OpenClawDocs
On this page

On this page

View as MarkdownView this page as plain textOpen in ChatGPTAsk questions about this pageOpen in ClaudeAsk questions about this page

Automation

Automation

OpenClaw runs work in the background through native runtimes, scheduled jobs, event hooks, and standing instructions. Use this page to pick the right mechanism.

Quick decision guide

flowchart TD
    START([What do you need?]) --> Q1{Schedule work?}
    START --> Q3{Orchestrate multi-step flows?}
    START --> Q4{React to lifecycle events?}
    START --> Q5{Give the agent persistent instructions?}

    Q1 -->|Yes| CRON["Automations"]

    Q3 -->|Yes| FLOW[Lobster]
    Q4 -->|Yes| HOOKS[Hooks]
    Q5 -->|Yes| SO[Standing Orders]
Use case Recommended Why
Send daily report at 9 AM sharp Automations Exact timing, isolated execution
Remind me in 20 minutes Automations One-shot with precise timing (--at)
Run weekly deep analysis Automations Standalone task, can use different model
Check inbox every 30 min Automations Independent recurring schedule and job history
Trigger safely on new IMAP email IMAP plugin Sender-gated isolated reader sessions
Monitor calendar for upcoming events Automations Explicit recurring schedule and delivery policy
Surface ambient main-session updates Automations Editable monitoring jobs with quiet results
Run a script on session reset Hooks Internal HOOK.md scripts react to lifecycle events
Trigger an agent from an external service Webhooks Authenticated HTTP ingress, not an internal event hook
Execute code on every tool call Plugin hooks Typed api.on(...) handlers can intercept tool calls
Always check compliance before replying Standing Orders Injected into every session automatically

Periodic monitoring

Recurring reports, reminders, and ambient checks are ordinary automation jobs. Each job owns its schedule, context, delivery policy, and history. Use activeHours and idleOnly when a check should respect quiet hours and foreground work; use scratch for a small checklist and NO_REPLY when nothing needs attention. Existing heartbeat monitors migrate through Doctor.

Core concepts

Automations

Automations are OpenClaw's built-in scheduler for all recurring and one-shot work, including periodic monitors. The scheduler persists jobs, wakes the agent at the right time, and can deliver output to a chat channel or webhook endpoint. It supports one-shot reminders, recurring intervals and cron expressions, and inbound webhook triggers.

See Automations.

Background execution and workflows

Use Sub-agents to launch and wait for delegated runs, ACP for coding harness sessions, and automation run history to inspect scheduled work. Each runtime owns execution and completion.

Lobster runs local pipelines with resumable approvals. The shared Tasks ledger, TaskFlow orchestration API, and TaskFlow Webhooks plugin have been removed. Generic Gateway HTTP hooks remain available for authenticated external triggers.

Standing orders

Standing orders grant the agent permanent operating authority for defined programs. They live in workspace files (typically AGENTS.md) and are injected into every session. Combine with automations for time-based enforcement.

See Standing Orders.

Hooks

Internal hooks are event-driven scripts triggered by agent lifecycle events (/new, /reset, /stop), session compaction, gateway startup, and message flow. They are discovered from hook directories and managed with openclaw hooks. For in-process tool-call interception, use Plugin hooks.

See Hooks.

Heartbeat

Existing heartbeat monitors migrate into ordinary editable jobs with their own scratch, execution policies, and delivery settings. Setup provisions one proactive check for the ambient owner; later reloads and restarts leave job edits and deletions alone. See Heartbeat migration.

How they work together

  • Automations own recurring reports, reminders, and monitoring checks. Each independently scheduled task belongs in its own job.
  • Hooks react to specific events (session resets, compaction, message flow) with custom scripts. Plugin hooks cover tool calls.
  • Standing orders give the agent persistent context and authority boundaries.

Retired inferred commitments

The inferred commitments experiment was removed in v2026.8.1: OpenClaw no longer extracts follow-ups from conversations or delivers them through heartbeat. The openclaw commitments maintenance CLI is also gone. The database migration discards the old commitment rows and removes their table and indexes.

For reminders or scheduled work, create an explicit automation. Automations are an alternative with a schedule and instructions you choose; they do not restore inferred follow-ups.

Was this useful?