diff --git a/swarms/agents/multi_modal_agent.py b/swarms/agents/multi_modal_agent.py
index be6831cd..31de5ece 100644
--- a/swarms/agents/multi_modal_agent.py
+++ b/swarms/agents/multi_modal_agent.py
@@ -1,3 +1,5 @@
+from agent_protocol import Agent, Step, Task
+
 from swarms.workers.multi_modal_workers.multi_modal_agent import MultiModalVisualAgent
 
 class MultiModalVisualAgent:
@@ -6,8 +8,27 @@ class MultiModalVisualAgent:
             agent: MultiModalVisualAgent
         ):
         self.agent = agent
+        self.plan = plan
     
-    def _run(self, text: str) -> str:
+    async def run(self, text: str) -> str:
         #run the multi-modal visual agent with the give task
         return self.agent.run_text(text)
+    
+    async def __call__(self, text: str) -> str:
+        return self.agent.run(text)
+    
+    async def plan(self, step: Step) -> Step:
+        task = Agent
+        pass
 
+    async def task_handler(self, task: Task):
+        await self.agent.run()
+    
+    async def step_handler(self, step: Step):
+        if step.name == "plan":
+            await self.plan(step)
+        else:
+            await self.agent.run(step)
+
+        return step
+    
diff --git a/swarms/agents/omni_modal_agent.py b/swarms/agents/omni_modal_agent.py
index a0d183a2..5e842dd6 100644
--- a/swarms/agents/omni_modal_agent.py
+++ b/swarms/agents/omni_modal_agent.py
@@ -3,11 +3,11 @@ from swarms.workers.multi_modal_workers.omni_agent.omni_chat import chat_hugging
 
 class OmniModalAgent:
     def __init__(
-            self, 
-            api_key, 
-            api_endpoint, 
-            api_type
-        ):
+        self, 
+        api_key, 
+        api_endpoint, 
+        api_type
+    ):
         self.api_key = api_key
         self.api_endpoint = api_endpoint
         self.api_type = api_type