A lightweight MQTT-based messaging layer for AI agents to broadcast their identities and real-time status updates across a network.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install communication-mqtt
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install communication-mqtt using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is MQTT Agent Messenger?
This skill provides a robust framework for inter-agent communication using the MQTT protocol. It allows individual AI agents to introduce themselves by sharing their unique IDs and roles, while also providing a mechanism for continuous status broadcasting.
By leveraging a local or remote MQTT broker, Openclaw Skills can maintain a synchronized view of a multi-agent ecosystem, facilitating coordination and monitoring. The skill is designed to be lightweight, utilizing Python's paho-mqtt library for efficient message handling. It serves as a foundational layer for developers building complex, distributed AI systems where real-time awareness of every agent's activity is critical.
MQTT Agent Messenger Use Cases
- Coordinating multiple Openclaw Skills to prevent task overlap during complex workflows.
- Building a centralized dashboard to monitor the real-time activity and status of various AI agents.
- Implementing discovery protocols where new agents announce their roles to an existing network.
- Triggering specific agent behaviors based on status updates received from peer agents.
How MQTT Agent Messenger Works
- The agent initializes a connection to a local or remote MQTT broker, defaulting to localhost:1883.
- To announce its presence, the agent publishes an intro message containing its ID and role to a specific MQTT topic.
- For ongoing tasks, the agent publishes status messages periodically to update the network on its current activity.
- Other agents or monitoring tools subscribe to these topics to receive real-time updates via the provided subscription scripts.
- The system handles message filtering, allowing users to listen to all agents or target specific IDs for granular tracking.
MQTT Agent Messenger Setup
To begin, ensure you have an MQTT broker running locally. Then, install the necessary Python dependencies:
pip install paho-mqtt typer
Verify your agent configuration to find your unique ID:
cat ~/.openclaw/openclaw.json
You can then publish an agent introduction using the following command:
python scripts/publish.py intro --agent-id "agent-1" --role "researcher"
MQTT Agent Messenger Data Schema & Taxonomy
The skill organizes its communication using structured topics and metadata to ensure compatibility within Openclaw Skills environments.
| Message Type | Data Fields | Purpose |
|---|---|---|
| Intro | agent-id, role | Identifies the agent and its primary function |
| Status | agent-id, activity, timestamp | Tracks current tasks and active duration |
| Configuration | agent_id (from json) | Ensures local identity matches network ID |
MQTT Agent Messenger Advanced Features
- Support for wildcard subscriptions to monitor entire clusters of agents simultaneously.
- Adjustable wait timers for the subscriber script to control monitoring windows.
- Metadata integration with local Openclaw Skills configuration files for automated identity management.
- Extensible CLI framework allowing for the addition of custom message types beyond standard status updates.
SKILL.md
Loading
Related Openclaw Skills
Foreseek
Foreseek enables natural language trading on prediction markets by matching your beliefs to Kalshi contracts.
Crypto Trading Assistant
A command-line powerhouse for real-time cryptocurrency market analysis, portfolio tracking, and automated price alerting.
Context Bridge
A sophisticated persistent memory layer that enables AI agents to resume complex projects with full context of past conversations and decisions.
Oblien Workspace Runtime
A secure, isolated Firecracker microVM environment providing a robust Internal API for AI agents to manage files, execute commands, and run interactive terminals.
Polymarket AutoTrader
An automated trading bot for Polymarket that uses technical analysis to trade crypto price prediction markets.
News Digest
An intelligent, multi-slot news aggregation system that delivers personalized, AI-summarized briefings based on your specific interests and schedule.