DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to let a coding agent drive the Mac from a shell command with Jev Use

Call scripts/say.sh so an agent can open apps and use menus on the Mac.

Credentials. The TypeSafe API key is stored in the Keychain, and an agent that runs commands acts with your Mac permissions, so limit which commands it sends.

Who it is forA developer whose AI agent needs to act on desktop apps, such as opening an app or choosing a menu item, as part of a larger task.

The problemAgents cannot act on the desktop apps a developer uses, so each step needs manual work.

The outcomeAn agent sends a typed command through the shell and the Mac performs it, with the result logged.

What you need first

  • A Mac running macOS 14.2 or later
  • Xcode installed to build the app
  • A TypeSafe API key to save in the app's setup
  • Accessibility, microphone and speech permissions granted in setup

Steps

  1. Run bash build.sh with the app quit, then run open "$HOME/Applications/Desktop Voice.app".
  2. Complete setup, including the TypeSafe API key stored in the Keychain and the Accessibility permission.
  3. Run scripts/say.sh "Open Finder" to confirm the shell path works.
  4. Have the agent call scripts/say.sh with each command it needs.
  5. Check the result with log show --predicate 'subsystem == "local.jev-use"' --last 10m --info.

Prompt for your agent

In the jev-use repo on this Mac, run `scripts/say.sh "<command>"` where <command> is the desktop action to perform, such as "Open Finder". Expect the Mac to perform the action and the app to report DONE, BLOCKED or WAIT. Verify by running the log command above and confirming the logged effect matches the requested action.

Caveat. Each command sends your command, app and window names, and on-screen labels and values to TypeSafe, so do not point an agent at sensitive screens.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page