Discover / LLM Ops & Observability
OpenInference
by Arize-aiPython
Open standard for instrumenting LLM applications to capture traces and spans for observability.
Maturity: stable because 3y old, python-openinference-instrumentation-agno-v1.0.1 released 3d ago. Derived from release and commit history, not a rating.
- Stars
- 1.1k
- Forks
- 284
- Downloads / mo
- 1.6M
- Last commit
- 2026-08-03
- License
- Apache-2.0
- Open issues
- 239
Market and trust evidence
Edition not yet matchedNo exact skills.sh identity match is available for this repository. Repository adoption and freshness remain visible above; install momentum is not inferred.
Trust analysis is a screening signal, not a security warranty. Read the ranking and trust methodology.
In practice
Written by AI from this repository’s README · medium confidenceLLM calls, retrievals and tool use do not map onto generic tracing conventions, so spans carry no useful detail.
Use it when
Use it when you want standard spans for LLM apps that any OpenTelemetry compatible backend can consume.
Not the right pick when
It is a monorepo of many per framework packages rather than one install, so you pick the instrumentations you need.
Capabilities
- semantic conventions for tracing LLM applications
- instrumentations for popular ML SDKs and frameworks
- packages across Python, JavaScript, Java and Go
- works with any OpenTelemetry compatible backend
- specification kept in markdown in the spec directory
Cost: Free and open source
Install
Derived from the published package name in the repository, not from a model.
Video walkthroughs
Third-party YouTube uploads matched to this tool by title, channel and repository name on 2026-08-03. Not made, reviewed or endorsed by SkillPilot. View counts and publish months are as of the match date and the month is approximate. Nothing loads from YouTube until you press play.
What the repository ships
Detected from the actual files in the repository root.
Latest release python-openinference-instrumentation-agno-v1.0.1
Published 2026-07-31
Tags
README
<p align="center">
<img alt="OpenInference" src="https://raw.githubusercontent.com/Arize-ai/phoenix-assets/main/logos/OpenInference/Full%20color/OI-full-horiz.svg" width="40%" height="100%" />
</p>
<p align="center">
<a href="https://arize-ai.github.io/openinference/spec/">
<img src="https://img.shields.io/static/v1?message=Spec&logo=data:image/png;base64,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&labelColor=grey&color=blue&logoColor=white&label=%20"/>
</a>
<a target="_blank" href="https://join.slack.com/t/arize-ai/shared_invite/zt-1px8dcmlf-fmThhDFD_V_48oU7ALan4Q">
<img src="https://img.shields.io/static/v1?message=Community&logo=slack&labelColor=grey&color=blue&logoColor=white&label=%20"/>
</a>
</p>
OpenInference is a set of conventions and plugins that is complimentary to OpenTelemetry to
enable tracing of AI applications. OpenInference is natively supported
by Arize Phoenix and Arize AX, but can be used with any OpenTelemetry-compatible backend as
well.
Specification
The OpenInference specification is edited in markdown files found in the spec directory. It's designed to
provide insight into the invocation of LLMs and the surrounding application context such as retrieval from vector stores
and the usage of external tools such as search engines or APIs. The specification is transport and file-format agnostic,
and is intended to be used in conjunction with other specifications such as JSON, ProtoBuf, and DataFrames.
Instrumentation
OpenInference provides a set of instrumentations for popular machine learning SDKs and frameworks in a variety of
languages.
Python
Libraries
| Package | Description | Version |
|-------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| openinference-semantic-conventions | Semantic conventions for tracing of LLM Apps. | PyPI Version |
| openinference-instrumentation | Reusable utilities, decorators, configurations, and helpers for instrumentation. | PyPI Version |
| openinference-instrumentation-agno | OpenInference Instrumentation for Agno Agents. | PyPI Version |
| openinference-instrumentation-openai | OpenInference Instrumentation for OpenAI SDK. | PyPI Version |
| openinference-instrumentation-openai-agents | OpenInference Instrumentation for OpenAI Agents SDK. | PyPI Version |
| openinference-instrumentation-claude-agent-sdk | OpenInference Instrumentation for Claude Agent SDK. | PyPI Version |
| openinference-instrumentation-llama-index | OpenInference Instrumentation for LlamaIndex. | PyPI Version |
| openinference-instrumentation-dspy | OpenInference Instrumentation for DSPy. | PyPI Version |
| openinference-instrumentation-bedrock | OpenInference Instrumentation for AWS Bedrock. | PyPI Version |
| openinference-instrumentation-langchain | OpenInference Instrumentation for LangChain. | PyPI Version |
| openinference-instrumentation-mcp | OpenInference Instrumentation for MCP. | PyPI Version |
| openinference-instrumentation-mistralai | OpenInference Instrumentation for MistralAI. | PyPI Version |
| openinference-instrumentation-portkey | OpenInference Instrumentation for Portkey. | PyPI Version |
| openinference-instrumentation-guardrails | OpenInference Instrumentation for Guardrails. | PyPI Version |
| openinference-instrumentation-vertexai | OpenInference Instrumentation for VertexAI. | PyPI Version |
| openinference-instrumentation-crewai | OpenInference Instrumentation for CrewAI. | PyPI Version |
| openinference-instrumentation-haystack | OpenInference Instrumentation for Haystack. | PyPI Version |
| openinference-instrumentation-litellm | OpenInference Instrumentation for liteLLM. | PyPI Version |
| openinference-instrumentation-groq | OpenInference Instrumentation for Groq. | PyPI Version |
| openinference-instrumentation-instructor | OpenInference Instrumentation for Instructor. | PyPI Version |
| openinference-instrumentation-anthropic | OpenInference Instrumentation for Anthropic. | PyPI Version |
| openinference-instrumentation-beeai | OpenInference Instrumentation for BeeAI. | PyPI Version |
| openinference-instrumentation-google-genai | OpenInference Instrumentation for Google GenAI. | PyPI Version
Truncated. Read the full README on GitHub ↗