokens spent checking. Drift launches a bounded, budgeted, approval-gated convergence run. Repeated failure escalates to a decision card on Home instead of retrying forever.

Reflexes, an immune system for your AI

Basecamp mines every transcript for the moments you pushed back (interruptions, "no, don't", permission denials) and turns each into an antibody. Once armed, every Claude Code session on your machine consults that memory before every Bash/Write/Edit action, so a mistake made twice gets blocked machine-wide before it happens a third time.

Session Rescue

Notices when a Claude Code session died mid-task and lets you resume the actual dead session, same session ID, full context, as a background run that finishes the job and commits.

A persistent manager for every repo

Each project gets an agent with full Claude Code tools plus control over Basecamp itself:

• "Keep the tests green from now on." -> creates a standing check
• "Our goal is to ship v1 by end of month, track it." -> records the goal
• "What's the state of this repo?" -> reads the code and tells you

Plus routines, background runs, an updates feed, goals, git-aware repo cards, stats, a command palette, an approval queue, notifications, incoming webhooks, GitHub issue and PR integration, and a one-click connector and skill catalog.

Why it's safe to run unattended

• Zero dependencies, about 4,000 lines of plain Node and vanilla JS, auditable in one sitting
• Local only, binds to 127.0.0.1, nothing leaves your machine, no telemetry
• Read-only on Claude's data, except explicit, confirmed, backed-up connector edits
• CSRF-guarded endpoints, webhooks use unguessable per-routine tokens
• Sandboxed by Claude Code's own permission modes
• Public domain (Unlicense), fork it, audit it, vendor it, no license gymnastics

Come build this with me

This is genuinely early, and I'd rather it grow from real usage than my own guesses. A few places I'd especially love a hand:

• Cross-repo resource governor, global token and attention budgeting across all checks
• Cost guardrails, per-routine monthly budgets
• One-click graphify export for token-heavy sessions
• More routine templates, more catalog entries, more edge cases from running this against your own repos

The repo is here: https://github.com/graybyrd13/claude-basecamp

Clone it, run npm test, poke around the code, open an issue, send a PR. All contributions are welcome, from typo fixes to entirely new features. And if you just want to kick the tires, npx claude-basecamp is all it takes. Let me know what breaks!