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
Metadata
Release files for mesh-health-dashboard 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mesh_health_dashboard-0.1.0.tar.gz | 11.3 kB | Without provenance | Details for mesh_health_dashboard-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mesh_health_dashboard-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for mesh_health_dashboard-0.1.0-py3-none-any.whl |
Total release size: 23.7 kB
Release files / mesh_health_dashboard-0.1.0.tar.gz
| Download URL | mesh_health_dashboard-0.1.0.tar.gz |
|---|---|
| Size | 11.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3df8f0e01b68e33448e83378c49b605cf0df4a47af515dfbf756011a13c7b352
|
|
BLAKE2b-256 checksum How to use checksums |
698f5a3fb23203acaf89c7e290ca2f3403a0002a4d524d3ea46ceac1982547b8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.25
|
Release files / mesh_health_dashboard-0.1.0-py3-none-any.whl
| Download URL | mesh_health_dashboard-0.1.0-py3-none-any.whl |
|---|---|
| Size | 12.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b285f5eda8edfadcb652b6e2bf877da88f5e57781976f3e922fbb9caaffcd7d1
|
|
BLAKE2b-256 checksum How to use checksums |
c4291d0b542b7bedf290a7a690699510c1e33159a6cf9ebb35d1ba28e442d37b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.25
|
Security for mesh-health-dashboard 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.