# Hanzo Metrics — Hanzo AI > High-cardinality time-series database for AI metrics metrics.hanzo.ai # Hanzo Metrics The metrics half of Hanzo O11y Metrics used to be its own database here. It is now a subsystem of Hanzo O11y, which serves metrics, logs and traces from one column store — so a counter and the trace that incremented it are one query. Reach for this page when the question is a number over time; the rest of O11y is where that number leads. [Get Started](https://docs.hanzo.ai/docs/metrics)[View on GitHub](https://github.com/hanzoai/metrics) ## What a metric is here A row in a column store rather than a series in a store of its own. ### One store, not four Metrics go where the logs and traces already are — Hanzo Datastore, a column store. Nothing to run beside it and nothing to keep in sync with it. ### PromQL, or the builder Bring the PromQL you already wrote, or assemble the query in the UI without learning it. Both compile to the same thing. ### Labels you would not dare add Per-model, per-route, per-tenant. A column store counts distinct values for a living, so a label that would multiply series in a time-series database is just another column here. ### The number leads somewhere A spike on a chart is the start of a question, not the end. Click it and you are in the traces for that window, because they were never in a different system. ### Alerts are saved queries You write the query, look at it, then keep it as a rule. What pages you is something you have already seen return the answer you expected. ### Scoped to your org Every query carries the org from your token, so one deployment serves many tenants and no panel can read across them. ## Send a metric, then follow it [Read the docs](https://docs.hanzo.ai/docs/metrics)[View on GitHub](https://github.com/hanzoai/metrics) ## Open source License: Apache-2.0[hanzoai/metrics](https://github.com/hanzoai/metrics) ## Get Metrics Time-series metrics [Deploy to Cloud](https://console.hanzo.ai/deploy)[Self-host](https://docs.hanzo.ai/docs/metrics)