DesktopCtl
desktopctl.com
What it is
DesktopCtl is a macOS launcher and command-line interface for AI agents that observe and control a computer through its screen, mouse, and keyboard. It works with any desktop application without app integrations or APIs, and accepts any CLI-capable agent and AI model, including local LLMs. Local GPU-accelerated text recognition and computer vision capture interface content and extract structured information. Deterministic CLI actions include clicking, typing, and waiting. The keyboard-first launcher shows active-window context and can run or resume sessions with multiple local agents. The maker says recognition runs locally, screenshots remain local by default, and a visual indicator appears during screen, mouse, or keyboard access. Operating-system permissions are granted only to DesktopCtl. It is open source under the MIT License, deployed locally, free to use, and currently supports macOS on Apple Silicon only. Release builds use an ad-hoc signature and are not Developer ID signed or notarized.
Spec sheet
- Purpose
- DesktopCtl is a local launcher and CLI for AI agents to observe and control a computer using its screen, mouse, and keyboard.Read 4 Oct 2026 · desktopctl.com
- 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.Read 4 Oct 2026 · desktopctl.com
- Privacy
- The maker says computer vision and text recognition run locally and screenshots stay local by default rather than being shared with AI agents.Read 4 Oct 2026 · desktopctl.com
- License
- The homepage identifies DesktopCtl as open source under the MIT License.Read 4 Oct 2026 · desktopctl.com
- 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.Read 4 Oct 2026 · desktopctl.com
- Agent support
- It supports agents that can use a CLI and lets users bring any AI model, including local LLMs.Read 4 Oct 2026 · desktopctl.com
- App compatibility
- It works with any desktop app and requires no app integrations or APIs.Read 4 Oct 2026 · desktopctl.com
- Automation
- Its CLI provides deterministic actions including clicking, typing, and waiting.Read 4 Oct 2026 · desktopctl.com
- 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.Read 4 Oct 2026 · github.com
- Launcher
- The macOS launcher provides keyboard-first navigation, active-window context, and the ability to run and resume sessions with multiple local agents.Read 4 Oct 2026 · desktopctl.com
- Platform support
- The maker’s repository says DesktopCtl currently supports macOS on Apple Silicon only.Read 4 Oct 2026 · github.com
- Signing
- The repository says release builds use a local ad-hoc signature and are not Developer ID signed or notarized.Read 4 Oct 2026 · github.com
- UI perception
- It uses local GPU-accelerated text recognition and computer vision to capture the UI and extract structured content.Read 4 Oct 2026 · desktopctl.com
Plans and prices
Strong points and limits
Strong points
- Works with desktop apps without integrations or APIs
- Supports any CLI-capable agent and AI model
- Local vision and text recognition
- Deterministic clicking, typing, and waiting
- Free and MIT-licensed open source
Limits
- Supports macOS on Apple Silicon only
- Release builds are not notarized
- Requires operating-system accessibility permissions
Who it suits
DesktopCtl suits users who want local AI-agent control of desktop applications through a CLI. It is intended for CLI-capable agents and users bringing their own models, including local LLMs, on Apple Silicon Macs.
Verdict
DesktopCtl combines local screen understanding with deterministic desktop control for CLI-based AI agents. Its macOS-only Apple Silicon support and non-notarized releases are important constraints.
Where Specifiction places it
- AI Computer Use Agents#13 of 247.6