---
title: "OpenLLMetry Trace Export"
description: "Export OpenLLMetry traces to the Judgment platform."
sidebar:
  label: "OpenLLMetry Integration"
seo:
  title: "OpenLLMetry Trace Export to Judgment | Integration Docs"
  description: "Export OpenLLMetry traces to Judgment so teams can inspect agent behavior, run judges, and monitor production regressions."
---

**OpenLLMetry integration** sends traces from your OpenLLMetry-instrumented applications to Judgment. OpenLLMetry provides OpenTelemetry-based instrumentation for various LLM providers and frameworks.

{/* @test-flow
  id: tracing-openllmetry
  lang: python
  env: JUDGMENT_API_KEY, JUDGMENT_ORG_ID, OPENAI_API_KEY
*/}

## Quickstart

1. ### Install Dependencies

    **uv**

    ```bash
    uv add opentelemetry-instrumentation-openai judgeval openai
    ```

    **pip**

    ```bash
    pip install opentelemetry-instrumentation-openai judgeval openai
    ```

2. ### Initialize Integration

    ```python
    from judgeval import Tracer
    from opentelemetry.instrumentation.openai import OpenAIInstrumentor

    Tracer.init(project_name="openllmetry_project")
    Tracer.registerOTELInstrumentation(OpenAIInstrumentor())
    ```

3. ### Use with OpenAI

    ```python
    from judgeval import Tracer
    from opentelemetry.instrumentation.openai import OpenAIInstrumentor
    from openai import OpenAI

    Tracer.init(project_name="openllmetry_project")
    Tracer.registerOTELInstrumentation(OpenAIInstrumentor())

    client = OpenAI()

    response = client.chat.completions.create(
        model="gpt-5.2",
        messages=[{"role": "user", "content": "Hello, world!"}]
    )

    print(response.choices[0].message.content)
    ```

    All OpenAI calls are automatically traced and exported to the Judgment platform.

## Available Instrumentors

OpenLLMetry provides instrumentors for various frameworks and libraries:

### OpenAI

```python
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
Tracer.registerOTELInstrumentation(OpenAIInstrumentor())
```

### Anthropic

```python
from opentelemetry.instrumentation.anthropic import AnthropicInstrumentor
Tracer.registerOTELInstrumentation(AnthropicInstrumentor())
```

### OpenAI Agents SDK

```python
from opentelemetry.instrumentation.openai_agents import OpenAIAgentsInstrumentor
Tracer.registerOTELInstrumentation(OpenAIAgentsInstrumentor())
```

### Google Generative AI

```python
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAiInstrumentor
Tracer.registerOTELInstrumentation(GoogleGenerativeAiInstrumentor())
```

### Together AI

```python
from opentelemetry.instrumentation.together import TogetherInstrumentor
Tracer.registerOTELInstrumentation(TogetherInstrumentor())
```

### Groq

```python
from opentelemetry.instrumentation.groq import GroqInstrumentor
Tracer.registerOTELInstrumentation(GroqInstrumentor())
```

### HuggingFace Transformers

```python
from opentelemetry.instrumentation.transformers import TransformersInstrumentor
Tracer.registerOTELInstrumentation(TransformersInstrumentor())
```

### Vertex AI

```python
from opentelemetry.instrumentation.vertexai import VertexAIInstrumentor
Tracer.registerOTELInstrumentation(VertexAIInstrumentor())
```

### Ollama

```python
from opentelemetry.instrumentation.ollama import OllamaInstrumentor
Tracer.registerOTELInstrumentation(OllamaInstrumentor())
```

### LiteLLM

```python
from opentelemetry.instrumentation.litellm import LiteLLMInstrumentor
Tracer.registerOTELInstrumentation(LiteLLMInstrumentor())
```

> **Tip**
>
> The LiteLLM instrumentor monkeypatches `litellm.completion` so every call emits an OTEL span with model name, prompt/completion tokens, and cost — even when using LiteLLM's functional API (e.g. in multi-agent swarms). See the [LiteLLM integration guide](/documentation/integrations/model-providers/litellm) for a full setup walkthrough.

### Other

> **Info**
>
> We support the complete list of available instrumentors, so visit the
> [OpenLLMetry GitHub repository](https://github.com/traceloop/openllmetry) for
> more.

## Next Steps

- [All Integrations](/documentation/integrations) - View the list of all integrations that Judgment supports.
- [Monitor a behavior](/documentation/monitoring) - Monitor your AI applications in production with behavioral scoring.
- [Instrument your agent](/documentation/tracing/instrumentation) - Configure and verify Judgment tracing beyond this integration.