Serve and embed

A data agent that only runs in a notebook helps one analyst. Behind an API, it answers questions from a Slack channel, a BI dashboard’s natural-language box, or an “explain this metric” widget in your product. AgentOS turns the agent into that API.

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses
from agno.os import AgentOS
from agno.tools.sql import SQLTools

agent = Agent(
    id="data-agent",
    model=OpenAIResponses(id="gpt-5.5"),
    db=PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    tools=[SQLTools(db_url="postgresql+psycopg://readonly@warehouse/analytics")],
    learning=True,
)

agent_os = AgentOS(agents=[agent])
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="data_agent:app", port=7777)

Any surface calls the same endpoint:

curl -X POST http://localhost:7777/agents/data-agent/runs \
  -F 'message=MRR by plan, last 6 months' \
  -F 'user_id=ab@acme.com' \
  -F 'session_id=q4-review' \
  -F 'stream=false'

Surfaces a data agent lives on

Surface	Shape
Slack channel	An interface maps a thread to a session; the team asks in plain English
Dashboard NL box	A widget posts the question and renders the answer plus its SQL
Scheduled digest	A cron job runs the agent and posts “yesterday’s numbers” every morning
Backend check	A pipeline calls the agent to sanity-check a metric before publishing

The serving model is identical to a product agent. The difference is what the agent does, not how it is served. Sessions still scope per user, so each analyst’s thread stays separate.

Learnings are shared, sessions are not

A data agent’s value compounds when corrections are shared across the team. Conversation threads stay scoped per user with user_id and session_id. Sharing learnings takes one change to the setup above. learning=True keeps learnings per user, so pass a knowledge base to LearningMachine instead. That enables the Learned Knowledge store, whose namespace defaults to "global", so a fix one analyst’s question triggered helps everyone.

from agno.knowledge import Knowledge
from agno.learn import LearningMachine
from agno.vectordb.pgvector import PgVector

knowledge = Knowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="warehouse_learnings",
    ),
)

agent = Agent(
    id="data-agent",
    # same model, db, and tools as above
    learning=LearningMachine(knowledge=knowledge),
)

State	Scope
Conversation thread	Per `user_id` and `session_id`
Learnings about the warehouse	Learned Knowledge store, shared `"global"` namespace by default

Next steps

Task	Guide
Add Slack or a browser surface	Interfaces
Lock down the endpoints	Security and auth

Welcome

Get Started

Features

Use Cases

Serve and embed

Surfaces a data agent lives on

Learnings are shared, sessions are not

Next steps

Developer Resources

​Surfaces a data agent lives on

​Learnings are shared, sessions are not

​Next steps

​Developer Resources

Surfaces a data agent lives on

Learnings are shared, sessions are not

Next steps

Developer Resources