OpenInference
OpenTelemetry-compatible conventions and auto-instrumentation packages for tracing LLM calls, retrieval, tools and agent frameworks.
Tags
Description
OpenInference is a specification plus a set of instrumentation plugins, complementary to OpenTelemetry, for tracing AI applications: LLM invocations, vector-store retrieval and external tool calls. Python packages cover OpenAI, the OpenAI Agents SDK, Claude Agent SDK, Anthropic, LangChain, LlamaIndex, DSPy, CrewAI, Google ADK, PydanticAI, smolagents, Strands Agents, MCP and more; JavaScript and Java instrumentations also exist. Span processors convert OpenLIT and OpenLLMetry traces into OpenInference form. Natively supported by Arize Phoenix and Arize AX, but works with any OTel backend.
Agent access
Related
- Arize Phoenix: Open-source AI observability and evaluation platform from Arize.
- Arize AX: Arize's commercial platform for agent observability, evaluation, tracing and experimentation, from a free tier to self-hosted.
- OpenTelemetry GenAI Semantic Conventions: OpenTelemetry conventions for spans, metrics and events emitted by GenAI clients, MCP and model providers, for interoperable agent observability.
- OpenLLMetry: Traceloop's open-source observability for GenAI/LLM applications, built on OpenTelemetry.
- OpenLIT: Open-source, OpenTelemetry-native platform for AI agents: tracing, evals, guardrails, prompt hub, vault, and cost and GPU monitoring; self-host free.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)