---
title: Google ADK
description: >-
  Monitor agent invocations, cost metrics, and evaluations of your Google Agent
  Development Kit (ADK) stack.
breadcrumbs: Docs > Integrations > Google ADK
---

# Google ADK
Supported OS Integration version1.0.0Visualize LLM Observability traces for AI Agents using Google ADK.
## Overview{% #overview %}

Use the Google Agent Development Kit (ADK) integration to monitor, troubleshoot, and evaluate your applications that use [Google ADK](https://google.github.io/adk-docs/) with LLM Observability.

[Datadog LLM Observability](https://www.datadoghq.com/product/llm-observability/) helps AI engineers, data scientists, and application developers quickly develop, evaluate, and monitor LLM applications. Confidently improve output quality, performance, costs, and overall risk with structured experiments, end-to-end tracing across AI agents, and evaluations.

The Google ADK auto-instrumentation allows you to:

- Visualize LLM calls with their associated token usage and costs
- See tool calls made by your application, with their respective inputs and outputs, including code execution tools
- Observe handoffs between different agents in your agentic stack

## Setup{% #setup %}

1. Install the `ddtrace` package:

   ```
   pip install ddtrace
   ```

1. Run your application using the `ddtrace-run` command to initialize the LLM Observability auto-instrumentation:

   ```
   DD_API_KEY=<YOUR_DD_API_KEY> DD_SITE=<YOUR_DD_SITE> DD_LLMOBS_ENABLED=true DD_LLMOBS_AGENTLESS_ENABLED=true DD_LLMOBS_ML_APP=<YOUR_ML_APP_NAME> ddtrace-run <YOUR-APP>.js
   ```

1. (Optional) If using the Datadog Agent, ensure it is running with the following command:

   ```gdscript3
   docker run -d \
       --cgroupns host \
       --pid host \
       -v /var/run/docker.sock:/var/run/docker.sock:ro \
       -v /proc/:/host/proc/:ro \
       -v /sys/fs/cgroup/:/host/sys/fs/cgroup:ro \
       -e DD_API_KEY=<DATADOG_API_KEY> \
       -p 127.0.0.1:8126:8126/tcp \
       -p 127.0.0.1:8125:8125/udp \
       -e DD_DOGSTATSD_NON_LOCAL_TRAFFIC=true \
       -e DD_APM_ENABLED=true \
       gcr.io/datadoghq/agent:latest
   ```

1. Before running your application with the Agent, unset the `DD_LLMOBS_AGENTLESS_ENABLED`, `DD_SITE`, and `DD_API_KEY` environment variables.

## Uninstallation{% #uninstallation %}

You can disable LLM Observability and its auto-instrumentation for Google ADK by removing all `DD_LLMOBS` environment variables and removing the `ddtrace-run` command from your application's initialization.

## Support{% #support %}

Need help? Contact [Datadog Support](https://app.datadoghq.com/help).

## Further Reading{% #further-reading %}

- [Automatic Instrumentation for LLM Observability](https://docs.datadoghq.com/llm_observability/instrumentation/auto_instrumentation?tab=python#google-adk)
- [Agent Development Kit (ADK)](https://google.github.io/adk-docs/)