Authorization notice. Atticus Mac is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Who it is forA Mac user working across two displays or several apps who wants to set up a workspace without clicking through each window.
The problemSetting up windows across displays and opening the right apps takes repeated clicks every time you start work.
The outcomeYour windows and apps are arranged by one spoken request, and repeated actions run again in a fraction of a second.
What you need first
- A Mac
- A Claude Pro or Max plan, or a local model server such as Ollama, LM Studio, llama.cpp or vLLM
- Claude Code installed (needed for the local model setup; the README says it does not require a Claude account in that case)
- Permission for Atticus to use the microphone and Accessibility controls
Steps
- Install Atticus from its GitHub repository and open it on your Mac.
- Hold ⌃ control, ⌥ option and space together, then say the layout you want, for example: "Code on my big screen, Chrome and Terminal on the laptop."
- Release the keys and let Atticus arrange the windows across your displays.
- Say "Open Spotify" or "Terminal on the left" to test instant commands, which run without AI.
- Repeat a window or app action once so Atticus learns it, then check that the next run is faster.
Prompt for your agent
Using the repo SaarthurR/atticus-mac, set up Atticus on a Mac so that the request "<your layout request>" arranges the named windows across the displays. Expected output: the windows are placed as described and the second run of the same request finishes faster. Verify by checking that the windows match the layout after one repeat of the request.
Caveat. Atticus needs a Claude plan or a local model server, and the README says it runs on your Claude Pro or Max plan through claude -p.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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