# Arize-ai/openinference

OpenTelemetry Instrumentation for AI Observability

Repository: https://github.com/Arize-ai/openinference
Canonical: https://ross.abutalabs.com/products/openinference
Homepage: https://arize-ai.github.io/openinference/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llmops, telemetry, aiops, llms, opentelemetry, tracing, hacktoberfest, haystack, langchain, langraph, llamaindex, openai, vercel, vertex, smolagents, openai-agents, mcp, gemini, pydantic-ai
Last push: 2026-09-02T23:35:52+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 70
- inputs: {"age_days": 981, "days_push": 0, "days_rel": 1, "gap_med": 0, "n_releases_24m": 962}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1194, forks 303 (observed 2026-09-03T02:15:04.995348+00:00)

## What it is
OpenInference is a set of OpenTelemetry-based conventions and instrumentation plugins for tracing AI and LLM applications. It provides packages that instrument popular SDKs like OpenAI, LangChain, and LlamaIndex, exporting traces to any OpenTelemetry-compatible backend such as Arize Phoenix.

## Use cases
- trace llm calls in my python app
- instrument langchain with opentelemetry
- monitor llm application performance
- add observability to rag pipelines
- trace llamaindex retrieval and tool usage
- export ai app traces to phoenix or any otel backend

## When to choose
- you need standardized OpenTelemetry tracing for LLM apps
- you use supported frameworks like LangChain, LlamaIndex, or OpenAI SDK
- you want vendor-neutral AI observability exportable to any OTel backend

## When to avoid
- you need a full observability UI rather than instrumentation libraries
- your stack uses languages or frameworks without an available instrumentation package

## Facets
- artifact type: library
- maturity: active
- function: tracing, monitoring, sdk
- domain: large-language-models, developer-tools, monitoring
- platform: python, cross-platform
- tags: opentelemetry, llm-observability, llmops, instrumentation, semantic-conventions, ai-agents

## Member repositories
- Arize-ai/openinference (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:04.995348+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:26:10.227958+00:00, confidence not recorded.
  - readme: https://github.com/Arize-ai/openinference (fetched 2026-09-03T02:15:04.995348+00:00, sha 0051cfbc6d57)
  - homepage: https://arize-ai.github.io/openinference/ (fetched 2026-08-29T12:33:01.507383+00:00, sha de2a75f34378)
- Data as of 2026-08-30T08:39:29.467469+00:00.