Skip to main content

Heartbeats

Added in: @mastra/core@1.46.0

beta

This feature is in alpha. Breaking changes may occur without a major version bump until the API is stable.

A heartbeat runs an agent on a cron schedule. On each fire, Mastra sends a prompt to the agent, either as a signal into a thread or as a threadless agent.generate() run. Use heartbeats for recurring agent work such as daily summaries, periodic checks, or scheduled nudges into a conversation.

Heartbeats are persisted, so they survive restarts and redeploys. Manage them at runtime through mastra.heartbeats, the canonical create, read, update, and delete (CRUD) surface.

Prerequisites
Direct link to Prerequisites

Heartbeats require a storage adapter that implements the schedules domain, for example @mastra/libsql. Without one, mastra.heartbeats.create() throws.

Quickstart
Direct link to Quickstart

The following heartbeat runs the pinger agent every hour. It has no thread, so each fire is an isolated agent.generate() run.

src/mastra/heartbeats.ts
import { Mastra } from '@mastra/core'
import { Agent } from '@mastra/core/agent'
import { LibSQLStore } from '@mastra/libsql'

const pinger = new Agent({
id: 'pinger',
name: 'Pinger',
instructions: 'Report the current system status in one sentence.',
model: 'openai/gpt-5.5',
})

const mastra = new Mastra({
agents: { pinger },
storage: new LibSQLStore({ url: 'file:./mastra.db' }),
})

await mastra.heartbeats.create({
agentId: 'pinger',
cron: '0 * * * *',
prompt: 'Give me a status update.',
})

Mastra starts the scheduler the first time a heartbeat is created, then fires the agent on the cron you specify.

Cadence
Direct link to Cadence

Heartbeats fire on a cron expression. The cron field accepts a standard 5-, 6-, or 7-part cron expression, and it's validated when you create or update the heartbeat.

Croner nicknames also work, for example @hourly, @daily, @weekly, @monthly, and @midnight. For day-and-time combinations, write the cron field directly:

// Every weekday at 9am
await mastra.heartbeats.create({
agentId: 'pinger',
cron: '0 9 * * 1-5',
prompt: 'Start-of-day check.',
})

Set timezone to an IANA timezone, for example America/New_York, so fire times don't depend on the host's locale. When omitted, the cron resolves against the host's local timezone.

For more readable cron construction, you can use a userland builder such as cron-time-generator and pass its output to cron.

Threadless and threaded heartbeats
Direct link to Threadless and threaded heartbeats

A heartbeat fires in one of two modes, decided by whether you pass a threadId.

Threadless
Direct link to Threadless

Without a threadId, each fire is an isolated agent.generate() run. Nothing is written to a conversation thread. This is the simplest mode and suits status checks, reports, and other work that doesn't need conversation context.

Threaded
Direct link to Threaded

With a threadId, the heartbeat sends a signal into that thread, so the prompt joins the agent's conversation. Threaded heartbeats require a resourceId alongside the threadId.

src/mastra/heartbeats.ts
await mastra.heartbeats.create({
agentId: 'pinger',
cron: '0 9 * * *',
prompt: 'Summarize anything new since yesterday.',
threadId: 'thread-123',
resourceId: 'user-456',
})

Threaded heartbeats accept extra fields that control how the signal behaves. They mirror the options agent.sendSignal accepts and stay JSON-serializable so they persist with the schedule.

  • signalType: the signal type to send, for example notification or system-reminder. Defaults to notification.
  • tagName: the XML tag the signal renders as. Defaults to heartbeat, so a fire surfaces to the agent as <heartbeat>…</heartbeat>.
  • attributes: values rendered onto the signal's XML tag.
  • ifActive: behavior when the thread is already streaming, as { behavior, attributes }. behavior is one of deliver, persist, or discard.
  • ifIdle: behavior when the thread is idle, as { behavior, attributes, streamOptions }. behavior is one of wake, persist, or discard. streamOptions.requestContext is applied to the woken run.

These fields require a threadId. Passing them on a threadless heartbeat throws.

await mastra.heartbeats.create({
agentId: 'pinger',
cron: '0 9 * * *',
prompt: 'Summarize anything new since yesterday.',
threadId: 'thread-123',
resourceId: 'user-456',
tagName: 'check-in', // renders as <check-in>…</check-in>
attributes: { source: 'cron' },
ifActive: { behavior: 'discard' }, // skip if the thread is mid-stream
ifIdle: {
behavior: 'wake', // wake the agent if the thread is idle
streamOptions: { requestContext: { locale: 'en-US' } },
},
})

providerOptions are merged into the signal payload on every fire and apply to both threaded and threadless heartbeats.

Managing heartbeats
Direct link to Managing heartbeats

Use mastra.heartbeats for all heartbeat operations. To scope to a single agent, pass agentId to create or list.

// Create
const hb = await mastra.heartbeats.create({
agentId: 'pinger',
cron: '0 * * * *',
prompt: 'Status check.',
})

// Read
await mastra.heartbeats.get(hb.id)
await mastra.heartbeats.list({ agentId: 'pinger' })

// Update — changing cron or timezone recomputes the next fire time
await mastra.heartbeats.update(hb.id, { cron: '*/30 * * * *' })

// Pause and resume
await mastra.heartbeats.pause(hb.id)
await mastra.heartbeats.resume(hb.id)

// Fire once now, off-schedule
await mastra.heartbeats.run(hb.id)

// Delete
await mastra.heartbeats.delete(hb.id)

A few rules worth knowing:

  • pause and resume are durable and idempotent. A paused heartbeat survives restarts, and resume recomputes the next fire time from now rather than firing backlogged runs.
  • run fires the heartbeat once immediately without affecting its schedule.
  • list filters by agentId, threadId, resourceId, and name.

Custom IDs
Direct link to Custom IDs

By default create generates a random hb_<uuid> id. Pass id to choose a stable one, for example when you want a predictable handle to look up, update, or delete later:

await mastra.heartbeats.create({
id: 'nightly-summary',
agentId: 'pinger',
cron: '0 9 * * *',
prompt: 'Summarize anything new since yesterday.',
})
// stored as `hb_nightly-summary`

The id is normalized to hb_<slug>: the hb_ prefix is added if missing and the rest is slugified. Creating a heartbeat with an id that already exists throws, so use update to change an existing one.

From the client
Direct link to From the client

The same operations are available from @mastra/client-js over the server routes, so you can manage heartbeats from a separate process or a UI.

Lifecycle hooks
Direct link to Lifecycle hooks

Hooks let you run code at key points in a heartbeat's lifecycle, for example to compute fire-time parameters or react to the outcome. Configure them on the Mastra constructor under heartbeat. The hooks are a single flat bundle that runs for every agent's heartbeats; each hook context carries the firing agentId, so branch on it when you need per-agent behavior. Hooks live at the Mastra level so they apply to both code-defined and stored agents.

src/mastra/index.ts
const mastra = new Mastra({
agents: { pinger },
storage: new LibSQLStore({ url: 'file:./mastra.db' }),
heartbeat: {
prepare: async ({ agentId, heartbeat, trigger }) => {
// Return overrides, null to skip this fire, or undefined for defaults
return { prompt: `Status as of ${trigger.firedAt.toISOString()}` }
},
onFinish: async ({ agentId, outcome, runId }) => {
// Runs on any non-error, non-abort outcome
},
onError: async ({ agentId, phase, error }) => {
// Runs when prepare, the signal, or the agent run threw
},
onAbort: async ({ agentId, runId }) => {
// Runs when the run was aborted mid-stream
},
},
})

The hooks are:

  • prepare: runs before the fire. Return an object to override fire-time parameters such as prompt or threadId, null to skip the fire, or undefined to use the stored defaults.
  • onFinish: runs once per trigger that reached a non-error, non-abort terminal state.
  • onError: runs when prepare, the signal, or the agent run threw.
  • onAbort: runs when the run was aborted mid-stream.

Every hook context includes agentId (the agent the heartbeat fired for) alongside heartbeat and trigger.

Hook exceptions are caught and logged. They never re-route the worker or trigger another hook.

  • Signals: the delivery mechanism behind threaded heartbeats.
  • Scheduled workflows: run a workflow, rather than an agent, on a cron schedule.