openllmetry and openinference
These are ecosystem siblings—both are OpenTelemetry-based instrumentation frameworks for LLM observability, with OpenInference defining the semantic conventions and data schema while OpenLLMetry provides a more feature-rich implementation that builds upon those standards.
About openllmetry
traceloop/openllmetry
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Provides pre-built OpenTelemetry instrumentations for 10+ LLM providers (OpenAI, Anthropic, Cohere, Gemini) and vector databases (Pinecone, Weaviate, Qdrant), plus a lightweight SDK for automatic trace collection. Traces export to 25+ observability backends including Datadog, Honeycomb, and New Relic via standard OpenTelemetry protocols, or directly to the Traceloop platform for LLM-specific analysis.
About openinference
Arize-ai/openinference
OpenTelemetry Instrumentation for AI Observability
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work