DEV Community

linou518
linou518

Posted on

Autonomous AI Agents: Building Self-Running AI with Heartbeat, Cron & Memory

#agents #llm #automation #ai

24/7 AI agents that find and execute work without human intervention. Here's how we built it in production.

The Problem: Passive AI

Most AI assistants — ChatGPT, Claude, etc. — are reactive: they wait for you to talk. But real operations need proactive behavior: publish a blog at 9 PM daily, check systems every 5 minutes, prepare today's task list each morning.

Running 20+ AI agents on OpenClaw, we solved this with a 3-layer architecture: Heartbeat + Cron + Memory.

The 3-Layer Architecture 

┌──────────────────────────────────────────┐
│  Layer 1: Heartbeat                       │
│  - Periodically wakes the agent           │
│  - Check inbox, read GOALS, assess tasks  │
│  - No work? Return HEARTBEAT_OK & sleep   │
└──────────────┬───────────────────────────┘
               ▼
┌──────────────────────────────────────────┐
│  Layer 2: Cron                            │
│  - Time-based task triggers               │
│  - e.g., Blog publish at 21:00 daily      │
│  - e.g., Monthly timesheet processing     │
└──────────────┬───────────────────────────┘
               ▼
┌──────────────────────────────────────────┐
│  Layer 3: Memory                          │
│  - CONTEXT.md: current state              │
│  - Daily notes: what happened today       │
│  - MEMORY.md: long-term knowledge         │
│  - Memory Service: vector-searchable DB   │
└──────────────────────────────────────────┘
Enter fullscreen mode Exit fullscreen mode

Layer 1: Heartbeat — The Agent's Pulse

The simplest yet most critical mechanism. At configured intervals (e.g., every 15 minutes), the agent receives a wake-up message and runs through a checklist:

  1. Check inbox — any messages from other agents?
  2. Read GOALS.md — any assigned tasks?
  3. Read CONTEXT.md — recall previous work state
  4. Decide — nothing to do? Return HEARTBEAT_OK and go back to sleep 
Heartbeat → Check → Nothing → HEARTBEAT_OK (sleep)
Heartbeat → Check → Task found → Execute → Report results
Enter fullscreen mode Exit fullscreen mode

Think of it as "glancing at your watch every 15 minutes." Cost is minimal — if nothing's happening, it's one API call.

Implementation Tips

  • Strictly enforce HEARTBEAT_OK responses (prevents unnecessary token burn)
  • Adjust intervals by role (monitoring: 5min, workers: 15-30min)
  • Never run heavy tasks inside heartbeat — delegate to cron or sub-agents

Layer 2: Cron — Scheduled Execution

For tasks that need to run at specific times. Standard crontab syntax.

Production Examples

Cron Task Agent
0 21 * * * Blog editing, translation & multi-platform publish Jack
0 9 * * 1-5 Learning material delivery (weekday mornings) Xuesi
30 8 * * * Health data review Health
0 0 L * * End-of-month timesheet processing HR

Writing Good Cron Prompts

Cron prompts must be completely self-contained:

  • Don't assume context — may execute in a fresh session
  • Include decision branches — "if no material exists, write one yourself"
  • Use absolute paths — working directory varies

Layer 3: Memory — Persistence Across Sessions

An AI agent's biggest weakness: forgetting. When a session ends, anything outside the context window is gone forever.

We solve this with 5 memory layers:

Layer Name Lifetime Purpose
L1 Session 1 session The conversation itself
L2 CONTEXT.md Always updated "What am I doing now"
L3 Daily notes Per day "What happened today"
L4 MEMORY.md Permanent Long-term knowledge
L5 Memory Service Permanent Vector-searchable DB

The Golden Rule: Write Immediately

"I'll write it later" is forbidden. Session compaction can run at any time, and unwritten information is lost permanently. Important decisions, completed tasks, inter-agent messages — all written immediately.

Practice: Coordinating 6 Agents

As a coordinator managing 6 specialized agents (learning, education, investment, health, life, real-estate), here are key lessons:

1. Message Bus for Loose Coupling

Inter-agent communication uses an HTTP API-based message bus. No direct session sharing. Same philosophy as microservices — loose coupling breeds stability.

2. GOALS.md for Autonomy

Each agent has a GOALS.md defining what to do. Permission levels (✅ autonomous / ⛔ needs approval / 🚫 forbidden) balance autonomy with safety.

3. Immediate Escalation

While autonomy is encouraged, "if unsure, ask immediately" is enforced. Asking takes 5 seconds; recovering from a wrong autonomous decision takes hours.

Cost Management

  • HEARTBEAT_OK instant responses minimize token consumption
  • Cache cron results to prevent duplicate execution
  • Delegate heavy tasks (translation, analysis) to sub-agents for parallelization
  • Optimize model selection (routine checks: lightweight model, writing: high-performance model)

Summary

Layer What It Solves Cost
Heartbeat "When to act" Minimal (1 API call)
Cron "What to do when" Task-dependent
Memory "What happened before" File I/O only

Combining these three layers transforms AI agents from "waiting for instructions" to "autonomous execution." It's not perfect, but it's practical. Daily blog publishing, learning material delivery, health data analysis — all running without human intervention.

"Self-running AI" isn't magic. It's architecture.

Top comments (0)