openinference-instrumentation-google-adk
OpenInference Google ADK Instrumentation
Decision gist · record as of 2026-08-14
Yes, if you are building or operating Google ADK agents with Gemini and need observability. The package is actively maintained, has no known vulnerabilities, low install friction, and integrates seamlessly with standard OpenTelemetry tooling. Install it alongside a tracing backend (Phoenix or Arize AX) to gain immediate visibility into agent behavior.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires GOOGLE_API_KEY environment variable to authenticate with Gemini API; also requires a tracing backend (e.g., Arize Phoenix or OpenTelemetry collector) to receive and view traces.
- Low friction: pure Python wheel with seven stable runtime dependencies (opentelemetry-api, opentelemetry-instrumentation, wrapt, and OpenInference libraries).
- Active maintenance—released 2 days ago with last commit 2026-08-14—and supports Python 3.10 through 3.14.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production and internal projects.
last release 2026-08-12 (2 days) · last repo commit 2026-08-14 · 1,147 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 551,904 downloads/mo, #6,045 on PyPI
Alternatives
Verify before relying
pip install openinference-instrumentation-google-adk
from openinference.instrumentation.google_adk import GoogleADKInstrumentor
from opentelemetry.sdk import trace as trace_sdk
tracer_provider = trace_sdk.TracerProvider()
GoogleADKInstrumentor().instrument(tracer_provider=tracer_provider)- Whether this package works with Google ADK versions other than those tested in CI/CD
- Performance overhead when instrumenting high-volume agent workloads
- Compatibility with custom Google ADK extensions or third-party agent frameworks
What it is and what it does
This package wraps Google ADK agent execution to automatically capture traces compatible with OpenTelemetry. It instruments agent initialization, tool calls, LLM requests to Gemini, and response generation, emitting structured span data that can be sent to observability backends like Arize Phoenix or Arize AX for visualization and debugging.
The instrumentation is applied via a single `GoogleADKInstrumentor().instrument()` call that attaches to your tracer provider. Once active, it requires no changes to your agent code—traces flow automatically to any OpenTelemetry exporter you configure. It depends on opentelemetry-api, opentelemetry-instrumentation, and OpenInference semantic conventions to ensure traces follow standard LLM observability patterns.
Use it for
- Debug multi-step agent workflows by viewing the full trace of tool calls, LLM prompts, and responses in Phoenix or Arize AX.
- Monitor production Gemini agents to detect latency bottlenecks, tool failures, or unexpected LLM behavior.
- Collect structured telemetry from agent sessions for post-hoc analysis, cost attribution, or quality audits.
- Integrate agent observability into existing OpenTelemetry infrastructure without rewriting agent code.
- Track session metadata and user interactions alongside agent execution for end-to-end observability.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building or operating Google ADK agents with Gemini and need observability.
The package is actively maintained, has no known vulnerabilities, low install friction, and integrates seamlessly with standard OpenTelemetry tooling. Install it alongside a tracing backend (Phoenix or Arize AX) to gain immediate visibility into agent behavior.
Install
openinference-instrumentation-google-adk on PyPI
Before you install
Low friction: pure Python wheel with seven stable runtime dependencies (opentelemetry-api, opentelemetry-instrumentation, wrapt, and OpenInference libraries). Active maintenance—released 2 days ago with last commit 2026-08-14—and supports Python 3.10 through 3.14.
Requires GOOGLE_API_KEY environment variable to authenticate with Gemini API; also requires a tracing backend (e.g., Arize Phoenix or OpenTelemetry collector) to receive and view traces.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production and internal projects.
Quickstart
pip install openinference-instrumentation-google-adk
from openinference.instrumentation.google_adk import GoogleADKInstrumentor
from opentelemetry.sdk import trace as trace_sdk
tracer_provider = trace_sdk.TracerProvider()
GoogleADKInstrumentor().instrument(tracer_provider=tracer_provider)Verify before relying
- Whether this package works with Google ADK versions other than those tested in CI/CD
- Performance overhead when instrumenting high-volume agent workloads
- Compatibility with custom Google ADK extensions or third-party agent frameworks
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesopeninference-instrumentationopeninference-semantic-conventionsopentelemetry-apiopentelemetry-instrumentationopentelemetry-semantic-conventionstyping-extensionswrapt |
| Maintenance | Actively maintained 2 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 551,904 / month, #6,045 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: openinference_instrumentation_google_adk-0.1.20-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “google adk instrumentation”
- openinference-instrumentation-google-adkAuto-instruments Google ADK applications to emit…
- ag_ui_adkBridges Google ADK agents to the AG-UI Protocol, enabling ADK-built…
- toolbox-adkEnables Google ADK agents to natively use tools from the MCP Toolbox…
Give your agent the search over MCP, or paste the wish link into any chat.
More Monitoring packages
Wraps any iterable to display a real-time progress bar in the terminal or Jupyter notebook, showing iteration count, elapsed time, and estimated time remaining.
Provides generated Python code for OpenTelemetry semantic conventions, enabling standardized attribute naming and constant definitions for instrumentation and telemetry collection.
Install it if you are using OpenTelemetry and want to follow semantic conventions correctly.
Provides the reference implementation of the OpenTelemetry API for collecting and exporting traces, metrics, and logs from Python applications.
Provides the abstract API and interfaces for OpenTelemetry instrumentation in Python, defining how to emit traces, metrics, and logs without tying code to a specific SDK implementation.
Exports OpenTelemetry observability data to an OpenTelemetry Collector using Protobuf-encoded messages over HTTP.
Install it if you are using OpenTelemetry in Python and need to send data to a Collector over HTTP.
Provides automatic instrumentation commands and programmatic APIs to inject distributed tracing into Python applications without code changes, detecting and instrumenting packages used by your program.
Install it if you need distributed tracing without code changes and have compatible instrumented packages in your environment.
See also openinference-instrumentation-agno · openinference-instrumentation-claude-agent-sdk · openinference-instrumentation-google-genai · openinference-instrumentation-openai · openinference-instrumentation-langchain · openinference-instrumentation-openai-agents · openinference-instrumentation-pydantic-ai · openinference-instrumentation-mcp · ag_ui_adk · openinference-instrumentation-portkey