Skip to main content
OpenBunny has two reminder systems that work together to keep tasks on track.

​
Decision engine

The decision engine periodically reviews all open tasks using the LLM. It reads a configurable policy file (data/reminder-policy.md) and decides which tasks need attention, escalation, or follow-up. This runs on a timer and produces reminder actions that are logged for auditing.

​
Schedule engine

The schedule engine handles per-task reminders that users configure explicitly. Each task can have one or more reminder schedules.

​
Schedule types

TypeDescriptionExample
One-timeFires once at a specific date/time”Remind me on March 15 at 9am”
IntervalRepeats every N days, weeks, or months”Every 3 days”
WeeklyFires on a specific day and time each week”Every Monday at 10am”
MonthlyFires on a specific date each month”1st of every month at 9am”

​
Managing schedules

Schedules are managed through the REST API or the client UI: 
# Create a reminder
curl -X POST http://localhost:3100/tasks/123/schedules \
  -H "Content-Type: application/json" \
  -d '{"type": "interval", "interval_days": 3}'

# List reminders for a task
curl http://localhost:3100/tasks/123/schedules

# Delete a reminder
curl -X DELETE http://localhost:3100/tasks/123/schedules/456

​
Reminder policy

The reminder policy file (data/reminder-policy.md) is a markdown document that instructs the LLM on how to evaluate tasks for reminders. You can customize it to match your team’s workflow — for example, escalating high-priority tasks that have been idle for more than 24 hours.