diff --git a/config.template b/config.template
index 92aa9cf..07af02c 100644
--- a/config.template
+++ b/config.template
@@ -60,6 +60,9 @@ ollama = False
 # ollamaModel = llama3.1
 # server instance to use (defaults to local machine install)
 ollamaHostName = http://localhost:11434
+# Produce LLM replies to messages that aren't commands?
+# If False, the LLM only replies to the "ask:" and "askai" commands.
+llmReplyToNonCommands = True
 
 # StoreForward Enabled and Limits
 StoreForward = True
diff --git a/mesh_bot.py b/mesh_bot.py
index 0d142d0..55ac24d 100755
--- a/mesh_bot.py
+++ b/mesh_bot.py
@@ -1243,7 +1243,7 @@ def onReceive(packet, interface):
                             playingGame = False
 
                     if not playingGame:
-                        if llm_enabled:
+                        if llm_enabled and llmReplyToNonCommands:
                             # respond with LLM
                             llm = handle_llm(message_from_id, channel_number, rxNode, message_string, publicChannel)
                             send_message(llm, channel_number, message_from_id, rxNode)
diff --git a/modules/settings.py b/modules/settings.py
index ce269d6..4e6aeaa 100644
--- a/modules/settings.py
+++ b/modules/settings.py
@@ -222,6 +222,7 @@ try:
     llm_enabled = config['general'].getboolean('ollama', False) # https://ollama.com
     llmModel = config['general'].get('ollamaModel', 'gemma2:2b') # default gemma2:2b
     ollamaHostName = config['general'].get('ollamaHostName', 'http://localhost:11434') # default localhost
+    llmReplyToNonCommands = config['general'].getboolean('llmReplyToNonCommands', True)
     # emergency response
     emergency_responder_enabled = config['emergencyHandler'].getboolean('enabled', False)
     emergency_responder_alert_channel = config['emergencyHandler'].getint('alert_channel', 2) # default 2