# injaneity/pi-computer-use

Let Pi control your apps on MacOS & Windows

Repository: https://github.com/injaneity/pi-computer-use
Canonical: https://ross.abutalabs.com/products/pi-computer-use
Language: Rust
License: MIT
License Family: permissive
Last push: 2026-08-18T07:04:54+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 95, longevity 9
- inputs: {"age_days": 135, "days_push": 15, "days_rel": 38, "gap_med": 1, "n_releases_24m": 22}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1777, forks 123 (observed 2026-08-28T04:05:34.731136+00:00)

## What it is
A Pi extension that gives AI agents tools to observe and operate desktop applications on macOS, Windows, and Linux. Agents can find windows, inspect UI elements, and perform actions like clicking, typing, and scrolling through accessibility APIs.

## Use cases
- automate desktop apps with an ai agent
- let an agent click and type in gui applications
- control macos and windows apps via computer use
- automate apps that have no api or cli
- agent-driven ui testing on the desktop
- read and interact with on-screen app controls

## When to choose
- you need an agent to operate a desktop app that lacks an API, CLI, or MCP server
- you use the Pi agent framework and want computer-use tools
- you need cross-platform desktop UI automation from a single extension

## When to avoid
- the target app has a reliable direct API or MCP server integration
- you need headless automation on Linux without a graphical session
- you don't use Pi and want a standalone computer-use agent

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, computer-vision, workflow-automation, gui
- domain: desktop-applications, developer-tools
- platform: windows, cross-platform, rust
- tags: computer-use, ui-automation, pi-extension, accessibility-apis, desktop-agents, ai-agents, automation, macos, linux, nodejs

## Member repositories
- injaneity/pi-computer-use (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.731136+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:25:12.954373+00:00, confidence not recorded.
  - readme: https://github.com/injaneity/pi-computer-use (fetched 2026-08-28T04:05:34.731136+00:00, sha e553f58687a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.