# traceloop/openllmetry

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Repository: https://github.com/traceloop/openllmetry
Canonical: https://ross.abutalabs.com/products/openllmetry
Homepage: https://www.traceloop.com/openllmetry
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llmops, observability, open-telemetry, metrics, monitoring, opentelemetry, datascience, ml, model-monitoring, opentelemetry-python, python, good-first-issue, help-wanted, artifical-intelligence, generative-ai, good-first-issues, llm, open-source
Last push: 2026-08-10T08:49:01+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 97, release rhythm 85, longevity 78
- inputs: {"age_days": 1096, "days_push": 23, "days_rel": 23, "gap_med": 2, "n_releases_24m": 130}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7402, forks 1060 (observed 2026-08-28T04:09:59.706974+00:00)

## What it is
OpenLLMetry is an open-source set of OpenTelemetry extensions and SDKs that provide observability (tracing, metrics, logging) for LLM and GenAI applications. It instruments popular LLM providers and frameworks non-intrusively and exports telemetry to Traceloop or any existing observability stack.

## Use cases
- trace and debug LLM calls in production
- monitor token usage and costs of OpenAI applications
- add OpenTelemetry instrumentation to a LangChain or vector DB pipeline
- export LLM traces to Datadog or another observability backend
- observe prompts and completions of a chatbot
- set up LLM observability with minimal code changes

## When to choose
- you want standards-based OpenTelemetry tracing for LLM apps
- you need vendor-neutral export to your existing observability stack
- you use Python or TypeScript with supported LLM providers/frameworks
- you want non-intrusive instrumentation with a few lines of code

## When to avoid
- you need a full commercial LLM monitoring UI out of the box without a backend
- your stack is in a language without an SDK (e.g., Go, Java)
- you only need simple prompt logging without distributed tracing

## Facets
- artifact type: library
- maturity: active
- function: monitoring, tracing, logging, sdk
- domain: large-language-models, monitoring, developer-tools, artificial-intelligence
- platform: python, cross-platform
- tags: llm-observability, opentelemetry, llmops, genai, tracing, model-monitoring, nodejs

## Member repositories
- traceloop/openllmetry (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:59.706974+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:38:02.638660+00:00, confidence not recorded.
  - readme: https://github.com/traceloop/openllmetry (fetched 2026-08-28T04:09:59.706974+00:00, sha 514f46fd096d)
  - homepage: https://www.traceloop.com/openllmetry (fetched 2026-08-29T08:33:33.822072+00:00, sha 7ffa1cebd86a)
  - site_page: https://traceloop.com/docs/openllmetry (fetched 2026-08-29T08:33:33.831189+00:00, sha 7456c64b6fc9)
- Data as of 2026-08-30T08:39:29.467469+00:00.