traceloop/openllmetry-js

Sister project to OpenLLMetry, but in Typescript. Open-source observability for your LLM application, based on OpenTelemetry

What it solves

OpenLLMetry-JS provides observability for LLM applications built with JavaScript and TypeScript. It helps developers track and monitor the internal workings of their AI applications, making it easier to debug and optimize performance by providing a standardized way to capture telemetry data from LLM providers and vector databases.

How it works

Built on top of OpenTelemetry, the project provides a set of extensions and a simplified SDK. It instruments calls to various LLM providers (like OpenAI, Anthropic, and Bedrock) and vector databases (like Pinecone and Chroma), capturing the data flow. Because it adheres to OpenTelemetry standards, the captured traces can be exported to a wide variety of existing observability tools such as Datadog, Honeycomb, and New Relic.

Who it’s for

Developers using Node.js or Next.js who are building LLM-powered applications and need a professional observability stack to monitor their AI workflows.

Highlights

  • OpenTelemetry-based: Uses industry-standard OpenTelemetry under the hood for compatibility with existing tools.
  • Broad Integration: Supports a wide range of LLM providers (OpenAI, Anthropic, Cohere, Vertex AI, Bedrock) and vector databases (Pinecone, Chroma, Qdrant).
  • Framework Support: Integrates with popular AI frameworks like LangChain and LlamaIndex.
  • Easy Setup: Offers a simplified SDK that allows instrumentation with just a few lines of code.