diff --git a/example.py b/example.py
index 70de7b80..a41f0995 100644
--- a/example.py
+++ b/example.py
@@ -20,4 +20,6 @@ I want it to have neumorphism-style. Serve it on port 4500.
 """
 
 # Run Swarms
-swarm.run_swarms(objective)
\ No newline at end of file
+task = swarm.run_swarms(objective)
+
+print(task)
\ No newline at end of file
diff --git a/swarms/agents/workers/auto_agent.py b/swarms/agents/workers/auto_agent.py
index 7cc1d1ff..199d0d08 100644
--- a/swarms/agents/workers/auto_agent.py
+++ b/swarms/agents/workers/auto_agent.py
@@ -32,19 +32,9 @@ from langchain.embeddings import OpenAIEmbeddings
 
 from langchain.tools.human.tool import HumanInputRun
 # from swarms.agents.workers.auto_agent import 
-from agents.workers.multi_modal import MultiModalVisualAgent
-from tools.main import Terminal, CodeWriter, CodeEditor, process_csv, WebpageQATool
+from swarms.agents.workers.visual_agent import multimodal_agent_tool
+from swarms.tools.main import Terminal, CodeWriter, CodeEditor, process_csv, WebpageQATool
 
-class MultiModalVisualAgentTool(BaseTool):
-    name = "multi_visual_agent"
-    description = "Multi-Modal Visual agent tool"
-
-    def __init__(self, agent: MultiModalVisualAgent):
-        self.agent = agent
-    
-    def _run(self, text: str) -> str:
-        #run the multi-modal visual agent with the give task
-        return self.agent.run_text(text)
 
 
 class WorkerAgent:
@@ -65,9 +55,6 @@ class WorkerAgent:
         query_website_tool = WebpageQATool(qa_chain=load_qa_with_sources_chain(llm))
         web_search = DuckDuckGoSearchRun()
 
-        multimodal_agent = MultiModalVisualAgent()
-        multimodal_agent_tool = MultiModalVisualAgentTool(multimodal_agent)
-
         tools = [
             web_search,
             WriteFileTool(root_dir="./data"),
@@ -102,7 +89,7 @@ class WorkerAgent:
         # worker_agent = WorkerAgent(objective, api_key)
 
     
-objective = "Your objective here"
+# objective = "Your objective here"
 
 
-worker_agent = WorkerAgent(objective)
+# worker_agent = WorkerAgent(objective)
diff --git a/swarms/agents/workers/multi_modal/__init__.py b/swarms/agents/workers/multi_modal/__init__.py
new file mode 100644
index 00000000..45040ecd
--- /dev/null
+++ b/swarms/agents/workers/multi_modal/__init__.py
@@ -0,0 +1,2 @@
+from swarms.agents.workers.multi_modal.multi_modal_agent import MultiModalVisualAgent
+from swarms.agents.workers.multi_modal.omni_agent import chat_huggingface
\ No newline at end of file
diff --git a/swarms/agents/workers/multi_modal.py b/swarms/agents/workers/multi_modal/multi_modal_agent.py
similarity index 100%
rename from swarms/agents/workers/multi_modal.py
rename to swarms/agents/workers/multi_modal/multi_modal_agent.py
diff --git a/swarms/agents/workers/visual_agent.py b/swarms/agents/workers/visual_agent.py
new file mode 100644
index 00000000..5585df52
--- /dev/null
+++ b/swarms/agents/workers/visual_agent.py
@@ -0,0 +1,17 @@
+from swarms.agents.workers.multi_modal.multi_modal_agent import MultiModalVisualAgent
+from langchain.tools import BaseTool
+
+class MultiModalVisualAgentTool(BaseTool):
+    name = "multi_visual_agent"
+    description = "Multi-Modal Visual agent tool"
+
+    def __init__(self, agent: MultiModalVisualAgent):
+        self.agent = agent
+    
+    def _run(self, text: str) -> str:
+        #run the multi-modal visual agent with the give task
+        return self.agent.run_text(text)
+
+
+multimodal_agent = MultiModalVisualAgent()
+multimodal_agent_tool = MultiModalVisualAgentTool(multimodal_agent)
\ No newline at end of file