DesktopCtl
desktopctl.com
- Free plan
- macOS
What DesktopCtl is
DesktopCtl is a free, open-source macOS launcher and CLI that lets AI agents observe and control a computer through its screen, mouse, and keyboard. It works with desktop apps without app-specific integrations or APIs, and supports CLI-capable agents using any AI model, including local LLMs. Local GPU-accelerated text recognition and computer vision capture the interface and extract structured content. The CLI offers deterministic actions such as clicking, typing, and waiting. The launcher adds keyboard-first navigation, active-window context, and ways to run or resume sessions with multiple local agents. The maker says screen recognition runs locally and screenshots stay local by default rather than being shared with agents. A visual indicator appears when an agent accesses the screen, mouse, or keyboard, and operating-system permissions are granted only to DesktopCtl. The software uses the MIT License and runs locally. The repository says current support is limited to macOS on Apple Silicon. Release builds use a local ad-hoc signature and are not Developer ID signed or notarized.
Who it suits
DesktopCtl suits people using CLI-capable AI agents to control desktop applications, including those bringing a local model. It is for users with macOS on Apple Silicon.
Good to know, and what to watch
- Works with desktop apps without app integrations
- Supports any AI model, including local LLMs
- Screen recognition runs locally
- Shows an indicator during agent access
- Currently supports macOS on Apple Silicon only
- Release builds are not Developer ID signed or notarized
Plans
Every plan and priceFree and open source
Free plan
The verdict
DesktopCtl gives CLI-capable agents a local way to interpret and operate desktop interfaces. Its platform support is limited to Apple Silicon Macs, and release builds are not notarized.
What the maker publishes
- Access controls
- The maker says a visual indicator appears when the agent accesses the screen, mouse, or keyboard, and OS-level permissions are granted only to DesktopCtl. source
- Agent support
- It supports agents that can use a CLI and lets users bring any AI model, including local LLMs. source
- App compatibility
- It works with any desktop app and requires no app integrations or APIs. source
- Automation
- Its CLI provides deterministic actions including clicking, typing, and waiting. source
- Installation
- The repository gives an install command that downloads the latest release and places the CLI at ~/.local/bin/desktopctl and the app at ~/Applications/DesktopCtl.app. source
- Intended users
- The maker describes DesktopCtl as a tool for AI agents to control desktop applications, with any CLI-capable agent able to use it. source
- Launcher
- The macOS launcher provides keyboard-first navigation, active-window context, and the ability to run and resume sessions with multiple local agents. source
- License
- The homepage identifies DesktopCtl as open source under the MIT License. source
- Platform support
- The maker’s repository says DesktopCtl currently supports macOS on Apple Silicon only. source
- Privacy
- The maker says computer vision and text recognition run locally and screenshots stay local by default rather than being shared with AI agents. source
- Purpose
- DesktopCtl is a local launcher and CLI for AI agents to observe and control a computer using its screen, mouse, and keyboard. source
- Signing
- The repository says release builds use a local ad-hoc signature and are not Developer ID signed or notarized. source
- UI perception
- It uses local GPU-accelerated text recognition and computer vision to capture the UI and extract structured content. source
Checked against the maker's pages on 4 Oct 2026.