agent-cu vs DesktopCtl
agent-cu
github.comDesktopCtl
desktopctl.comSide by side
| Figure | agent-cu | DesktopCtl |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Windows | Yes | — |
| macOS | Yes | Yes |
| Linux | Yes | — |
| Plans published | 1 | 1 |
| Spec score · AI Computer Use Agents | 8.1 (#3) | 7.6 (#13) |
| Automation | It supports batched commands and reusable YAML workflows. | Its CLI provides deterministic actions including clicking, typing, and waiting. |
| Installation | Precompiled binaries are provided for macOS Apple Silicon and Intel, Linux, and Windows, with npm, pnpm, yarn, and bun installation instructions. | 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. |
| Intended users | The README describes the tool as intended for AI agents such as Claude, Cursor, and Codex, local models, and humans. | The maker describes DesktopCtl as a tool for AI agents to control desktop applications, with any CLI-capable agent able to use it. |
| License | The project is released under the MIT license. | The homepage identifies DesktopCtl as open source under the MIT License. |
Plans
In their own words
agent-cu
agent-cu is a command-line tool for controlling desktop apps by clicking, typing, and reading interface information. It uses the accessibility tree that screen readers rely on to identify interface elements, then acts on them through references. Commands include snapshots, selectors, clicks, typing, scrolling, dragging, window management, and JSON output. Users can batch commands and reuse YAML workflows. The tool supports Electron apps through CDP, including Slack, Cursor, VS Code, Postman, Discord, and Notion. Its skill can be used with Claude Code, Cursor, Codex, Copilot, OpenCode, Cline, and 40+ other agents. agent-cu runs locally on macOS, Linux, and Windows; precompiled binaries are available for macOS Apple Silicon and Intel, Linux, and Windows. Installation instructions cover npm, pnpm, yarn, and bun. It requires explicit operating-system accessibility permissions to read and control apps. The project is free and MIT licensed. Its repository states that it is no longer maintained and recommends Cua and Cua Driver instead.
DesktopCtl
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.