Use cases
Monitor multiple coding agents from one place
Updated · 2 min read
Running agents in parallel creates a second job: noticing when each one needs you. Perch gathers supported sessions into a screen-edge shelf while keeping each project in its own app.
Separate running work from waiting work
A busy terminal does not tell you what the other sessions are doing. Perch makes the distinction visible: Needs you, Working and Recent. A blue ring means work is running, amber means attention is needed, and a green check marks a finished turn.
Status depends on the events each provider exposes. Cursor passive hooks do not report awaiting-permission status. The absence of an amber mark cannot prove that every provider is able to continue.
Give each agent independent work
- Split the work into tasks with clear ownership and verification criteria.
- Avoid simultaneous edits to the same working copy.
- Review waiting requests in their own project context.
- Inspect and validate finished changes before combining the results.
Clear requests without losing context
With opt-in answering, Claude Code supports tools, questions, plans and replies. Codex supports approvals and replies; Cursor supports replies after a turn. Every answer has two seconds to undo.
Recent steps show kinds of activity and their timing, built from status rather than a transcript. Open the agent when you need its full output.
Keep orchestration in your existing workflow
Perch does not assign tasks, create branches, schedule agents or resolve conflicts. It keeps activity visible while you remain responsible for task boundaries and integration.
Common questions
Can I mix agents in the same shelf?
Yes. Supported Claude Code, Codex and Cursor sessions appear together, with different available actions.
Is a completed turn a verified result?
No. Review the changes and check the result in the project.
Your agents, one glance away.
Perch is launching soon. Join the launch list to hear when it is ready.
macOS 14+ · Apple silicon · Native SwiftUI + AppKit