---
title: "openllmetry"
type: "tool"
slug: "traceloop-openllmetry"
canonical_url: "https://www.graphcanon.com/tools/traceloop-openllmetry"
github_url: "https://github.com/traceloop/openllmetry"
homepage_url: "https://www.traceloop.com/openllmetry"
stars: 7280
forks: 1016
primary_language: "Python"
license: "Apache-2.0"
categories: ["evaluation-observability"]
tags: ["good-first-issue", "ml", "llm", "artificial-intelligence", "datascience", "generative-ai", "help-wanted", "model-monitoring"]
updated_at: "2026-07-07T19:50:30.401933+00:00"
---

# openllmetry

> Open-source observability for your LLM application

A Python-based open-source tool for monitoring and observing Large Language Model (LLM) or GenAI applications using OpenTelemetry.

## Facts

- Repository: https://github.com/traceloop/openllmetry
- Homepage: https://www.traceloop.com/openllmetry
- Stars: 7,280 · Forks: 1,016 · Open issues: 591 · Watchers: 18
- Primary language: Python
- License: Apache-2.0
- Last pushed: 2026-07-01T18:11:56+00:00

## Categories

- [Evaluation & Observability](/categories/evaluation-observability.md)

## Tags

good-first-issue, ml, llm, artificial-intelligence, datascience, generative-ai, help-wanted, model-monitoring

## Related tools

- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,311)
- [ai-engineering-from-scratch](/tools/rohitg00-ai-engineering-from-scratch.md) - Curriculum for building AI systems from scratch (★ 37,583)
- [langfuse](/tools/langfuse-langfuse.md) - Open source AI engineering platform (★ 30,631)
- [FastGPT](/tools/labring-fastgpt.md) - FastGPT is a knowledge-based platform for developing and deploying complex question-answering systems using LLMs, offering out-of-the-box capabilities like data processing, RAG retrieval, and visual A (★ 28,855)
- [mlflow](/tools/mlflow-mlflow.md) - The open source AI engineering platform for agents, LLMs, and ML models (★ 26,923)
- [llm-action](/tools/liguodongiot-llm-action.md) - 分享大模型技术原理与实战经验，涵盖工程化和应用落地 (★ 24,670)
- [promptfoo](/tools/promptfoo-promptfoo.md) - Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. (★ 23,004)
- [vector](/tools/vectordotdev-vector.md) - A high-performance observability data pipeline (★ 22,152)

## README (excerpt)

```text
<p align="center">
<a href="https://www.traceloop.com/openllmetry#gh-light-mode-only">
<img width="600" src="https://raw.githubusercontent.com/traceloop/openllmetry/main/img/logo-light.png">
</a>
<a href="https://www.traceloop.com/openllmetry#gh-dark-mode-only">
<img width="600" src="https://raw.githubusercontent.com/traceloop/openllmetry/main/img/logo-dark.png">
</a>
</p>
<p align="center">
  <p align="center">Open-source observability for your LLM application</p>
</p>
<h4 align="center">
    <a href="https://traceloop.com/docs/openllmetry/getting-started-python"><strong>Get started »</strong></a>
    <br />
    <br />
  <a href="https://traceloop.com/slack">Slack</a> |
  <a href="https://traceloop.com/docs/openllmetry/introduction">Docs</a> |
  <a href="https://www.traceloop.com/openllmetry">Website</a>
</h4>

<h4 align="center">
  <a href="https://github.com/traceloop/openllmetry/releases">
    <img src="https://img.shields.io/github/release/traceloop/openllmetry">
  </a>
  <a href="https://pepy.tech/project/opentelemetry-instrumentation-openai">
  <img src="https://static.pepy.tech/badge/opentelemetry-instrumentation-openai/month">
  </a>
   <a href="https://github.com/traceloop/openllmetry/blob/main/LICENSE">
    <img src="https://img.shields.io/badge/license-Apache 2.0-blue.svg" alt="OpenLLMetry is released under the Apache-2.0 License">
  </a>
  <a href="https://github.com/traceloop/openllmetry/actions/workflows/ci.yml">
  <img src="https://github.com/traceloop/openllmetry/actions/workflows/ci.yml/badge.svg">
  </a>
  <a href="https://github.com/traceloop/openllmetry/issues">
    <img src="https://img.shields.io/github/commit-activity/m/traceloop/openllmetry" alt="git commit activity" />
  </a>
  <a href="https://www.ycombinator.com/companies/traceloop"><img src="https://img.shields.io/website?color=%23f26522&down_message=Y%20Combinator&label=Backed&logo=ycombinator&style=flat-square&up_message=Y%20Combinator&url=https%3A%2F%2Fwww.ycombinator.com"></a>
  <a href="https://github.com/traceloop/openllmetry/blob/main/CONTRIBUTING.md">
    <img src="https://img.shields.io/badge/PRs-Welcome-brightgreen" alt="PRs welcome!" />
  </a>
  <a href="https://traceloop.com/slack">
    <img src="https://img.shields.io/badge/chat-on%20Slack-blueviolet" alt="Slack community channel" />
  </a>
  <a href="https://twitter.com/traceloopdev">
    <img src="https://img.shields.io/badge/follow-%40traceloopdev-1DA1F2?logo=twitter&style=social" alt="Traceloop Twitter" />
  </a>
</h4>

**🎉 New**:
Our semantic conventions are now part of OpenTelemetry! Join the [discussion](https://github.com/open-telemetry/community/blob/1c71595874e5d125ca92ec3b0e948c4325161c8a/projects/llm-semconv.md) and help us shape the future of LLM observability.

Looking for the JS/TS version? Check out [OpenLLMetry-JS](https://github.com/traceloop/openllmetry-js).

OpenLLMetry is a set of extensions built on top of [OpenTelemetry](https://opentelemetry.io/) that gives you complete observability over your LLM application. Because it uses OpenTelemetry under the hood, [it can be connected to your existing observability solutions](https://www.traceloop.com/docs/openllmetry/integrations/introduction) - Datadog, Honeycomb, and others.

It's built and maintained by Traceloop under the Apache 2.0 license.

The repo contains standard OpenTelemetry instrumentations for LLM providers and Vector DBs, as well as a Traceloop SDK that makes it easy to get started with OpenLLMetry, while still outputting standard OpenTelemetry data that can be connected to your observability stack.
If you already have OpenTelemetry instrumented, you can just add any of our instrumentations directly.

## 🚀 Getting Started

The easiest way to get started is to use our SDK.
For a complete guide, go to our [docs](https://traceloop.com/docs/openllmetry/getting-started-python).

Install the SDK:

```bash
pip install traceloop-sdk
```

Then, to start instrumenting your code, just add this line to your code:
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/traceloop-openllmetry`](/api/graphcanon/tools/traceloop-openllmetry)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_