Clawbus

ClawBus

**A minimal protocol turning multiple Claude Code sessions into an observable, auditable agent team.**

**Claude Code is excellent per session. ClawBus makes cross-session coordination auditable without inventing a new runtime.**

Claude Code is powerful as a single coding agent, but real work usually needs a team — planning, investigation, implementation, review, and human approval. ClawBus defines a minimal protocol and reference implementation so multiple Claude Code / Claude Agent SDK sessions can delegate subtasks, share context, and surface decisions that need human sign-off.

This repository is the submission for **Built with Opus 4.7: a Claude Code Hackathon** (Cerebral Valley × Anthropic, 2026-04-21 – 2026-04-26).

---

TL;DR for hackathon reviewers

git clone https://github.com/tokimwc/clawbus.git
cd clawbus
npm install
npm run build
export ANTHROPIC_API_KEY=sk-ant-...
npx clawbus demo

You should see:

1. A Planner agent decompose a toy task (examples/broken-node-project has a bug).
2. A Worker agent investigate and propose a patch.
3. A Human Approval Gate pause at the terminal asking you to approve/reject.
4. On approval, the patch is applied and npx clawbus logs shows the full causal timeline of messages.

Everything runs locally on SQLite. No network calls except to the Anthropic API. See [`docs/judging-guide.md`](docs/judging-guide.md) for a 5-minute review checklist with branches for "no API key" vs "with API key" reviewers.

**No API key handy?** The [judging guide](docs/judging-guide.md) and [`docs/scenarios/`](docs/scenarios/) contain three captured end-to-end runs with full message timelines and costs. The whole protocol fits in two pages — see [`docs/protocol.md`](docs/protocol.md).

**Want the longer argument?** [`docs/manifesto.md`](docs/manifesto.md) explains why we built this and — more importantly — what we deliberately didn't build.

---

Why a "bus"?

Individual Claude Code agents are statef