AI product Open source
OpenInference is an open-source set of OpenTelemetry-complementary semantic conventions, instrumentation libraries, and plugins for tracing AI applications. Its specification models LLM invocations and surrounding context such as vector-store retrieval and external tool use in a transport- and file-format-agnostic schema, while its instrumentations normalize traces from model, agent, and application frameworks across Python, JavaScript, Java, and Go. The project also defines conventions for real-time audio and voice-agent traces, allowing audio, transcripts, and tool calls to be represented in a queryable session trace. It is natively supported by Arize Phoenix and Arize AX and can send data to any OpenTelemetry-compatible backend.
3 uses taken from transcripts — each links to the moment in the video.
OpenInference is an open-source set of OpenTelemetry-compliant semantic conventions for generative AI and real-time audio. It normalizes events from different model providers into a queryable schema and supports instrumentation of voice-agent traces.
Instruments the Claude Agent SDK with LLM-specific trace attributes, including prompts, completions, token counts, models, and tool invocations.
Provides the open standard instrumentation that generates traces for AI application activity.
3 in the library.