Skip to content

The open-source agent harness - the runtime layer that turns an LLM into a working agent.

3.2 KB
Raw Blame
---
title: 'Schedules'
sidebarTitle: 'Schedules'
description: 'Run a saved agent on a recurring cadence, unattended, and review each run.'
---

**Schedules** run a saved agent on a recurring cadence, unattended. Each run sends the agent the same task, executes on the server, and is recorded as a [session](/sessions) you can open later. Use them for recurring work such as a daily brief, a periodic report, or a regular check.

## Before you start

A schedule runs an existing **saved agent**, so [create an agent](/create-agent/overview) first. The agent receives the same task on every run, so its instructions and tools should already cover that work.

## Creating a schedule

Open **Schedules** from the sidebar and click **Create Schedule**. Fill in:

- **Agent**: the saved agent to run.
- **Name**: a label for the schedule.
- **Task**: the message sent to the agent on every run. Write it as you would the first message in a chat, for example: "Summarize the most important AI news from the last 24 hours and list the top five items with links."
- **Frequency**: **Hourly**, **Daily**, or **Weekly**, with the hour, minute, and **timezone** to run in. The form previews the result, such as "Daily 9:00 AM" in your timezone.

Click **Save**. The schedule becomes active and runs on that cadence.

<Frame caption="Creating a schedule: pick a saved agent, write the task, and set the cadence and timezone.">
  ![The New Schedule form with an agent, a name, a task message, and a Daily frequency set to a time and timezone, with a preview of the resulting cadence](/images/schedules-create.png)
</Frame>

<Note>
  The shortest interval is one hour. Times are evaluated in the timezone you choose, and daylight-saving shifts are handled for you.
</Note>

## How runs work

- Every run starts a fresh session, sends the agent the task, and ends when the agent completes it.
- Each run is recorded as a [session](/sessions), marked **Scheduled run**, so you can open it to read the transcript, tool calls, and result.
- The list shows the outcome of the **last five runs** for each schedule.
- Use **Run now** to trigger a run immediately, without waiting for the next scheduled time.

## Managing schedules

The **Scheduled Agents** page lists every schedule with its agent, cadence, status, and recent runs. From here you can:

- **Search** by name, or filter by **status** or **agent**.
- **Pause** a schedule to stop it from running, and resume it later. Paused schedules stay in the list.
- **Edit** a schedule's task, cadence, or timezone.
- **Delete** a schedule you no longer need.

<Frame caption="The Scheduled Agents list: each schedule with its agent, frequency, status, and last five runs.">
  ![The Scheduled Agents list showing a schedule with its name, agent, creator, frequency, status, and last-five-runs summary, with a Run now button and a row menu](/images/schedules-list.png)
</Frame>

<Note>
  Schedules run on the server, so the server must be running for them to trigger. In hosted mode with [login](/authentication/overview) enabled, schedules are owner-scoped: each user sees only their own.
</Note>

## Via the SDK

You can create and manage schedules programmatically with `client.schedules`. See [Schedules in the SDK](/api/use-agent#schedules).