# Hanzo O11y — Hanzo AI

> Unified AI observability platform: distributed tracing, real-time metrics, structured logs, and profiling for LLMs and agent swarms.

o11y.hanzo.ai

# Hanzo O11y

Traces, metrics and logs, in one place

[View on GitHub](https://github.com/hanzoai/o11y)

O11y — Hanzo

[Logs](https://hanzo.ai/cloud/logs)[Metrics](https://hanzo.ai/metrics)[Dashboards](https://hanzo.ai/dashboards)[O11y](https://hanzo.ai/o11y)[AI Metrics](https://hanzo.ai/cloud/ai-metrics)[Billing](https://hanzo.ai/billing)[Plans & Pricing](https://hanzo.ai/cloud/plans)[Sessions](https://hanzo.ai/cloud/sessions)

- gatewayReady
- payments-apiReady
- checkout-webBuilding
- docs-siteReady

Every request enters here, so the limiter does too.

`api.hanzo.ai/v1/o11y`[Open in the console](https://hanzo.ai/home)

Example project. Every name in it is one you would give your own.

Paste and ship

Paste this into any agent. It reads the skill manifest and calls O11y from there.

Agent promptapi /v1/o11yCopy

```
Read https://hanzo.ai/skill.md and use Hanzo O11y in my project. Start with: hanzo o11y logs get
```

## One store, one query language

Every panel scopes to your org from the token, so a shared deployment still answers one tenant at a time.

01

### Traces and APM

Follow one request across services, queues and databases. Sort by the slow tail rather than the average, and open the span that spent the time.

02

### Metrics

Write PromQL if you already have it, or build the query in the UI if you do not. Both run against the same store the traces are in.

03

### Logs

Search structured logs by field, not by regex over a blob. A span carries the id its log lines were written with, so the pivot is a click.

04

### Exceptions

Errors are grouped and counted rather than listed, so a thousand of the same stack trace is one row with a number on it — and it links to the trace that raised it.

05

### Dashboards and alerts

An alert rule is a saved query, so what fires at three in the morning is something you already looked at. It reaches PagerDuty, Opsgenie, Slack, Teams, email or a webhook.

06

### OpenTelemetry on the wire

OTLP over gRPC on 4317 and HTTP on 4318. Any OTel SDK or collector points at it by setting one endpoint variable — there is no agent of ours to install.

## Point an OTLP endpoint at it

[View on GitHub](https://github.com/hanzoai/o11y)

Related capabilities

[LogsSearch every line](https://hanzo.ai/cloud/logs)[MetricsTime series & SLOs](https://hanzo.ai/metrics)[Dashboards](https://hanzo.ai/dashboards)

## Get O11y

Observability suite

License: Apache-2.0[hanzoai/o11y](https://github.com/hanzoai/o11y)

[Deploy to Cloud](https://platform.hanzo.ai/deploy)