# Perch > A native Mac utility for agent activity and sticky notes at the edge of your screen. Perch is standalone software for Apple silicon Macs on macOS 14 and later, built with SwiftUI and AppKit. Price: $29 USD, one time, for the first 1,000 customers, then $99. Plus applicable taxes. Includes a year of updates and email support; full refund within 14 days. App license only; source code is not included. Status: Purchases are closed until delivery is ready. No payment is currently collected. ## Official pages - [Overview](https://perched.fyi/): Features, requirements, integrations, pricing, and FAQ. - [Purchase information](https://perched.fyi/checkout/): Current availability and $29 offer. - [Privacy](https://perched.fyi/privacy/): Local app data and website/payment handling. - [Terms](https://perched.fyi/terms/): Offer scope, availability, and compatibility. - [Full product information](https://perched.fyi/llms-full.txt): Plain-text product context. - [Support](mailto:support@trillium.one): Email support from One Trinity Consulting Inc. ## Integration limitations Claude Code CLI and Cursor local Agent activity have been checked live, and Codex CLI answering was checked live; the Codex desktop app is not verified yet. Cursor passive hooks do not expose awaiting-permission status. Answering is opt-in and off by default: for Claude Code, Perch can allow or deny tools, answer questions, approve or revise plans, and reply when a turn ends; Codex supports allow, deny and replies; Cursor supports a reply when a turn finishes. Every answer has a two-second undo, and Perch never answers on its own. ## Resource collections - [Resources](https://perched.fyi/resources/): Start here for all product documentation. - [Use cases](https://perched.fyi/use-cases/): Explore Perch for developers, founders, agencies and parallel coding sessions, with dedicated Claude Code, Codex and Cursor workflows. - [Guides](https://perched.fyi/guides/): Practical Perch guides for setup, agent compatibility, answering, keyboard shortcuts, privacy, troubleshooting and local sticky notes. - [Compare](https://perched.fyi/alternatives/): Compare Perch with manual terminal checks, notifications and shared agent dashboards. Understand the tradeoffs without unverified product rankings. - [Blog](https://perched.fyi/blog/): Original Perch articles about parallel coding agents, deliberate approvals, local status monitoring and reducing the checking loop. - [Glossary](https://perched.fyi/glossary/): Understand agent hooks, sessions, tool approvals, local-first software, human-in-the-loop decisions and context switching in Perch. ## Individual pages - [A coding-agent monitor for developers on Mac](https://perched.fyi/use-cases/developers/): See Claude Code, Codex and Cursor activity at the edge of your Mac. Review requests, keep notes and return to the coding session that needs you. - [Keep agents moving while you run the business](https://perched.fyi/use-cases/founders/): See when a coding agent needs a decision while you work on product, customers and the rest of your business. A local workflow with Perch for Mac. - [Keep client coding sessions in view on your Mac](https://perched.fyi/use-cases/agencies/): Track local coding sessions across client projects with Perch. Check project context before reviewing an agent request or a completed handoff. - [Monitor multiple coding agents from one place](https://perched.fyi/use-cases/parallel-agents/): See parallel Claude Code, Codex and Cursor sessions in one local view. Find what is working, finished or waiting for your next decision. - [Monitor and answer Claude Code from your screen edge](https://perched.fyi/use-cases/claude-code/): See Claude Code activity in Perch. With answering enabled, review tool requests, answer questions, approve plans and reply when a turn ends. - [Keep Codex CLI activity and requests in view on Mac](https://perched.fyi/use-cases/codex/): Use Perch beside Codex CLI to see activity and, with answering enabled, allow or deny supported requests and reply after a turn. - [See Cursor Agent activity from the edge of your Mac](https://perched.fyi/use-cases/cursor/): Monitor Cursor local Agent activity in Perch and reply after a turn finishes. Understand Cursor status limits and session navigation. - [Get started with Perch on your Mac](https://perched.fyi/guides/getting-started/): Check Perch requirements, review local agent hooks, connect your first session and understand the three status states before enabling answers. - [Perch compatibility: Claude Code, Codex and Cursor](https://perched.fyi/guides/agent-compatibility/): Compare Perch support for Claude Code, Codex CLI and Cursor local Agent: status, approvals, questions, plans, replies and navigation limits. - [Approve, answer and reply from Perch](https://perched.fyi/guides/answering-agents/): Learn Perch’s opt-in answering workflow, supported provider actions, two-second undo and handoff back to the agent’s own app. - [Perch keyboard shortcuts and the review loop](https://perched.fyi/guides/keyboard-shortcuts/): Open Perch with Control-Option-C, navigate sessions and use Return, number keys and Esc for supported answers and the two-second undo. - [What Perch stores and which permissions it needs](https://perched.fyi/guides/privacy-and-permissions/): Understand Perch’s local status storage, in-memory requests and optional Automation permission. No screen recording, microphone or Accessibility. - [What to check when agent status is not updating](https://perched.fyi/guides/agent-status-not-updating/): Check Perch’s connection, new sessions, hidden sessions and provider limits when activity or an expected request does not appear. - [Keep the next prompt beside your coding agents](https://perched.fyi/guides/sticky-notes/): Use Perch’s ten local sticky notes for follow-up prompts, acceptance criteria and review reminders, then copy them into your coding workflow. - [Perch or checking your terminal tabs?](https://perched.fyi/alternatives/terminal-tabs/): Compare manual terminal checks with a local Perch shelf. Understand where full terminal context is useful and where visible agent state helps. - [Perch or agent notifications?](https://perched.fyi/alternatives/notifications/): Compare a momentary notification with a persistent local view of coding-agent sessions. Choose around how you notice and review handoffs. - [A local Perch shelf or a shared agent dashboard?](https://perched.fyi/alternatives/agent-dashboards/): Choose between personal local visibility and requirements such as team access, remote sessions and shared task coordination. Where Perch fits. - [How to monitor multiple coding agents without checking every terminal](https://perched.fyi/blog/monitor-multiple-coding-agents/): A practical review loop for parallel coding agents: bound the tasks, distinguish running from waiting, and verify each completed result. - [Why an agent status monitor does not need your transcripts](https://perched.fyi/blog/status-without-transcripts/): How Perch separates session status from request content, and what a status-only recent-steps view can and cannot tell you about coding work. - [Keep a human decision in the coding-agent loop](https://perched.fyi/blog/human-in-the-loop-coding/): Make agent approvals easier to review without turning them into automatic decisions. A practical approach to context, scope, undo and handoff. - [Reduce the checking loop around your coding agents](https://perched.fyi/blog/reduce-agent-context-switching/): Distinguish checking for a change from reviewing a result. Use visible state, project names and small notes to manage agent handoffs on Mac. - [A coding agent, a monitor and an orchestrator do different jobs](https://perched.fyi/blog/agent-monitor-vs-agent/): Understand where Perch fits beside coding agents: local activity and human responses, with task execution and orchestration kept separate. - [What is an agent hook?](https://perched.fyi/glossary/agent-hook/): An agent hook is an event-triggered integration point. Learn how Perch uses local hooks to receive activity without reading your terminal screen. - [What is a coding-agent session?](https://perched.fyi/glossary/agent-session/): A coding-agent session is a particular ongoing interaction with an agent. Understand sessions, turns and Perch’s working, waiting and recent states. - [What does human-in-the-loop mean for coding agents?](https://perched.fyi/glossary/human-in-the-loop/): Human-in-the-loop means a person makes a decision in an automated workflow. In Perch, you review and choose each supported agent response. - [What does local-first mean for Perch?](https://perched.fyi/glossary/local-first/): For Perch, local-first means the app keeps activity and notes on your Mac and makes no network requests. Agent provider processing remains separate. - [What is a coding-agent tool approval?](https://perched.fyi/glossary/tool-approval/): A tool approval is your decision about a proposed agent action. Learn the difference between approving a tool, a plan and a completed result. - [What is context switching in an agent workflow?](https://perched.fyi/glossary/context-switching/): Context switching means moving attention between tasks or apps. Distinguish checking agent state from the focused work of reviewing its result. ## Machine-readable formats - [Content index](https://perched.fyi/resources/content.json): Full structured content, canonical URLs and Markdown URLs. - [Blog RSS](https://perched.fyi/blog/rss.xml): Articles with canonical permalinks. Every resource page links to its corresponding Markdown representation under /content/.