---
name: "Trace LLM and agent workflows with OpenLLMetry"
slug: "trace-llm-and-agent-workflows-with-openllmetry"
description: "Add OpenTelemetry-based instrumentation to LLM and agent code so operators can inspect prompts, tool calls, latency, errors, and provider behavior in their existing observability stack."
github_stars: 7170
verification: "security_reviewed"
source: "https://github.com/traceloop/openllmetry"
author: "Traceloop"
publisher_type: "organization"
category: "Monitoring & Alerts"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "traceloop/openllmetry"
  github_stars: 7170
---

# Trace LLM and agent workflows with OpenLLMetry

Add OpenTelemetry-based instrumentation to LLM and agent code so operators can inspect prompts, tool calls, latency, errors, and provider behavior in their existing observability stack.

## Prerequisites

Python, OpenLLMetry or Traceloop SDK, OpenTelemetry-compatible collector or backend

## Installation

Use the upstream install or setup path that matches your environment:
- pip install traceloop-sdk

Requirements and caveats from upstream:
- <a href="https://traceloop.com/docs/openllmetry/getting-started-python"><strong>Get started »</strong></a>
- For a complete guide, go to our [docs](https://traceloop.com/docs/openllmetry/getting-started-python).
- python

Basic usage or getting-started notes:
- Then, to start instrumenting your code, just add this line to your code:
- from traceloop.sdk import Traceloop
- Traceloop.init()

- Source: https://github.com/traceloop/openllmetry
- Extracted from upstream docs: https://raw.githubusercontent.com/traceloop/openllmetry/HEAD/README.md

## Documentation

- https://traceloop.com/docs/openllmetry/getting-started-python

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/trace-llm-and-agent-workflows-with-openllmetry/)