agent-cu vs Scalaris Atlas

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 Its repository states that it is no longer maintained and recommends Cua and Cua Driver instead.

Scalaris Atlas is a local deployment that turns a computer into a private host for AI models and serves them to compatible clients. It accepts OpenAI-compatible clients at localhost and exposes routes for chat completions, embeddings, and model lists. Atlas includes Pulsar, while its model manager lets users install their own models. The API covers a strict subset of the OpenAI HTTP surface; unimplemented endpoints return a typed 501 response. Models are served locally, and the maker says nothing leaves the machine. Egress is denied by default, and non-loopback binds are refused unless explicitly enabled. Atlas has no telemetry or phone-home behavior, according to the maker. Scalaris Toolbox installs and supervises it. Configuration is kept in one TOML file and reloads when changed. GPU exhaustion can trigger CPU fallback only with --allow-cpu. It is free forever at free and runs on macOS, Linux, and Windows.