Async Postgres for Team

Store team sessions and run history asynchronously in PostgreSQL with AsyncPostgresDb.

AsyncPostgresDb stores a Team's sessions and run history asynchronously in PostgreSQL. Use async Team methods such as arun() and aprint_response().

Usage

Start in a virtual environment and set the model key before running the example.

Set OpenAI Key

Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.

export OPENAI_API_KEY=sk-***

Install the sqlalchemy, psycopg, openai, and ddgs packages:

uv pip install agno "sqlalchemy[asyncio]" "psycopg[binary]" openai ddgs

Run PostgreSQL

Install Docker Desktop, then start PostgreSQL with pgvector on port 5532:

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
async_postgres_for_team.py
import asyncio
from typing import List

from agno.agent import Agent
from agno.db.postgres import AsyncPostgresDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.websearch import WebSearchTools
from pydantic import BaseModel

db_url = "postgresql+psycopg_async://ai:ai@localhost:5532/ai"
db = AsyncPostgresDb(db_url=db_url)


class Article(BaseModel):
    title: str
    summary: str
    reference_links: List[str]


hn_researcher = Agent(
    name="HackerNews Researcher",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Gets top stories from HackerNews.",
    tools=[HackerNewsTools()],
)

web_searcher = Agent(
    name="Web Searcher",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Searches the web for information on a topic",
    tools=[WebSearchTools()],
    add_datetime_to_context=True,
)

hn_team = Team(
    name="HackerNews Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[hn_researcher, web_searcher],
    db=db,
    instructions=[
        "First, search HackerNews for what the user is asking about.",
        "Then, ask the web searcher to search for each story to get more information.",
        "Finally, summarize each story and include its reference links.",
    ],
    output_schema=Article,
    markdown=True,
    show_members_responses=True,
)


async def main():
    try:
        await hn_team.aprint_response(
            "Write an article about the top 2 stories on HackerNews"
        )
    finally:
        await db.close()


if __name__ == "__main__":
    asyncio.run(main())

Parameters

ParameterTypeDefaultDescription
idOptional[str]-The ID of the database instance. UUID by default.
db_urlOptional[str]-The database URL to connect to.
db_engineOptional[AsyncEngine]-The SQLAlchemy async database engine to use.
db_schemaOptional[str]-The database schema to use.
session_tableOptional[str]-Name of the table to store Agent, Team and Workflow sessions.
runs_tableOptional[str]-Name of the table to store the runs of each session.
memory_tableOptional[str]-Name of the table to store memories.
metrics_tableOptional[str]-Name of the table to store metrics.
eval_tableOptional[str]-Name of the table to store evaluation runs data.
knowledge_tableOptional[str]-Name of the table to store knowledge content.
traces_tableOptional[str]-Name of the table to store traces.
spans_tableOptional[str]-Name of the table to store spans.
versions_tableOptional[str]-Name of the table to store schema versions.
components_tableOptional[str]-Name of the table to store components.
learnings_tableOptional[str]-Name of the table to store learnings.
schedules_tableOptional[str]-Name of the table to store cron schedules.
schedule_runs_tableOptional[str]-Name of the table to store schedule run history.
job_tableOptional[str]-Name of the table to store durable background run jobs.
approvals_tableOptional[str]-Name of the table to store human approval requests.
auth_tokens_tableOptional[str]-Name of the table to store OAuth tokens for external services.
service_accounts_tableOptional[str]-Name of the table to store service accounts.
create_schemaboolTrueWhether to create the database schema if it doesn't exist. Set to False when the schema is managed externally.

Run the Example

Save the code as async_postgres_for_team.py, complete the prerequisites above, then run:

python async_postgres_for_team.py