Running Agents in Parallel

Run agents side by side, conflict-free.

The Workflow

Step 1 — Create panes

Press ⌘+N (macOS) or Ctrl+N (Windows/Linux) for each task. Give each pane a descriptive feature name — this becomes the branch name.

Step 2 — Assign tasks

In each pane’s terminal, give the agent its instructions. Because each pane runs in an isolated worktree, agents work on independent copies of your codebase.

Step 3 — Monitor

Notifications alert you when an agent finishes or needs input — no need to babysit each terminal.

Let an Agent Create the Panes

Pane’s runpane CLI is agent-operable. If you already have a list of issues or tasks, you can ask your current agent to set up the next panes for you.

runpane doctor --json
runpane agent-context --json
runpane repos list --json
runpane panes create --repo active --name issue-252 --agent codex --prompt "Plan issue 252" --source agent --wait-ready --yes --json
runpane panels wait --panel <panel-id> --for ready --json
runpane panels screen --panel <panel-id> --limit 80 --json

The agent can use runpane agent-context --command "panes create" when it needs the full schema for pane creation, or fetch /runpane-cli-contract.json before installing. See runpane CLI for the complete flow, including registering a repository with runpane repos add.

Tips

• Write self-contained tasks. Agents that touch overlapping files will cause merge conflicts when you go to integrate. Scope each task to a single feature or file boundary.
• Notifications do the waiting for you. Enable desktop notifications in Settings → Notifications so you’re alerted the moment an agent finishes or needs input — no polling required.
• Review and commit each pane independently. Use ⌘+⇧+K to commit a pane’s work, then move to the next. Integrate via your normal PR or merge flow.