- Home
- AI Computer Use Agents
- DesktopCtl
DesktopCtl
What it is
DesktopCtl is a free, open-source launcher and command-line tool for AI agents to interact with desktop applications. It lets CLI-capable agents observe a computer’s screen and use its mouse and keyboard, without app integrations or APIs. Users can bring any AI model, including local LLMs. Local GPU-accelerated text recognition and computer vision capture the interface and extract structured content; the CLI provides deterministic actions such as clicking, typing, and waiting. The macOS launcher offers keyboard-first navigation, active-window context, and ways to run or resume sessions with multiple local agents. The maker says 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 OS-level permissions are granted only to DesktopCtl. It is licensed under MIT and currently supports macOS on Apple Silicon only. Release builds use a local ad-hoc signature and are not Developer ID signed or notarized.
For and against
For
- Works with any desktop app without integrations or APIs.
- Supports local LLMs and other AI models.
- Screen understanding runs locally, according to the maker.
- Open source under the MIT License.
Against
- Currently supports macOS on Apple Silicon only.
- Release builds are not Developer ID signed or notarized.
- Use requires granting DesktopCtl operating-system permissions.
The verdict
DesktopCtl pairs local screen understanding with command-line desktop actions and a macOS launcher. Its platform support is limited to Apple Silicon Macs, and its release builds lack Developer ID signing and notarization.
Who it suits
DesktopCtl may suit people who want CLI-capable AI agents to control desktop apps without app-specific integrations. It is intended for macOS on Apple Silicon.
Plans and prices
Free and open source
No integrations required · works with any desktop app
Read 4 Oct 2026 · desktopctl.com
On the record
- 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.desktopctl.com · read 4 Oct 2026
- Agent support
- It supports agents that can use a CLI and lets users bring any AI model, including local LLMs.desktopctl.com · read 4 Oct 2026
- App compatibility
- It works with any desktop app and requires no app integrations or APIs.desktopctl.com · read 4 Oct 2026
- Automation
- Its CLI provides deterministic actions including clicking, typing, and waiting.desktopctl.com · read 4 Oct 2026
- 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.github.com · read 4 Oct 2026
- 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.desktopctl.com · read 4 Oct 2026
- Launcher
- The macOS launcher provides keyboard-first navigation, active-window context, and the ability to run and resume sessions with multiple local agents.desktopctl.com · read 4 Oct 2026
- License
- The homepage identifies DesktopCtl as open source under the MIT License.desktopctl.com · read 4 Oct 2026
- Platform support
- The maker’s repository says DesktopCtl currently supports macOS on Apple Silicon only.github.com · read 4 Oct 2026
- Privacy
- The maker says computer vision and text recognition run locally and screenshots stay local by default rather than being shared with AI agents.desktopctl.com · read 4 Oct 2026
- Purpose
- DesktopCtl is a local launcher and CLI for AI agents to observe and control a computer using its screen, mouse, and keyboard.desktopctl.com · read 4 Oct 2026
- Signing
- The repository says release builds use a local ad-hoc signature and are not Developer ID signed or notarized.github.com · read 4 Oct 2026
- UI perception
- It uses local GPU-accelerated text recognition and computer vision to capture the UI and extract structured content.desktopctl.com · read 4 Oct 2026
