ocean database

README.md

@@ -204,3 +204,4 @@ In the context of swarm LLMs, one could consider an **Omni-Vector Embedding Data
 
 * Get baby agi set up with the autogpt instance as a tool
 
+* Integrate [Ocean](https://github.com/kyegomez/Ocean) vector db as the main embedding database for all the agents boss and or worker

swarms/agents/boss/babyagi_agent.py

@@ -48,7 +48,7 @@ tools = [
     Tool(
         name="AUTONOMOUS AGENT",
         func=agent.run,
-        description="Useful for when you need to spawn an autonomous agent instance as a worker to accomplish complex tasks"
+        description="Useful for when you need to spawn an autonomous agent instance as a worker to accomplish complex tasks, it can search the internet or spawn child multi-modality models to process and generate images and text or audio and so on"
     )
 ]