Scheduling

AgentOS comes with a built-in cron-style scheduler. Use it to run morning briefings, daily triage, weekly digests, hourly health checks. Agents can also manage their own schedules through tool calls. Registered schedules live in the AgentOS database (agno_schedules table). The scheduler runs in the same FastAPI process as your agents. No separate worker.

from agno.os import AgentOS

agent_os = AgentOS(
    agents=[agent],
    db=db,
    scheduler=True,
    scheduler_poll_interval=15,    # check for due jobs every N seconds
)

The scheduler polls agno_schedules every scheduler_poll_interval seconds, fires due jobs, retries failures up to each schedule’s max_retries, and persists state. The scheduler fires a due job by calling its endpoint over HTTP, against http://127.0.0.1:7777 by default. That matches the default serve() port. Set scheduler_base_url to match when you serve on a different host or port; otherwise schedules fire against the wrong URL.

Two ways to create schedules

Pattern	How
Agent Managed	`SchedulerTools` lets an agent create, list, inspect, delete, enable, disable, and review runs for schedules. Creating a schedule with an existing name updates it.
Manually Registered	Schedules created in code, registered at startup.

Agent Managed

Give an agent SchedulerTools and it can schedule its own work via chat:

from agno.agent import Agent
from agno.tools.scheduler import SchedulerTools

agent = Agent(
    id="my-agent",
    model="openai:gpt-5.4",
    tools=[
        SchedulerTools(
            db=db,
            default_endpoint="/agents/my-agent/runs",
            default_method="POST",
            default_timezone="UTC",
        ),
    ],
)

# In Slack: "@MyAgent post a daily digest of open PRs at 9am ET"
# The agent calls SchedulerTools.create_schedule() with a cron expr.

The Scheduler Tools Agent example is a runnable version of this pattern.

Manually Registered

For schedules that should always exist (the daily digest, the hourly sync, the nightly cleanup), create them in your app’s lifespan via ScheduleManager:

from contextlib import asynccontextmanager
from agno.scheduler import ScheduleManager

@asynccontextmanager
async def lifespan(app):
    manager = ScheduleManager(db=db)
    manager.create(
        name="daily_digest",
        cron="0 9 * * 1-5",                       # weekdays 9am
        endpoint="/agents/my-agent/runs",
        payload={"message": "Create the daily digest."},
        if_exists="update",                       # idempotent on restart
    )
    yield

agent_os = AgentOS(agents=[agent], db=db, scheduler=True, lifespan=lifespan)

if_exists="update" makes the call idempotent. Re-running on restart updates the existing schedule rather than raising or duplicating. Pass "skip" if you want to leave manually-edited schedules alone, or "raise" (the default) to surface accidental name collisions. This is the pattern Coda uses for daily digest and repo sync.

Workflows for multi-step jobs

Schedules fire single endpoints. When the work is multi-step (research, then outline, then draft, then review), you reach for a workflow. Workflows are a separate primitive, but they’re the most common thing a schedule fires. A workflow is a typed pipeline whose steps run in order. Use Parallel for concurrent steps, Loop for repetition, and Router to select one branch.

from agno.workflow import Loop, Step, Workflow

workflow = Workflow(
    name="content_pipeline",
    steps=[
        Step(name="research", agent=researcher),
        Step(name="outline", agent=outliner),
        Loop(
            name="draft_review",
            steps=[
                Step(name="draft", agent=writer),
                Step(name="review", agent=editor),
            ],
            end_condition='last_step_content.contains("APPROVED")',
            max_iterations=3,
        ),
    ],
)

Loop.end_condition accepts a CEL expression string (as above) or a callable that takes the iteration’s step outputs and returns a bool. Condition is a separate primitive for if/else branching inside a workflow.

CEL string conditions need the optional cel-python dependency: pip install cel-python or pip install 'agno[cel]'. Without it, the expression logs an error, evaluates to False, and the loop runs to max_iterations. The callable form has no extra dependency.

Registered workflows get a POST /workflows/<id>/runs endpoint and can be scheduled. Session history is persisted when the workflow has a database. Traces are stored when AgentOS tracing is enabled.

Pattern	Use when
Sequential	Steps depend on each other
Parallel	Steps are independent and you want fanout
Loop with condition	Quality threshold or max iterations
Router + Condition	Dynamic branching on input
Cross-modal chaining	Output of one agent is input to a different modality (text → speech, code → narration)

For worked examples, see Demo OS.

Schedule runs and observability

When a schedule fires, AgentOS:

Looks up the schedule in agno_schedules and claims it via a row-level lease.
Calls the configured endpoint (POST /agents/<id>/runs or POST /workflows/<id>/runs) over HTTP via httpx.AsyncClient. This is the same path an external caller would take, including auth headers.
Records the schedule attempt in agno_schedule_runs with status, timings, the underlying run_id and session_id when returned, and any error. The target component persists its run according to its database configuration. Traces require tracing to be enabled.

Schedule runs are queryable from agno_schedule_runs. When the target component persists sessions and AgentOS tracing is enabled, the linked run also appears in session and trace views. This Postgres query lists runs fired in the last 24 hours:

SELECT
    s.name,
    sr.status,
    sr.triggered_at,
    (sr.completed_at - sr.triggered_at) AS duration_s
FROM ai.agno_schedule_runs sr
JOIN ai.agno_schedules s ON s.id = sr.schedule_id
WHERE sr.created_at > extract(epoch from NOW() - INTERVAL '24 hours')::bigint
ORDER BY sr.created_at DESC;

The ai. prefix is the schema PostgresDb creates its tables in by default (override with PostgresDb(db_schema=...)). Timestamps on schedule runs are stored as epoch seconds (BigInt). For the trace of a specific scheduled run, follow the run_id from agno_schedule_runs back to agno_traces. See Observability for the full data model.

Scheduler in HA

Every replica can run the scheduler loop safely on the backends that implement the scheduler’s claim methods (Postgres, SQLite, and MongoDB). Due schedules are claimed via a row-level lease (locked_by, locked_at on agno_schedules). The first replica to claim a due job runs it; the others skip. No leader election needed. If you’d rather keep scheduler polling off your hot request path, pin it to a dedicated replica via deployment config. See Scheduler for tuning details.

Welcome

Get Started

Features

Use Cases

Two ways to create schedules

Agent Managed

Manually Registered

Workflows for multi-step jobs

Schedule runs and observability

Scheduler in HA

​Two ways to create schedules

​Agent Managed

​Manually Registered

​Workflows for multi-step jobs

​Schedule runs and observability

​Scheduler in HA

Two ways to create schedules

Agent Managed

Manually Registered

Workflows for multi-step jobs

Schedule runs and observability

Scheduler in HA