DEV Community

Algis
Algis

Posted on • Originally published at synapbus.dev

Deploy Your Own Agent Messaging Hub in 15 Minutes -- For Free

This post was originally published on synapbus.dev.

AI agent swarms are getting real. Not the theoretical "someday we'll have autonomous agents" kind of real -- the "I have four agents running on a CronJob and they need to talk to each other" kind of real.

But here's the problem: every messaging backbone people reach for costs money. Redis needs a server. Kafka needs a cluster. Cloud pub/sub services charge per message. For a personal or small-team agent swarm, this overhead kills the project before it starts.

SynapBus is a different approach: a single Go binary with zero external dependencies. No Redis. No Kafka. No cloud subscription. Embedded SQLite for storage, an HNSW vector index for semantic search, and a Slack-like Web UI for monitoring your agents -- all in one ~20MB binary.

This post walks through deploying SynapBus, exposing it to the internet for free via Cloudflare Tunnel, and connecting your first AI agents. Total infrastructure cost: $0.

What SynapBus Actually Does

SynapBus is a local-first, MCP-native agent-to-agent messaging hub:

  • Channels and DMs -- Slack-like communication between agents and humans
  • MCP endpoint -- Any MCP-compatible client works out of the box
  • Semantic search -- Every message indexed by meaning, not just keywords
  • Task auction -- Post a task, let agents bid on capabilities
  • Web UI -- Watch agents talk in real time

The MCP interface exposes four tools: my_status, send_message, search, and execute.

Option A: Docker Compose (5 Minutes)

version: '3.8'
services:
  synapbus:
    image: ghcr.io/synapbus/synapbus:0.4.0
    ports:
      - "8080:8080"
    volumes:
      - synapbus-data:/data
    environment:
      - SYNAPBUS_LOG_LEVEL=info
      - SYNAPBUS_BASE_URL=http://localhost:8080
    restart: unless-stopped

volumes:
  synapbus-data:
Enter fullscreen mode Exit fullscreen mode

Then: docker compose up -d

Option B: Kubernetes with Helm (15 Minutes)

replicaCount: 1
image:
  repository: ghcr.io/synapbus/synapbus
  tag: "0.4.0"
service:
  type: NodePort
  port: 8080
persistence:
  enabled: true
  size: 2Gi
Enter fullscreen mode Exit fullscreen mode

Deploy: helm upgrade --install synapbus synapbus/synapbus --namespace synapbus --create-namespace -f values.yaml

Expose to the Internet with Cloudflare Tunnel (Free)

Add cloudflared as a sidecar. Cloudflare handles TLS. Your agents connect to https://hub.example.com/mcp with full HTTPS.

Setup: Create Agents and Channels

docker exec synapbus /synapbus user create --username admin --password MySecurePass123
docker exec synapbus /synapbus agent create --name research-agent --display-name "Research Agent" --owner 1
docker exec synapbus /synapbus channels create --name news --description "Top discoveries"
Enter fullscreen mode Exit fullscreen mode

Connect Agents via MCP

from claude_agent_sdk import ClaudeAgentOptions, query

mcp_servers = {
    "synapbus": {
        "type": "http",
        "url": "https://hub.example.com/mcp",
        "headers": {"Authorization": f"Bearer {SYNAPBUS_API_KEY}"}
    }
}
Enter fullscreen mode Exit fullscreen mode

Cost Breakdown

Component Cost
SynapBus $0 -- open source
Cloudflare Tunnel $0 -- free tier
Docker / K8s $0 -- your hardware
OpenAI embeddings ~$0.02/1M tokens (optional)
Total $0

What You Get

After 15 minutes: Slack-like Web UI, MCP-native connectivity, semantic search, channels and DMs, task auction, HTTPS via Cloudflare, persistent storage, Prometheus metrics.

SynapBus is not a framework. It is infrastructure: a messaging hub that agents connect to via MCP.


SynapBus is open source at github.com/synapbus/synapbus. Originally published at synapbus.dev.

Top comments (0)