Update From Lifespan

Register a second agent and resync AgentOS from a FastAPI lifespan function.

update_from_lifespan.py

"""
Update From Lifespan
====================

Demonstrates update from lifespan.
"""

from contextlib import asynccontextmanager

from agno.agent.agent import Agent
from agno.db.postgres.postgres import PostgresDb
from agno.os import AgentOS
from agno.tools.mcp import MCPTools

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

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

# First agent. We will add this to the AgentOS on initialization.
agent1 = Agent(
    name="First Agent",
    markdown=True,
)

# Second agent. We will add this to the AgentOS in the lifespan function.
agent2 = Agent(
    id="second-agent",
    name="Second Agent",
    tools=[MCPTools(transport="streamable-http", url="https://docs.agno.com/mcp")],
    markdown=True,
    db=db,
)


# Lifespan function receiving the AgentOS instance as parameter.
@asynccontextmanager
async def lifespan(app, agent_os):
    # Add the new Agent
    agent_os.agents.append(agent2)

    # Resync the AgentOS
    agent_os.resync(app=app)

    yield


# Setup our AgentOS with the lifespan function and the first agent.
agent_os = AgentOS(
    lifespan=lifespan,
    agents=[agent1],
    mcp_server=True,
)

# Get our app.
app = agent_os.get_app()

# Serve the app.
# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    agent_os.serve(app="update_from_lifespan: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[mcp,os]" "psycopg[binary]" 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 update_from_lifespan.py, then run:

   python update_from_lifespan.py
   

Full source: cookbook/05_agent_os/customize/update_from_lifespan.py