agent-cu vs Computer Use OOTB

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 Its repository states that it is no longer maintained and recommends Cua and Cua Driver instead.

Computer Use OOTB is an open-source framework for automating desktop tasks through a graphical interface, using API-based or locally running models. It supports Windows and macOS and provides a Gradio interface without requiring Docker. Users can configure one model for a task or separate models for planning and computer control; listed options include Claude 3.5 Sonnet, GPT-4o, Qwen models, ShowUI, and UI-TARS. Local inference can avoid API costs, though a task using Claude 3.5 Computer Use may cost a few dollars. Setup requires Miniconda, Python 3.12 or newer, dependency installation, and starting the interface with `python app.py`. ShowUI local runs require a CUDA-enabled NVIDIA GPU with at least 6 GB of GPU memory on Windows, or an M1-or-newer Apple Silicon Mac with at least 16 GB unified RAM. A mobile browser can send commands to the computer running the software. The project uses an Apache-2.0 license. Its README warns that model actions can be unintended or harmful and recommends monitoring them; anyone with a public Gradio link may be able to control the computer.