OpenClaw Heartbeats: How Proactive AI Scheduling Works

In the fast-evolving world of AI assistants, the dream of a truly autonomous agent isn’t just about responding to prompts; it’s about anticipation. It’s about an AI that doesn’t wait for instructions but proactively manages tasks, monitors systems, and keeps things running smoothly in the background. For OpenClaw users, this isn’t a future vision—it’s here, powered by OpenClaw Heartbeats. This feature transforms your agent from a reactive tool into a vigilant, self-starting team member, constantly checking on things and taking action without you needing to lift a finger. Let’s dive deep into how this works and how you can harness its power for your projects.

What is an OpenClaw Heartbeat?

At its core, an OpenClaw Heartbeat is a scheduled, automated invocation of your AI agent. Think of it as your agent taking its pulse at regular intervals. Instead of waiting for a user prompt, the OpenClaw scheduler wakes up your designated agent, provides it with a specific set of instructions, and expects it to perform necessary checks and actions.

The operational flow is straightforward yet powerful:

1. Scheduled Trigger: The OpenClaw scheduler, configured to a specific interval (e.g., every 5 minutes, daily at 9 AM), sends a “heartbeat” signal to your agent.
2. Instruction Loading: Upon receiving the heartbeat, the agent loads its predefined instructions, typically from a file like HEARTBEAT.md located in its operational context.
3. Execution & Action: The agent parses these instructions and, leveraging its integrated tools and knowledge base, performs the specified tasks. This could involve checking external services, summarizing data, drafting communications, or initiating workflows.
4. Reporting & Acknowledgment: If tasks are completed successfully and no specific output is required, the agent silently replies with HEARTBEAT_OK, signaling to the scheduler that it has processed the heartbeat. If an action was taken or an issue was found, the agent provides relevant output (e.g., a Slack message, an email, a log entry).

This system allows for truly proactive behavior, shifting the burden of monitoring and routine tasks from you to your AI assistant. It’s about empowering your agent to be a responsible, autonomous entity within your operational stack.

Configuring Your OpenClaw Heartbeat System

Setting up heartbeats involves modifying your OpenClaw configuration and preparing the agent’s instruction file. Let’s walk through the practical steps.

1. Enable and Configure in openclaw_config.yaml

The primary configuration happens in your OpenClaw instance’s main configuration file, usually openclaw_config.yaml. You’ll need to locate or add the heartbeat_scheduler section:

# openclaw_config.yaml

heartbeat_scheduler:
  enabled: true
  interval: "/5    *"  # Cron string: every 5 minutes
  # interval: "30m"          # Or duration string: every 30 minutes
  # interval: "1h"           # Every 1 hour
  agent_id: "my_dev_ops_agent" # The ID of the agent to trigger
  context_path: "/agents/my_dev_ops_agent/heartbeat/" # Path where HEARTBEAT.md lives
  log_level: "INFO" # Or DEBUG, WARNING, ERROR

agents:
  my_dev_ops_agent:
    model: "claude-3-opus-20240229" # Or gpt-4-turbo, etc.
    temperature: 0.2
    max_tokens: 2000
    # ... other agent specific configurations, like tool definitions
    tools:
      - name: "email_reader"
        path: "plugins/email_reader.py"
      - name: "slack_notifier"
        path: "plugins/slack_notifier.py"
      - name: "jira_api"
        path: "plugins/jira_api.py"
      # ... other tools your agent might use

• enabled: true: Activates the heartbeat scheduler.
• interval: "/5 ": This is a cron expression. /5 means “every 5 minutes.” You can use standard cron syntax for more complex schedules (e.g., 0 9 1-5 for 9 AM every weekday). Alternatively, you can use duration strings like "30m" or "1h" for simpler, fixed intervals.
• agent_id: "my_dev_ops_agent": Specifies which registered agent in your OpenClaw setup should receive the heartbeat. Ensure this agent ID matches an entry under your agents section.
• context_path: "/agents/my_dev_ops_agent/heartbeat/": This is crucial. It tells the agent where to find its heartbeat instructions. Within this directory, the agent will look for a file named HEARTBEAT.md.
• log_level: Sets the verbosity for heartbeat-related logs.

After modifying openclaw_config.yaml, you’ll need to restart your OpenClaw instance for the changes to take effect:

openclaw-cli restart

2. Create Your HEARTBEAT.md File

Navigate to the context_path you defined (e.g., /agents/my_dev_ops_agent/heartbeat/) and create a file named HEARTBEAT.md. This file contains the instructions your agent will follow every time it receives a heartbeat.

# HEARTBEAT.md

## OpenClaw Agent Daily Routine
Objective: Proactively monitor critical systems, ensure communication, and prepare for upcoming tasks.
---
### Task 1: Check Production System Health
Action: Use the `system_monitor` tool to ping `api.mycompany.com` and `db.mycompany.com`.
Condition: If any service is down or latency exceeds 200ms, use the `slack_notifier` tool to send an alert to `#devops-alerts` with severity "CRITICAL" and the service status.
Output: Log results silently if all services are healthy.


### Task 2: Review Calendar for Tomorrow's Meetings
Action: Use the `calendar_api` tool to fetch all events scheduled for tomorrow (PST).
Condition: For each meeting involving "Client X" or "Project Phoenix", use the `jira_api` tool to fetch related tickets (status "In Progress" or "To Do") and the `confluence_api` tool to find relevant documentation.
Output: Summarize key discussion points and associated Jira/Confluence links. Use the `email_sender` tool to send this summary to `team-lead@mycompany.com` with subject "Meeting Prep: [Meeting Title]".


### Task 3: Monitor RSS Feeds for Industry News
Action: Use the `rss_parser` tool to check `techcrunch.com/feed.xml` and `openai.com/blog/rss.xml` for new articles published in the last 24 hours.
Condition: Filter for articles containing keywords like "