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

How to schedule a saved prompt to run as a new session with Pi Agent Desktop

Run a saved prompt hourly, daily, weekly, on a cron expression, or once, with notifications.

Who it is forA developer who wants a recurring check, such as a daily summary of a project, run by the agent without starting it by hand.

The problemRepeated agent checks are easy to forget when each one has to be started manually in a new session.

The outcomeThe saved prompt runs on the chosen schedule in a new session, and the user is notified when a run succeeds or fails.

What you need first

  • A supported machine: Apple Silicon Mac on macOS 11 or later, Windows 10/11 x64, or Linux x64 with WebKitGTK 4.1 and GTK 3
  • Pi sessions or Pi model keys on this machine (optional, only needed to see existing history)
  • For the proxy use case: Node.js 22 and npm, plus a running HTTP proxy address

Steps

  1. Install and open Pi Agent from the releases page at https://github.com/abcwyc/pi-agent-desktop/releases.
  2. Save the prompt you want to repeat and open the Scheduled tasks area.
  3. Choose the schedule: hourly, daily, weekly, a custom cron expression, or once.
  4. Keep the default read-only tools unless the task needs more access.
  5. Keep the app open, since scheduled tasks run while the app is open, even with its window hidden, and check the notification for each run.

Prompt for your agent

Using the abcwyc/pi-agent-desktop README, describe how to set up a daily scheduled task that runs a saved prompt for <project-name>. Expected output: the schedule settings and the default tool mode. Verify that the README states the app must stay open for runs to happen.

Caveat. Scheduled runs only happen while Pi Agent is open, so a machine that is closed or asleep will miss runs except for a single catch-up run after sleep.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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