Examples
- Examples
- Getting Started
- Agents
- Teams
- Workflows
- Applications
- Streamlit Apps
- Evals
Agent Concepts
- Reasoning
- Multimodal
- RAG
- User Control Flows
- Knowledge
- Memory
- Built-in Memory
- Standalone Memory Operations
- Persistent Memory with SQLite
- Custom Memory Creation
- Memory Search
- Agent With Memory
- Agentic Memory
- Agent with Session Summaries
- Multiple Agents Sharing Memory
- Custom Memory
- Multi-User Multi-Session Chat
- Multi-User Multi-Session Chat Concurrent
- Memory References
- Session Summary References
- Mem0 Memory
- DB
- Async
- Hybrid Search
- Storage
- Tools
- Vector Databases
- Context
- Embedders
- Agent State
- Observability
- Miscellaneous
Models
- Anthropic
- AWS Bedrock
- AWS Bedrock Claude
- Azure AI Foundry
- Azure OpenAI
- Cerebras
- Cerebras OpenAI
- Cohere
- DeepInfra
- DeepSeek
- Fireworks
- Gemini
- Groq
- Hugging Face
- IBM
- LM Studio
- LiteLLM
- LiteLLM OpenAI
- Meta
- Mistral
- NVIDIA
- Ollama
- OpenAI
- Perplexity
- Together
- XAI
- Vercel
- vLLM
Memory
Agentic Memory
This example shows you how to use persistent memory with an Agent.
During each run the Agent can create/update/delete user memories.
To enable this, set enable_agentic_memory=True
in the Agent config.
Code
cookbook/agent_concepts/memory/07_agentic_memory.py
Copy
Ask AI
from agno.agent.agent import Agent
from agno.memory.v2.db.sqlite import SqliteMemoryDb
from agno.memory.v2.memory import Memory
from agno.models.openai import OpenAIChat
from rich.pretty import pprint
memory_db = SqliteMemoryDb(table_name="memory", db_file="tmp/memory.db")
# No need to set the model, it gets set by the agent to the agent's model
memory = Memory(db=memory_db)
# Reset the memory for this example
memory.clear()
john_doe_id = "john_doe@example.com"
agent = Agent(
model=OpenAIChat(id="gpt-4o-mini"),
memory=memory,
enable_agentic_memory=True,
)
agent.print_response(
"My name is John Doe and I like to hike in the mountains on weekends.",
stream=True,
user_id=john_doe_id,
)
agent.print_response("What are my hobbies?", stream=True, user_id=john_doe_id)
memories = memory.get_user_memories(user_id=john_doe_id)
print("Memories about John Doe:")
pprint(memories)
agent.print_response(
"Remove all existing memories of me.",
stream=True,
user_id=john_doe_id,
)
memories = memory.get_user_memories(user_id=john_doe_id)
print("Memories about John Doe:")
pprint(memories)
agent.print_response(
"My name is John Doe and I like to paint.", stream=True, user_id=john_doe_id
)
memories = memory.get_user_memories(user_id=john_doe_id)
print("Memories about John Doe:")
pprint(memories)
agent.print_response(
"I don't pain anymore, i draw instead.", stream=True, user_id=john_doe_id
)
memories = memory.get_user_memories(user_id=john_doe_id)
print("Memories about John Doe:")
pprint(memories)
Usage
1
Create a virtual environment
Open the Terminal
and create a python virtual environment.
Copy
Ask AI
python3 -m venv .venv
source .venv/bin/activate
2
Set your API key
Copy
Ask AI
export GOOGLE_API_KEY=xxx
3
Install libraries
Copy
Ask AI
pip install -U agno google-generativeai
4
Run Example
Copy
Ask AI
python cookbook/agent_concepts/memory/07_agentic_memory.py
Was this page helpful?
Assistant
Responses are generated using AI and may contain mistakes.