@injaneity/pi-computer-use

Pi extension that lets AI agents observe and control macOS and Windows apps.

Packages

Package details

extension

Install @injaneity/pi-computer-use from npm and Pi will load the resources declared by the package manifest.

npm repohome report
$ pi install npm:@injaneity/pi-computer-use
Package
@injaneity/pi-computer-use
Version
0.4.3
Published
Jul 12, 2026
Downloads
1,881/mo · 635/wk
Author
injaneity
License
MIT
Types
extension
Size
3 MB
Dependencies
0 dependencies · 3 peers
Pi manifest JSON
{
  "extensions": [
    "./extensions"
  ],
  "image": "./assets/reference/img.jpg"
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

pi-computer-use

pi-computer-use lets AI agents use desktop apps on macOS and Windows.

The macOS helper requires macOS 14 or newer.

An agent can look at an app window, understand the buttons and text inside it, and perform actions like clicking, typing, scrolling, and waiting for something to change. This is useful when the agent needs to work with a normal desktop app instead of an API, a terminal command, or a file.

New to computer use? Start with: Wait, what exactly is Computer Use?

What this package does

This is a Pi extension. After installation, Pi agents get tools for:

  • finding open apps and windows
  • observing what is visible in a window
  • searching the visible interface for text, buttons, and controls
  • inspecting parts of the interface in more detail
  • clicking, typing, scrolling, and pressing UI controls
  • waiting for UI changes

In short: it gives an agent a controlled way to operate desktop software.

What this package is not

pi-computer-use is not a replacement for app APIs or MCP servers. If an app has a reliable direct integration, use that first.

Computer use is most helpful when the only available interface is the app on screen.

Install

pi install git:github.com/injaneity/pi-computer-use@v0.4.3

Start Pi and complete the platform setup flow.

On macOS, grant permissions to:

/Applications/pi-computer-use.app

Required macOS permissions:

  • Accessibility
  • Screen Recording, shown as Screen and System Audio Recording on newer macOS versions

The macOS setup flow registers the helper first, so it should already appear in both Settings panes. Enable the toggles and choose Recheck.

On Windows, use an interactive desktop session. Windows support uses the platform accessibility APIs and does not use the macOS helper app or TCC permission flow.

Use /computer-use inside Pi to show the active configuration and where it came from.

Main tools

  • find_roots
  • observe_ui
  • search_ui
  • expand_ui
  • inspect_ui
  • act_ui
  • read_text
  • wait_for

See docs/usage.md for the full tool reference.

Documentation

Development status

The architecture is centered on immutable, state-scoped observations. Desktop surfaces and CDP pages form one multi-root forest; progressive outline queries remain cached, while live work is ordered per physical resource so independent roots can run in parallel. act_ui accepts one or more intent steps, preserves focus across dependent input, verifies delivery, recovers safely, stores one complete successor state, and returns a compact diff when identity confidence allows. Older direct tools such as screenshot, click, set_text, and computer_actions are no longer part of the public extension surface.

License

MIT