Agent Serialization

Serialize an agent with to_dict and from_dict, and persist versions with save and load.

agent_serialization.py

"""
Agent Serialization
=============================

Agent Serialization.
"""

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
agent_db = SqliteDb(db_file="tmp/agents.db")

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    id="serialization-demo-agent",
    name="Serialization Demo Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    db=agent_db,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    config = agent.to_dict()
    recreated = Agent.from_dict(config)

    version = agent.save()
    loaded = Agent.load(id=agent.id, db=agent_db, version=version)

    recreated.print_response("Say hello from a recreated agent.", stream=True)
    loaded.print_response("Say hello from a loaded agent.", stream=True)

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai sqlalchemy
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

   Save the code above as agent_serialization.py, then run:

   python agent_serialization.py
   

Full source: cookbook/02_agents/14_advanced/agent_serialization.py