Checkpointing

Enable tool-batch checkpointing on a research agent served through AgentOS with Postgres.

checkpointing.py

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.tools.websearch import WebSearchTools

db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")

research_agent = Agent(
    name="Research Agent",
    checkpoint="tool-batch",
    id="research_agent",
    model=OpenAIChat(id="gpt-5.2"),
    instructions=["You are a research agent"],
    tools=[WebSearchTools()],
    db=db,
)

agent_os = AgentOS(
    id="checkpointing-demo",
    name="Checkpointing Demo",
    description="A demo of checkpointing in AgentOS",
    agents=[research_agent],
)

app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="checkpointing:app", reload=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[os]" "psycopg[binary]" ddgs openai
   
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 PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run the example

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

   python checkpointing.py
   

Full source: cookbook/05_agent_os/advanced_demo/checkpointing.py