OpenLLMetry
Open-source LLM observability for Python and JavaScript/TypeScript apps, with Ollama support and standard OpenTelemetry output. Licensed under Apache 2.0.
OpenLLMetry adds LLM tracing to the OpenTelemetry monitoring stack a team already uses. It's for developers who need to follow model calls alongside database activity and API requests in their AI applications. The extensions run within your application and send standard OpenTelemetry data to your chosen monitoring destination.
Support covers local LLM calls through Ollama as well as hosted providers such as OpenAI, Anthropic, Gemini and AWS Bedrock. It also traces vector databases, including Chroma, Qdrant, Weaviate and LanceDB, so retrieval activity can sit alongside model calls in the same monitoring stack.
Framework integrations include LangChain, LangGraph, LlamaIndex, CrewAI and OpenAI Agents. MCP instrumentation covers that protocol too. Python is supported in this project, while OpenLLMetry-JS provides the JavaScript and TypeScript implementation.
Its standard output gives teams a choice of where traces go. Supported destinations include OpenTelemetry Collector, Grafana, SigNoz, Datadog and Honeycomb, as well as Traceloop. Instrumentation runs with your code; the destination can be a self-hosted monitoring system or a cloud service. You can use individual instrumentations with an existing OpenTelemetry setup or use the Traceloop SDK.
Traceloop maintains the project under the Apache 2.0 license. Current SDK and instrumentation releases do not collect their own usage telemetry; older SDK releases may collect it. Application traces go to the monitoring destination you select.
