The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Add CrewAI Usage doc (#2029)
Dev Khant1ebe5b643d19
diff --git a/docs/integrations/crewai.mdx b/docs/integrations/crewai.mdxnew file mode 100644index 000000000..decc0cc2b--- /dev/null+++ b/docs/integrations/crewai.mdx@@ -0,0 +1,166 @@+---+title: CrewAI+---++Build an AI system that combines CrewAI's agent-based architecture with Mem0's memory capabilities. This integration enables persistent memory across agent interactions and personalized task execution based on user history.++## Overview++In this guide, we'll create a CrewAI agent that:+1. Uses CrewAI to manage AI agents and tasks+2. Leverages Mem0 to store and retrieve conversation history+3. Creates personalized experiences based on stored user preferences++## Setup and Configuration++Install necessary libraries:++```bash+pip install crewai crewai-tools mem0ai+```++Import required modules and set up configurations:++<Note>Remember to get your API keys from [Mem0 Platform](https://app.mem0.ai), [OpenAI](https://platform.openai.com) and [Serper Dev](https://serper.dev) for search capabilities.</Note>++```python+import os+from mem0 import MemoryClient+from crewai import Agent, Task, Crew, Process+from crewai_tools import SerperDevTool++# Configuration+os.environ["MEM0_API_KEY"] = "your-mem0-api-key"+os.environ["OPENAI_API_KEY"] = "your-openai-api-key"+os.environ["SERPER_API_KEY"] = "your-serper-api-key"++# Initialize Mem0 client+client = MemoryClient()+```++## Store User Preferences++Set up initial conversation and preferences storage:++```python+def store_user_preferences(user_id: str, conversation: list):+ """Store user preferences from conversation history"""+ client.add(conversation, user_id=user_id)++# Example conversation storage+messages = [+ {+ "role": "user",+ "content": "Hi there! I'm planning a vacation and could use some advice.",+ },+ {+ "role": "assistant",+ "content": "Hello! I'd be happy to help with your vacation planning. What kind of destination do you prefer?",+ },+ {"role": "user", "content": "I am more of a beach person than a mountain person."},+ {+ "role": "assistant",+ "content": "That's interesting. Do you like hotels or airbnb?",+ },+ {"role": "user", "content": "I like airbnb more."},+]++store_user_preferences("crew_user_1", messages)+```++## Create CrewAI Agent++Define an agent with memory capabilities:++```python+def create_travel_agent():+ """Create a travel planning agent with search capabilities"""+ search_tool = SerperDevTool()++ return Agent(+ role="Personalized Travel Planner Agent",+ goal="Plan personalized travel itineraries",+ backstory="""You are a seasoned travel planner, known for your meticulous attention to detail.""",+ allow_delegation=False,+ memory=True,+ tools=[search_tool],+ )+```++## Define Tasks++Create tasks for your agent:++```python+def create_planning_task(agent, destination: str):+ """Create a travel planning task"""+ return Task(+ description=f"""Find places to live, eat, and visit in {destination}.""",+ expected_output=f"A detailed list of places to live, eat, and visit in {destination}.",+ agent=agent,+ )+```++## Set Up Crew++Configure the crew with memory integration:++```python+def setup_crew(agents: list, tasks: list):+ """Set up a crew with Mem0 memory integration"""+ return Crew(+ agents=agents,+ tasks=tasks,+ process=Process.sequential,+ memory=True,+ memory_config={+ "provider": "mem0",+ "config": {"user_id": "crew_user_1"},+ }+ )+```++## Main Execution Function++Implement the main function to run the travel planning system:++```python+def plan_trip(destination: str, user_id: str):+ # Create agent+ travel_agent = create_travel_agent()++ # Create task+ planning_task = create_planning_task(travel_agent, destination)++ # Setup crew+ crew = setup_crew([travel_agent], [planning_task])++ # Execute and return results+ return crew.kickoff()++# Example usage+if __name__ == "__main__":+ result = plan_trip("San Francisco", "crew_user_1")+ print(result)+```++## Key Features++1. **Persistent Memory**: Uses Mem0 to maintain user preferences and conversation history+2. **Agent-Based Architecture**: Leverages CrewAI's agent system for task execution+3. **Search Integration**: Includes SerperDev tool for real-world information retrieval+4. **Personalization**: Utilizes stored preferences for tailored recommendations++## Benefits++1. **Persistent Context & Memory**: Maintains user preferences and interaction history across sessions+2. **Flexible & Scalable Design**: Easily extendable with new agents, tasks and capabilities++## Conclusion++By combining CrewAI with Mem0, you can create sophisticated AI systems that maintain context and provide personalized experiences while leveraging the power of autonomous agents.++## Help++- For CrewAI documentation, visit [CrewAI Documentation](https://docs.crewai.com/)+- For Mem0 documentation, refer to the [Mem0 Platform](https://app.mem0.ai/)diff --git a/docs/mint.json b/docs/mint.jsonindex 5d02819c5..6d252531e 100644--- a/docs/mint.json+++ b/docs/mint.json@@ -208,6 +208,7 @@"group": "Integrations","pages": ["integrations/vercel-ai-sdk",+ "integrations/crewai","integrations/multion","integrations/autogen","integrations/langchain",