Agent Message Bus: Communication Infrastructure for 16 AI Agents

Source: Dev.to

Agent Message Bus Born: Communication Infrastructure for 16 AI Agents

When your AI Agent count grows from 3 to 16, communication becomes urgent business.

Why a Message Bus?

OpenClaw’s built-in agentToAgent communication has a critical limitation: it only works within the same Gateway instance. When the main agent tries to message a learning agent on a different machine, an instant error occurs.

• Telegram group relay and Redis Pub/Sub were both considered.
• The former lacks format control, the latter is overkill.

Final decision: build a lightweight message bus with the following requirements:

• HTTP API
• Multi‑Agent registration
• Message persistence
• Simplicity

Tech Stack: Flask + SQLite

• Flask – chosen for familiarity and lightness.
• SQLite – zero additional services, single‑file storage, easy backups.

Deployed on a T440 (192.168.x.x:8091).

API Design

Six endpoints, keeping it minimal:

POST   /send      # Send messages (specific recipient or broadcast)
GET    /inbox     # View inbox with unread filtering
GET    /history   # View history with time‑range queries
POST   /ack       # Mark messages as read
GET    /agents    # List registered agents
GET    /stats     # System statistics

Key Features

• Broadcast: Omit the to field to send to all registered agents.
• Reply chains: reply_to field tracks conversation context.
• Priority: normal / high / urgent levels.
• Read receipts: Confirm processing via ack.

Pitfalls

• SQLite concurrency: Setting journal_mode=WAL solved occasional lock issues.
• Message accumulation: Auto‑archive read messages older than 7 days.
• Heartbeat: Agents inactive for 5+ minutes are marked offline; queued messages are auto‑pushed on reconnect.

Reflections

An AI Agent’s value isn’t in individual strength but in efficient collaboration.

Flask + SQLite may look “primitive,” but for a dozen agents on an internal network it is simple, stable, and maintainable. The smallest solution that solves the problem is the best solution.