diff --git a/cli.py b/cli.py
index 16ce554e..7f2b160b 100755
--- a/cli.py
+++ b/cli.py
@@ -1722,6 +1722,8 @@ class HermesCLI:
             self._show_gateway_status()
         elif cmd_lower == "/verbose":
             self._toggle_verbose()
+        elif cmd_lower == "/compress":
+            self._manual_compress()
         else:
             # Check for skill slash commands (/gif-search, /axolotl, etc.)
             base_cmd = cmd_lower.split()[0]
@@ -1763,6 +1765,41 @@ class HermesCLI:
         }
         self.console.print(labels.get(self.tool_progress_mode, ""))
 
+    def _manual_compress(self):
+        """Manually trigger context compression on the current conversation."""
+        if not self.conversation_history or len(self.conversation_history) < 4:
+            print("(._.) Not enough conversation to compress (need at least 4 messages).")
+            return
+
+        if not self.agent:
+            print("(._.) No active agent -- send a message first.")
+            return
+
+        if not self.agent.compression_enabled:
+            print("(._.) Compression is disabled in config.")
+            return
+
+        original_count = len(self.conversation_history)
+        try:
+            from agent.model_metadata import estimate_messages_tokens_rough
+            approx_tokens = estimate_messages_tokens_rough(self.conversation_history)
+            print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens)...")
+
+            compressed, new_system = self.agent._compress_context(
+                self.conversation_history,
+                self.agent._cached_system_prompt or "",
+                approx_tokens=approx_tokens,
+            )
+            self.conversation_history = compressed
+            new_count = len(self.conversation_history)
+            new_tokens = estimate_messages_tokens_rough(self.conversation_history)
+            print(
+                f"  ✅ Compressed: {original_count} → {new_count} messages "
+                f"(~{approx_tokens:,} → ~{new_tokens:,} tokens)"
+            )
+        except Exception as e:
+            print(f"  ❌ Compression failed: {e}")
+
         if self.verbose:
             logging.getLogger().setLevel(logging.DEBUG)
             for noisy in ('openai', 'openai._base_client', 'httpx', 'httpcore', 'asyncio', 'hpack', 'grpc', 'modal'):
diff --git a/hermes_cli/commands.py b/hermes_cli/commands.py
index b7e5a621..5de1c6bc 100644
--- a/hermes_cli/commands.py
+++ b/hermes_cli/commands.py
@@ -26,6 +26,7 @@ COMMANDS = {
     "/skills": "Search, install, inspect, or manage skills from online registries",
     "/platforms": "Show gateway/messaging platform status",
     "/verbose": "Cycle tool progress display: off → new → all → verbose",
+    "/compress": "Manually compress conversation context (flush memories + summarize)",
     "/quit": "Exit the CLI (also: /exit, /q)",
 }