mcp-remote-macos-use vs open-codex-computer-use

MCP desktop automation compared

Both projects expose desktop interaction to compatible AI clients through MCP. mcp-remote-macos-use connects to a remote Mac over Screen Sharing, while open-codex-computer-use provides desktop automation across macOS, Linux, and Windows.

mcp-remote-macos-useopen-codex-computer-use
LanguagePythonSwift
LicenseMITMIT
Stars4902.3k
Forks56204
Last analyzedOct 9, 2026Oct 5, 2026

Key differences

  • mcp-remote-macos-use targets a remote Mac; open-codex-computer-use supports macOS, Linux, and Windows.
  • mcp-remote-macos-use uses Screen Sharing and requires it enabled on the target Mac; open-codex-computer-use describes accessibility-based controls and requires macOS permissions on that platform.
  • mcp-remote-macos-use is written in Python and documents Docker deployment; open-codex-computer-use is written in Swift and offers an npm launcher, CLI commands, and JavaScript automation.
  • mcp-remote-macos-use reports inactive development, with no commits in over a year and no release in the past year; open-codex-computer-use's supplied details do not describe its development activity.
  • mcp-remote-macos-use supports only Apple authentication protocol 30 according to its README; open-codex-computer-use's supplied details do not describe a remote-screen authentication protocol.
  • Both projects use the MIT license. The supplied project details list 490 stars for mcp-remote-macos-use and 2.3k for open-codex-computer-use.

Choose mcp-remote-macos-use if you…

  • need an AI client to interact with a remote Mac through Screen Sharing.
  • want a Docker-based server that does not require a separate background agent on the target Mac.
  • are prepared to assess the documented authentication protocol and inactive development before adopting it.
Read the mcp-remote-macos-use analysis →

Choose open-codex-computer-use if you…

  • need desktop automation across macOS, Linux, and Windows.
  • want CLI sequences or JavaScript-based automation through a terminal REPL.
  • are connecting clients such as Codex, Claude Code, Gemini CLI, or opencode to desktop workflows.
Read the open-codex-computer-use analysis →

Compare the numbers side by side, or add more projects

This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.