A major challenge in volcanology is forecasting eruptions. Repeating earthquake sequences may precede volcanic eruptions or lava dome growth and collapse, providing an opportunity for short‐term eruption forecasting. I develop an automated repeating earthquake sequence detector and near‐real‐time alarm to send alerts when an in‐progress sequence is identified. The algorithm is based on a standard event detector (e.g., short‐term average/long‐term average [STA/LTA]) and subsequent correlation‐matching procedure that identifies repeating event sequences. A notification algorithm determines when a sequence is in progress and sends alerts. I use eruptions of three Alaskan volcanoes as case studies to test the alarm, implementing it both in retrospect and in real time during the 2016–2017 Bogoslof eruption. These case studies show that the alarm can be used to successfully detect and alert on sequences of repeating events in a timely manner.

You do not have access to this content, please speak to your institutional administrator if you feel you should have access.