End-to-end visibility with execution traces, metrics, and cost tracking. Works locally or with separate monitoring infra.
Components
- OpenTelemetry tracing (Tempo)
- Prometheus metrics (FastAPI, agent metrics)
- Grafana dashboards
What you get
- Trace trees with timing and token usage
- Health checks and live execution status
- Alerts for latency, errors, and budgets
Quick Start tutorial
Ready to build production AI?
Start with the Quick Start guide or explore the API. Join the community and help shape the open-source platform for AI agents.