# Hanzo Telemetry — Hanzo AI

> OpenTelemetry-native data collector and stream pipeline purpose-built for high-throughput AI agent workloads and cloud telemetry.

telemetry.hanzo.ai

# Hanzo Telemetry

The collector that sits between your app and wherever the data goes

Your services talk to it instead of talking to a backend. It receives OTLP, batches it, holds a memory ceiling so a traffic spike cannot take the host down with it, and forwards onward. Change where the data goes by editing its config — not by redeploying every service that produces the data.

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

One hop you control

- OTLP in, OTLP out01
- Traces, metrics and logs02
- Batching03
- A memory ceiling04
- Assembled, not installed05
- It runs where you run06

Receives over gRPC and HTTP, exports the same way. OTLP is the format the OpenTelemetry SDKs already speak, so nothing in your code changes to point at it.

All three move through the same process, so there is one thing to run, one config to read and one place to look when telemetry stops arriving.

Spans arrive one at a time and leave in batches. That is the difference between a request per span and a request per few thousand, and your backend feels it.

Tell it how much memory it may use and it refuses work rather than exceeding it. Telemetry is the thing that should degrade during an incident, not the thing that causes one.

This is the collector itself. Build a distribution with the receivers, processors and exporters you actually want, and ship one binary containing those and nothing else.

A binary in your own network. Whatever you decide not to forward, you decide before the data has left — which is the only point where that is still your call.

Paste and ship

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

Agent promptCopy

```
Read https://hanzo.ai/skill.md and use Hanzo Telemetry in my project.
```

## Put it in front of your backend

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

## Get Telemetry

OpenTelemetry ingest

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

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