Parallel work in one repository by footprint

The idea

Each plan predicts the files and functions it touches; overlapping work goes to the same worker or waits, and disjoint work runs side by side without worktrees.

The problem
Parallel agents editing the same files collide.
Why it matters
Fewer conflicting edits, with a visible reason when work is held.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

  • Delegation down the chain with fan-out

    A manager splits work into parts, creates every child in one transaction with dependencies, and waits once for all of them.

  • Employee supervises its agents

    The AI employee plans, briefs, reviews, integrates and talks to people. It hands bounded plan slices to cheaper models or agent CLIs.

  • Campaigns over a goal

    A campaign is a root item and all work under it, with limits, one-click hold and resume, one instruction sent to all open work, and a report of runs, pull requests, cost and follow-ups.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.