Schedule Agents

Run an agent on a recurring cadence without holding open an HTTP connection. Each scheduled run follows the same execution path, tracing, and billing as a direct API call.

Create a Schedule

AI Studio
API & SDK
CLI

Open the agent and go to the Schedules tab. Click New schedule to open the form.

Agent schedule creation form showing Name, Frequency toggle with Hourly, Daily, and Weekly options, Time, Summary, Input, Variables, and Metadata fields. — Create a new schedule from the Schedules tab on an agent.

Field	Description
Name	A display label for the schedule in the UI. Required. Not sent to the agent.
Frequency	Hourly, Daily, or Weekly.
Time	The hour the schedule fires, in local time. Shown for Daily and Weekly.
Pick the day	Day of the week to fire. Shown for Weekly only.
Summary	Auto-generated human-readable description of the schedule.
Input	The user message sent to the agent on each firing. Required, since every agent invocation needs a user message.
Variables	Key-value pairs passed to the agent on each run. See below.
Metadata	Key-value pairs attached to every response this schedule generates. See below.

VariablesUse the Variables section to define values that the agent needs on each run. Variables are sent alongside the input as a distinct payload field, and can be consumed by the agent’s instructions, any configured tool, or a subagent wherever the variable is wired up.

For example, a support agent with an HTTP tool that looks up a customer in an external system can receive customer_id=1234 from the schedule and use it to query the right record on every run. See the screenshot below.

Variables cannot be referenced inside the Input field itself. Wire them into the agent’s instructions, a tool, or a subagent instead.MetadataUse the Metadata section to attach arbitrary key-value pairs to every response generated by this schedule. Metadata is not passed to the agent: it is stored on the trace and can be used to filter traces in Observability, identify which schedule triggered a run, or tag responses for downstream processing.Click Create to activate the schedule. It starts firing at the next matching time.

A saved agent schedule entry showing the schedule name, frequency, next run time, and the configured variables and metadata key-value pairs. — A created schedule showing configured variables and metadata.

Only cron schedules are supported. Expressions use the 6-field format: sec min hour dom month dow. Three patterns are accepted:

Pattern	Expression	Example
Hourly	`0 0 * * * *`	Fires every hour
Daily	`0 0 <hour> * * *`	`0 0 9 * * *` (9:00 AM UTC daily)
Weekly	`0 0 <hour> * * <day>`	`0 0 9 * * 1` (9:00 AM UTC every Monday)

<day> is 0 (Sunday) through 6 (Saturday). All times are stored in UTC; the UI displays them in the user’s local timezone.

Only cron is accepted. Seconds and minutes must be 0, dom and month must be *, and the weekday field must be a single integer 0-6 or * (names like mon and ranges like 1-5 are rejected). To run an agent in response to an event rather than a clock, invoke it directly via the Run API.Expressions that do not match a supported pattern return 400 with "code": "invalid_expression". The message field describes the specific violation, for example invalid schedule expression: day-of-month and month fields must be '*'

curl -X POST https://my.orq.ai/v3/agents/ops_digest/schedules \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "cron",
    "expression": "0 0 9 * * *",
    "display_name": "Morning briefing",
    "payload": {
      "input": "Generate the morning briefing for {{region}}",
      "variables": { "region": "EMEA" }
    }
  }'

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    schedule = orq.schedules.create(
        agent_key="ops_digest",
        type_="cron",
        expression="0 0 9 * * *",
        display_name="Morning briefing",
        payload={
            "input": "Generate the morning briefing for {{region}}",
            "variables": {"region": "EMEA"},
        },
    )
    print(schedule)

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

const schedule = await orq.schedules.create({
  agentKey: 'ops_digest',
  requestBody: {
    type: 'cron',
    expression: '0 0 9 * * *',
    displayName: 'Morning briefing',
    payload: {
      input: 'Generate the morning briefing for {{region}}',
      variables: { region: 'EMEA' },
    },
  },
});

console.log(schedule);

The TypeScript SDK uses camelCase keys (agentKey, requestBody) and nests the request body under requestBody, while the Python SDK uses flat keyword arguments. Both map to the same wire format.

payload is required. Response (schedule records use _id rather than id):

{
  "_id": "01KPN29WWKSK0VDPJNTKZPVNRB",
  "agent_key": "ops_digest",
  "type": "cron",
  "expression": "0 0 9 * * *",
  "display_name": "Morning briefing",
  "is_active": true,
  "generation": 1,
  "payload": {
    "input": "Generate the morning briefing for {{region}}",
    "variables": { "region": "EMEA" }
  },
  "trigger_count": 0,
  "created": "2026-04-20T10:00:00Z",
  "updated": "2026-04-20T10:00:00Z"
}

Schedule fields:

Field	Type	Description
`display_name`	string	Required. Label shown in the UI Schedules tab. Max 200 characters, cannot be blank.
`type`	string	Must be `cron`.
`expression`	string	6-field cron expression matching one of the three supported patterns.
`agent_tag`	string	Pin the schedule to a specific agent version. Omit to always run the active version.

Payload fields:

Field	Type	Description
`input`	string or array	The instruction the agent runs on each firing. Same shape as the `input` field in the Run API. Supports template variables via `{{variable}}`.
`variables`	object	Template variable substitution. Use `{"secret": true, "value": "..."}` for secret values.
`memory_entity_id`	string	Memory store entity to attach on each run.
`metadata`	object	Opaque key/value pairs attached to every response this schedule generates. Values must be strings.

generation increments each time type or expression changes and resets trigger_count to 0. Use it to distinguish firings before and after a cadence change.Use agent_tag (string) to pin the schedule to a specific agent version. Omit it to always use the active version:

{
  "type": "cron",
  "expression": "0 0 9 * * *",
  "display_name": "Morning briefing",
  "agent_tag": "v2",
  "payload": { "input": "Generate the morning briefing for {{region}}" }
}

display_name is required and is not exposed as a flag on schedules create, so pipe the full body via --stdin:

echo '{
  "type": "cron",
  "expression": "0 0 9 * * *",
  "display_name": "Morning briefing",
  "payload": {
    "input": "Generate the morning briefing for {{region}}",
    "variables": { "region": "EMEA" }
  }
}' | orq schedules create ops_digest --stdin

See install and setup to get started with the CLI. Run orq schedules create --help for the full flag reference.

List & Retrieve

AI Studio
API & SDK
CLI

All schedules for the agent are listed in the Schedules tab. Click a schedule row to open its details, including trigger count and last fired time.

# List all schedules
curl https://my.orq.ai/v3/agents/ops_digest/schedules \
  -H "Authorization: Bearer $ORQ_API_KEY"

# Get a single schedule
curl https://my.orq.ai/v3/agents/ops_digest/schedules/{schedule_id} \
  -H "Authorization: Bearer $ORQ_API_KEY"

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    # List all schedules
    result = orq.schedules.list(agent_key="ops_digest")
    print(result.schedules)

    # Get a single schedule
    schedule = orq.schedules.retrieve(
        agent_key="ops_digest",
        schedule_id="{schedule_id}",
    )
    print(schedule)

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

// List all schedules
const result = await orq.schedules.list({ agentKey: 'ops_digest' });
console.log(result.schedules);

// Get a single schedule
const schedule = await orq.schedules.retrieve({
  agentKey: 'ops_digest',
  scheduleId: '{schedule_id}',
});
console.log(schedule);

List returns { "schedules": [...] }, most recent first. The single-schedule response includes trigger_count, last_triggered_at (UTC timestamp string; null before the first firing), and generation.

# List schedules for this agent
orq schedules list ops_digest

# Get a single schedule
orq schedules retrieve ops_digest <schedule_id>

See install and setup to get started with the CLI. Run orq schedules list --help for the full flag reference.

Pause and Resume

AI Studio
API & SDK
CLI

Click on the schedule row, then click Enable to toggle the schedule on or off. Field edits saved while paused take effect on the next active run.

# Pause
curl -X PATCH https://my.orq.ai/v3/agents/ops_digest/schedules/{schedule_id} \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "is_active": false }'

# Resume
curl -X PATCH https://my.orq.ai/v3/agents/ops_digest/schedules/{schedule_id} \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "is_active": true }'

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    # Pause
    orq.schedules.update(
        agent_key="ops_digest",
        schedule_id="{schedule_id}",
        is_active=False,
    )

    # Resume
    orq.schedules.update(
        agent_key="ops_digest",
        schedule_id="{schedule_id}",
        is_active=True,
    )

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

// Pause
await orq.schedules.update({
  agentKey: 'ops_digest',
  scheduleId: '{schedule_id}',
  requestBody: { isActive: false },
});

// Resume
await orq.schedules.update({
  agentKey: 'ops_digest',
  scheduleId: '{schedule_id}',
  requestBody: { isActive: true },
});

Payload-only and agent_tag-only changes do not reset the firing cadence and apply to the next regular run. Changing type or expression shifts the cadence from the PATCH time and resets trigger_count to 0.Lifecycle notes:

Missed firings: Not replayed. If the service is unavailable when a schedule fires, that firing is lost. The schedule resumes on its next scheduled time once service is restored.

# Pause
orq schedules update ops_digest <schedule_id> --is-active=false

# Resume
orq schedules update ops_digest <schedule_id> --is-active=true

See install and setup to get started with the CLI. Run orq schedules update --help for the full flag reference.

Trigger On Demand

API & SDK
CLI

Runs the schedule’s payload immediately without affecting its regular cadence. Useful for smoke-testing a new schedule or manually re-running a missed execution.

curl -X POST https://my.orq.ai/v3/agents/ops_digest/schedules/{schedule_id}/execution \
  -H "Authorization: Bearer $ORQ_API_KEY"

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    orq.schedules.trigger(
        agent_key="ops_digest",
        schedule_id="{schedule_id}",
    )

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

await orq.schedules.trigger({
  agentKey: 'ops_digest',
  scheduleId: '{schedule_id}',
});

Returns 202 Accepted with:

{
  "status": "triggered",
  "schedule_id": "01KPN29WWKSK0VDPJNTKZPVNRB"
}

The run appears in traces as a schedule.<agent_key> leading span roughly 10 seconds later, carrying orq.schedule_id and the full agent execution chain. Schedule-driven cost and token usage appear in usage reports alongside HTTP-invoked runs. Inactive schedules return 400 schedule_inactive.

orq schedules trigger ops_digest <schedule_id>

See install and setup to get started with the CLI. Run orq schedules trigger --help for the full flag reference.

Delete

AI Studio
API & SDK
CLI

Click on the schedule row, then click Delete. The action is immediate and permanent.

curl -X DELETE https://my.orq.ai/v3/agents/ops_digest/schedules/{schedule_id} \
  -H "Authorization: Bearer $ORQ_API_KEY"

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    orq.schedules.delete(
        agent_key="ops_digest",
        schedule_id="{schedule_id}",
    )

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

await orq.schedules.delete({
  agentKey: 'ops_digest',
  scheduleId: '{schedule_id}',
});

Returns 204 No Content. Deleting the agent itself removes all its schedules automatically.

orq schedules delete ops_digest <schedule_id>

See install and setup to get started with the CLI. Run orq schedules delete --help for the full flag reference.

Examples

API & SDK
CLI

Daily morning briefing (9 AM UTC)

curl -X POST https://my.orq.ai/v3/agents/ops_digest/schedules \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "cron",
    "expression": "0 0 9 * * *",
    "display_name": "Daily morning briefing",
    "agent_tag": "v2",
    "payload": {
      "input": "Generate the morning briefing for {{region}}",
      "variables": { "region": "EMEA" },
      "metadata": { "run_source": "daily-briefing" }
    }
  }'

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    schedule = orq.schedules.create(
        agent_key="ops_digest",
        type_="cron",
        expression="0 0 9 * * *",
        display_name="Daily morning briefing",
        agent_tag="v2",
        payload={
            "input": "Generate the morning briefing for {{region}}",
            "variables": {"region": "EMEA"},
            "metadata": {"run_source": "daily-briefing"},
        },
    )
    print(schedule)

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

const schedule = await orq.schedules.create({
  agentKey: 'ops_digest',
  requestBody: {
    type: 'cron',
    expression: '0 0 9 * * *',
    displayName: 'Daily morning briefing',
    agentTag: 'v2',
    payload: {
      input: 'Generate the morning briefing for {{region}}',
      variables: { region: 'EMEA' },
      metadata: { run_source: 'daily-briefing' },
    },
  },
});

console.log(schedule);

Hourly background summarizer (with memory)

curl -X POST https://my.orq.ai/v3/agents/knowledge_indexer/schedules \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "cron",
    "expression": "0 0 * * * *",
    "display_name": "Hourly knowledge indexer",
    "payload": {
      "input": "Fetch new entries and update the knowledge base",
      "memory_entity_id": "mem_entity_123"
    }
  }'

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    schedule = orq.schedules.create(
        agent_key="knowledge_indexer",
        type_="cron",
        expression="0 0 * * * *",
        display_name="Hourly knowledge indexer",
        payload={
            "input": "Fetch new entries and update the knowledge base",
            "memory_entity_id": "mem_entity_123",
        },
    )
    print(schedule)

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

const schedule = await orq.schedules.create({
  agentKey: 'knowledge_indexer',
  requestBody: {
    type: 'cron',
    expression: '0 0 * * * *',
    displayName: 'Hourly knowledge indexer',
    payload: {
      input: 'Fetch new entries and update the knowledge base',
      memoryEntityId: 'mem_entity_123',
    },
  },
});

console.log(schedule);

memory_entity_id attaches a Memory Store entity to every run. The agent can read from and write to the store on each firing, accumulating context across executions.

Scheduled run with secret variables

curl -X POST https://my.orq.ai/v3/agents/daily_sync/schedules \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "cron",
    "expression": "0 0 3 * * *",
    "display_name": "Nightly warehouse sync",
    "payload": {
      "input": "Sync new rows from {{table}} to the analytics warehouse",
      "variables": {
        "table": "orders",
        "warehouse_token": { "secret": true, "value": "sk-secret-123" }
      }
    }
  }'

from orq_ai_sdk import Orq
import os

with Orq(api_key=os.getenv("ORQ_API_KEY", "")) as orq:
    schedule = orq.schedules.create(
        agent_key="daily_sync",
        type_="cron",
        expression="0 0 3 * * *",
        display_name="Nightly warehouse sync",
        payload={
            "input": "Sync new rows from {{table}} to the analytics warehouse",
            "variables": {
                "table": "orders",
                "warehouse_token": {"secret": True, "value": "sk-secret-123"},
            },
        },
    )
    print(schedule)

import { Orq } from '@orq-ai/node';

const orq = new Orq({ apiKey: process.env['ORQ_API_KEY'] ?? '' });

const schedule = await orq.schedules.create({
  agentKey: 'daily_sync',
  requestBody: {
    type: 'cron',
    expression: '0 0 3 * * *',
    displayName: 'Nightly warehouse sync',
    payload: {
      input: 'Sync new rows from {{table}} to the analytics warehouse',
      variables: {
        table: 'orders',
        warehouse_token: { secret: true, value: 'sk-secret-123' },
      },
    },
  },
});

console.log(schedule);

Secret values are redacted from traces and stripped from the stored payload’s observable form.

display_name is not yet exposed as a flag on schedules create, so these examples pipe the full body via --stdin:

Daily morning briefing (9 AM UTC)

echo '{
  "type": "cron",
  "expression": "0 0 9 * * *",
  "display_name": "Daily morning briefing",
  "agent_tag": "v2",
  "payload": {
    "input": "Generate the morning briefing for {{region}}",
    "variables": { "region": "EMEA" },
    "metadata": { "run_source": "daily-briefing" }
  }
}' | orq schedules create ops_digest --stdin

Hourly background summarizer (with memory)

echo '{
  "type": "cron",
  "expression": "0 0 * * * *",
  "display_name": "Hourly knowledge indexer",
  "payload": {
    "input": "Fetch new entries and update the knowledge base",
    "memory_entity_id": "mem_entity_123"
  }
}' | orq schedules create knowledge_indexer --stdin

Scheduled run with secret variables

echo '{
  "type": "cron",
  "expression": "0 0 3 * * *",
  "display_name": "Nightly warehouse sync",
  "payload": {
    "input": "Sync new rows from {{table}} to the analytics warehouse",
    "variables": {
      "table": "orders",
      "warehouse_token": { "secret": true, "value": "sk-secret-123" }
    }
  }
}' | orq schedules create daily_sync --stdin

See install and setup to get started with the CLI. Run orq schedules create --help for the full flag reference.

Overview

Managed Agents

Context Management

Test & Evaluate

Playground

Create a Schedule

List & Retrieve

Pause and Resume

Trigger On Demand

Delete

Examples

​Create a Schedule

​List & Retrieve

​Pause and Resume

​Trigger On Demand

​Delete

​Examples

Create a Schedule

List & Retrieve

Pause and Resume

Trigger On Demand

Delete

Examples