diff --git a/nix/agent-modules/mcp.nix b/nix/agent-modules/mcp.nix
index 1a02336c..d41e92fb 100644
--- a/nix/agent-modules/mcp.nix
+++ b/nix/agent-modules/mcp.nix
@@ -353,6 +353,11 @@ in
         # no stdio fallback — same reasoning as `hive-mcp-http` below.
         Restart = "always";
         RestartSec = 3;
+        # systemd's default `stop` tears the whole unit down when the kernel
+        # kills *any* process in its cgroup, so one OOM-killed task would
+        # take every running sibling task with it. `continue` scopes the
+        # loss to the process the kernel chose.
+        OOMPolicy = "continue";
         User = userName;
         Group = userName;
       };
diff --git a/nix/module-eval/agent-memory.nix b/nix/module-eval/agent-memory.nix
index e1377e9c..dd1b09dc 100644
--- a/nix/module-eval/agent-memory.nix
+++ b/nix/module-eval/agent-memory.nix
@@ -30,6 +30,7 @@ let
 
   agentUncapped = agent { };
 
+  agentBashDaemon = machine: machine.systemd.services.hive-bash-daemon;
   agentSubagentDaemon = machine: machine.systemd.services.hive-subagent-daemon;
   cases = [
     {
@@ -82,6 +83,12 @@ let
       name = "one subagent losing the OOM draw does not stop the daemon";
       ok = (agentSubagentDaemon agentUncapped).serviceConfig.OOMPolicy == "continue";
     }
+    {
+      # Each bash task is a process in the daemon's cgroup; under `stop` one
+      # OOM-killed task would end every running sibling task.
+      name = "one bash task losing the OOM draw does not stop the daemon";
+      ok = (agentBashDaemon agentUncapped).serviceConfig.OOMPolicy or null == "continue";
+    }
   ];
 in
 runGroup "agent-memory" cases