> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openlit.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Instrumentation Methods

> Choose between zero-code instrumentation or manual instrumentation for AI observability

OpenLIT SDK offers two ways to add opentelemetry-native observability to your AI applications:

> [card] Zero-code instrumentation
>
> Runtime wrapper, no code changes needed
>
> ```bash terminal theme={"theme":{"light":"github-light","dark":"github-dark"}}
> openlit-instrument \
>   python app.py
> ```
>
> **Use when:**
>
> * Working with existing/production apps
> * Code changes are restricted or risky

> [card] Manual instrumentation
>
> Add 2 lines to your code for auto instrumentation
>
> ```python example.py theme={"theme":{"light":"github-light","dark":"github-dark"}}
> import openlit
> openlit.init()
> ```
>
> **Use when:**
>
> * Building new applications
> * Need custom spans or metadata
> * Want advanced configuration options

## Comparison

| | Zero-code instrumentation | Manual instrumentation |
| - | - | - |
| **Code changes** | None | 2 lines |
| **Advanced features** | Basic configuration | Full access to custom spans, metadata |
| **Setup time** | Instant | 1 minute |
| **Best for** | Production apps, Existing Apps | New apps, custom needs |

***

> [card] [Quickstart: LLM Observability](https://docs.openlit.io/latest/sdk/quickstart-ai-observability.md)
>
> Production-ready AI monitoring setup in 2 simple steps with zero code changes

> [card] [Integrations](https://docs.openlit.io/latest/sdk/integrations/overview.md)
>
> 60+ AI integrations with automatic instrumentation and performance tracking

> [card] [Deploy OpenLIT Platform](https://docs.openlit.io/latest/openlit/installation.md)
>
> Deployment options for scalable LLM monitoring infrastructure

> [card] [Destinations](https://docs.openlit.io/latest/sdk/destinations/overview.md)
>
> Send telemetry to Datadog, Grafana, New Relic, and other observability stacks


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.