mesh-health-dashboard

Real-time observability for multi-agent AI workflows. Monitor agent communication, task completion, token usage, and budget health in one dashboard.

What is this?

mesh-health-dashboard is a lightweight observability layer for ZachOS's AI agent mesh infrastructure. It provides real-time visibility into agent interactions, resource consumption, and cost metrics—helping you debug workflow bottlenecks, prevent budget overruns, and optimize task routing without friction. Deploy it alongside your existing agents and start monitoring immediately.

Features

• Real-time Agent Monitoring – Track communication patterns, task completion rates, and agent health status
• Token & Cost Tracking – Monitor token consumption and budget spend across your mesh with configurable alerts
• Task Routing Insights – Visualize task distribution and identify routing inefficiencies
• Multi-agent Debugging – Inspect agent interactions and workflow execution traces
• Zero-friction Deployment – Docker Compose setup ready to run alongside your infrastructure
• REST API – Programmatic access to metrics and health data
• Lightweight Database – Embedded metrics storage with minimal operational overhead

Quick Start

Prerequisites

• Docker & Docker Compose
• Python 3.10+ (for local development)

Installation

Via Docker Compose (Recommended)

docker-compose up -d

The dashboard will be available at http://localhost:8000.

Local Development

# Install dependencies
pip install -e .

# Configure your mesh connection
export MESH_API_URL="http://your-mesh-endpoint:5000"

# Start the server
python -m mesh_health_dashboard.app

Usage

View the Dashboard

Navigate to http://localhost:8000 after startup. The dashboard displays:

• Active agents and their current tasks
• Real-time token consumption
• Budget utilization and alerts
• Communication topology between agents

Query Metrics via API

# Get agent status
curl http://localhost:8000/api/agents

# Get token usage summary
curl http://localhost:8000/api/metrics/tokens

# Get task completion rate
curl http://localhost:8000/api/metrics/tasks

Configuration

Create a .env file or edit src/mesh_health_dashboard/config.py:

MESH_API_URL=http://localhost:5000
BUDGET_LIMIT=1000
ALERT_TOKEN_THRESHOLD=80
DATABASE_PATH=./data/metrics.db

Tech Stack

• Backend: FastAPI (Python)
• Database: SQLite
• Frontend: HTML5 + JavaScript (responsive, no build step)
• Containerization: Docker & Docker Compose
• Testing: pytest

License

MIT