Specification
The OpenInference specification defines how an AI application is recorded as an OpenTelemetry trace: which span kinds mark LLM calls, agents, tools, retrievers and embeddings, and which attributes hold their inputs, outputs, token counts and metadata. Every instrumentation follows it, so a trace reads the same whichever framework or language produced it.
Instrumentation
Instrumentation libraries trace popular model providers and agent frameworks automatically, following the specification. They are available for Python, JavaScript, Java and Go.
Python
Libraries
| Package | Description | Version |
|---|---|---|
openinference-semantic-conventions |
Semantic conventions for tracing of LLM Apps. | |
openinference-instrumentation |
Reusable utilities, decorators, configurations, and helpers for instrumentation. | |
openinference-instrumentation-agno |
OpenInference Instrumentation for Agno Agents. | |
openinference-instrumentation-ag2 |
OpenInference Instrumentation for AG2. | |
openinference-instrumentation-openai |
OpenInference Instrumentation for OpenAI SDK. | |
openinference-instrumentation-openai-agents |
OpenInference Instrumentation for OpenAI Agents SDK. | |
openinference-instrumentation-claude-agent-sdk |
OpenInference Instrumentation for Claude Agent SDK. | |
openinference-instrumentation-llama-index |
OpenInference Instrumentation for LlamaIndex. | |
openinference-instrumentation-dspy |
OpenInference Instrumentation for DSPy. | |
openinference-instrumentation-bedrock |
OpenInference Instrumentation for AWS Bedrock. | |
openinference-instrumentation-langchain |
OpenInference Instrumentation for LangChain. | |
openinference-instrumentation-mcp |
OpenInference Instrumentation for MCP. | |
openinference-instrumentation-mistralai |
OpenInference Instrumentation for MistralAI. | |
openinference-instrumentation-portkey |
OpenInference Instrumentation for Portkey. | |
openinference-instrumentation-guardrails |
OpenInference Instrumentation for Guardrails. | |
openinference-instrumentation-vertexai |
OpenInference Instrumentation for VertexAI. | |
openinference-instrumentation-crewai |
OpenInference Instrumentation for CrewAI. | |
openinference-instrumentation-haystack |
OpenInference Instrumentation for Haystack. | |
openinference-instrumentation-litellm |
OpenInference Instrumentation for liteLLM. | |
openinference-instrumentation-groq |
OpenInference Instrumentation for Groq. | |
openinference-instrumentation-instructor |
OpenInference Instrumentation for Instructor. | |
openinference-instrumentation-anthropic |
OpenInference Instrumentation for Anthropic. | |
openinference-instrumentation-beeai |
OpenInference Instrumentation for BeeAI. | |
openinference-instrumentation-google-genai |
OpenInference Instrumentation for Google GenAI. | |
openinference-instrumentation-google-adk |
OpenInference Instrumentation for Google ADK. | |
openinference-instrumentation-autogen-agentchat |
OpenInference Instrumentation for Microsoft Autogen AgentChat. | |
openinference-instrumentation-pydantic-ai |
OpenInference Instrumentation for PydanticAI. | |
openinference-instrumentation-smolagents |
OpenInference Instrumentation for smolagents. | |
openinference-instrumentation-pipecat |
OpenInference Instrumentation for Pipecat. | |
openinference-instrumentation-agentspec |
OpenInference Instrumentation for Open Agent Specification. | |
openinference-instrumentation-strands-agents |
OpenInference Instrumentation for Strands Agents. | |
openinference-instrumentation-together |
OpenInference Instrumentation for Together AI. | |
openinference-instrumentation-typesafe |
OpenInference Instrumentation for TypeSafe AI. | |
openinference-instrumentation-ollama |
OpenInference Instrumentation for Ollama. | |
openinference-instrumentation-cohere |
OpenInference Instrumentation for Cohere. |
Span Processors
Normalize and convert data across other instrumentation libraries by adding span processors that unify data.
| Package | Description | Version |
|---|---|---|
openinference-instrumentation-openlit |
OpenInference Span Processor for OpenLIT traces. | |
openinference-instrumentation-openllmetry |
OpenInference Span Processor for OpenLLMetry (Traceloop) traces. |
Examples
| Name | Description | Complexity Level |
|---|---|---|
| Agno | Agno agent examples | Beginner |
| OpenAI SDK | OpenAI Python SDK, including chat completions and embeddings | Beginner |
| Claude Agent SDK | Claude Agent SDK | Beginner |
| MistralAI SDK | MistralAI Python SDK | Beginner |
| VertexAI SDK | VertexAI Python SDK | Beginner |
| LlamaIndex | LlamaIndex query engines | Beginner |
| DSPy | DSPy primitives and custom RAG modules | Beginner |
| Boto3 Bedrock Client | Boto3 Bedrock client | Beginner |
| LangChain | LangChain primitives and simple chains | Beginner |
| LiteLLM | A lightweight LiteLLM framework | Beginner |
| LiteLLM Proxy | LiteLLM Proxy to log OpenAI, Azure, Vertex, Bedrock | Beginner |
| Groq | Groq and AsyncGroq chat completions | Beginner |
| Together AI | Together and AsyncTogether chat completions, streaming, and tool calls | Beginner |
| TypeSafe AI | TypeSafeClient and AsyncTypeSafeClient System One calls (Noul, Choice, Score) | Beginner |
| Anthropic | Anthropic Messages client | Beginner |
| BeeAI | Agentic instrumentation in the BeeAI framework | Beginner |
| Haystack | A Haystack QA RAG application | Intermediate |
| OpenAI Agents | OpenAI Agents with handoffs | Intermediate |
| Autogen AgentChat | Microsoft Autogen Assistant Agent and Team Chat | Intermediate |
| AG2 | AG2 tool calling, group chats, and sequential chats | Intermediate |
| PydanticAI | PydanticAI agent examples | Intermediate |
| Pipecat | Pipecat application examples | Intermediate |
| Ollama | Ollama chat, streaming, and tool calls | Beginner |
| Cohere | Cohere ClientV2 chat completions | Beginner |
JavaScript
Libraries
| Package | Description | Version |
|---|---|---|
@arizeai/openinference-semantic-conventions |
Semantic conventions for tracing of LLM Apps. | |
@arizeai/openinference-core |
Reusable utilities, configuration, and helpers for instrumentation. | |
@arizeai/openinference-instrumentation-bedrock |
OpenInference Instrumentation for AWS Bedrock. | |
@arizeai/openinference-instrumentation-bedrock-agent-runtime |
OpenInference Instrumentation for AWS Bedrock Agent Runtime. | |
@arizeai/openinference-instrumentation-beeai |
OpenInference Instrumentation for BeeAI. | |
@arizeai/openinference-instrumentation-langchain |
OpenInference Instrumentation for LangChain.js. | |
@arizeai/openinference-instrumentation-mcp |
OpenInference Instrumentation for MCP. | |
@arizeai/openinference-instrumentation-openai |
OpenInference Instrumentation for OpenAI SDK. | |
@arizeai/openinference-instrumentation-anthropic |
OpenInference Instrumentation for the Anthropic SDK. | |
@arizeai/openinference-instrumentation-claude-agent-sdk |
OpenInference Instrumentation for Claude Agent SDK. | |
@arizeai/openinference-vercel |
OpenInference Support for Vercel AI SDK. | |
@arizeai/openinference-tanstack-ai |
OpenInference middleware for TanStack AI. | |
@arizeai/openinference-genai |
OpenInference Support for GenAI conventions | |
@arizeai/openinference-instrumentation-typesafe |
OpenInference Instrumentation for the TypeSafe AI SDK. |
Examples
| Name | Description | Complexity Level |
|---|---|---|
| TypeSafe AI | Classification, structured questions, and confidence-gated routing to an LLM | Beginner |
Java
Libraries
| Package | Description | Version |
|---|---|---|
openinference-semantic-conventions |
Semantic conventions for tracing of LLM Apps. | |
openinference-instrumentation |
Base instrumentation utilities. | |
openinference-instrumentation-langchain4j |
OpenInference Instrumentation for LangChain4j. | |
openinference-instrumentation-springAI |
OpenInference Instrumentation for Spring AI. | |
openinference-instrumentation-annotation |
Annotation-based manual tracing with ByteBuddy. | |
openinference-instrumentation-adk-java |
OpenInference Instrumentation for Google ADK Java (-javaagent). |
Examples
| Name | Description | Complexity Level |
|---|---|---|
| LangChain4j Example | Simple example using LangChain4j with OpenAI | Beginner |
| Spring AI Example | Spring AI example with OpenAI and tool calling | Beginner |
| Annotation Example | Annotation-based tracing with @Chain, @LLM, @Tool, @Agent |
Beginner |
| Programmatic Example | Manual tracing with typed span classes (LLMSpan, AgentSpan, etc.) |
Beginner |
| ADK Java Example | Google ADK for Java agent with a function tool, traced by the ADK -javaagent |
Beginner |
Go
Libraries
| Package | Description | Version |
|---|---|---|
openinference-semantic-conventions |
Semantic conventions for tracing of LLM Apps. | go get github.com/Arize-ai/openinference/go/openinference-semantic-conventions |
openinference-instrumentation |
Suppression, context attribute propagation, and TraceConfig masking. Honors OPENINFERENCE_HIDE_* env vars. |
go get github.com/Arize-ai/openinference/go/openinference-instrumentation |
openinference-instrumentation-anthropic-sdk-go |
OpenInference Instrumentation for the Anthropic Go SDK (anthropics/anthropic-sdk-go). |
go get github.com/Arize-ai/openinference/go/openinference-instrumentation-anthropic-sdk-go |
openinference-instrumentation-openai-go |
OpenInference Instrumentation for the official OpenAI Go SDK (openai/openai-go). |
go get github.com/Arize-ai/openinference/go/openinference-instrumentation-openai-go |
Requires Go 1.25+. Pair with arize-otel-go for the one-line OTLP/HTTP setup to Arize AX, or wire up any OTel exporter (e.g. Phoenix at http://localhost:6006/v1/traces).
Supported Destinations
OpenInference traces are standard OpenTelemetry traces, so they can be sent to any backend that accepts OTLP.
- Arize Phoenix: open source, with native OpenInference support.
- Arize AX: native OpenInference support.
- Dynatrace: OpenInference support in Dynatrace AI Observability.
- Any OpenTelemetry collector or OTLP-compatible backend.
Community
Questions, bug reports and ideas are welcome.
- Report bugs and request features in GitHub Issues.
- Star the repository on GitHub.