# Spacedock
> Spacedock is a multi-agent orchestrator where nothing ships without a decision. It lives within your existing harness: Claude Code or Codex.  Spacedock pools the decisions your agents need from you into one evidenced queue, so you make the few calls that matter and the rest keeps running.

The unit is the decision: evidence in, a resolution out (approve, send back, escalate), reason recorded. A separate agent reviews the work, so no agent rubber-stamps itself, and the bar starts rough and sharpens as you reject. Brownfield-first: on install it scans about a month of your sessions and surfaces the workflow you already run. Runs inside Claude Code or Codex.

## Links

- [Agent guide](https://spacedock.md/agents.md): how an agent should use this site and the product
- [Landing page, markdown mirror](https://spacedock.md/index.md)
- [Markdown sitemap](https://spacedock.md/sitemap.md)
- [Project README](https://github.com/spacedock-dev/spacedock/raw/main/README.md)
- Full docs index, every page as .md: https://spacedock.md/docs/llms.txt
- Docs site: https://spacedock.md/docs/
- Source: https://github.com/spacedock-dev/spacedock
- Early access: https://spacedock.md/#cta