Coding agents in containers, one per issue

Long-running agentsTeam running Claude Code headless in containers on its own server

We run up to six containers on a spare server. Each one picks a GitHub issue labelled 'agent', runs Claude Code headless, and opens a pull request. Twice a week, two containers took the same issue, and every container started cold, rereading the repo.

How do I stop two headless Claude Code containers from working on the same GitHub issue?

Set up ArcRoom in each container with npx arcroom init, using ARCROOM_API_KEY and ARCROOM_APPROVE_CHECKS from secrets, and have the agent call claim_task on the issue before it starts. A second container sees the claim and picks another. Saved answers, decisions and code map lines reach every container through recall, and a final arcroom flush saves what it learned.

Also asked as: Our agent containers keep picking the same issue and rereading the repo. What can we do? · How do I share memory between Claude Code agents running in Docker containers? · Can parallel headless agents claim tasks so they don't overlap?

The work

Each container runs npx arcroom init with ARCROOM_API_KEY and ARCROOM_APPROVE_CHECKS from secrets.

ArcRoom keeps
  • Claim
  • Code map
  • Decision
  • Recall
  • Flush in CI
The next agent gets

claim_task → already claimed: "issue #812 date picker in Safari" (container w3, 9 min ago)

Step by step

  1. Each container runs npx arcroom init with ARCROOM_API_KEY and ARCROOM_APPROVE_CHECKS from secrets.
  2. Before starting, the agent calls claim_task on the issue; a second container sees the claim and picks another.
  3. Saved answers, decisions and code map lines reach every container through recall.
  4. The container's last step is arcroom flush, so what it learned is saved before it is removed.

What the agent sees

claim_task → already claimed: "issue #812 date picker in Safari" (container w3, 9 min ago)
Recall: code map · packages/ui/date: wraps react-day-picker, Safari fix in polyfills.ts

Compared with today's tools

GitHub issue assignment

A worker assigns the issue to a bot account before starting, and other workers skip assigned issues.

Setup
1–2 hours
Ongoing
Unassign issues from crashed workers, ~15 min a week

ArcRoom

Every agent reads the team playbook before it works and writes to it when it finishes. Nothing to update by hand.

Setup
2 min (npx arcroom init)
Ongoing
None

Assignment is a fine lock and visible to people; it doesn't give the next container the repo knowledge earlier containers gathered.

Where it stops

Handover comes through saved steps, answers and the project's last-run note. Claims prevent duplicates only if the agent calls claim_task first.

Try it in your project

Works with the agents your team already uses, and any agent over MCP or the HTTP API.

More in long-running agents