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:
Zero-code instrumentation
Runtime wrapper, no code changes neededUse when:
terminal
- Working with existing/production apps
- Code changes are restricted or risky
Manual instrumentation
Add 2 lines to your code for auto instrumentationUse when:
example.py
- 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 |
Quickstart: LLM Observability
Production-ready AI monitoring setup in 2 simple steps with zero code changes
Integrations
60+ AI integrations with automatic instrumentation and performance tracking
Deploy OpenLIT Platform
Deployment options for scalable LLM monitoring infrastructure
Destinations
Send telemetry to Datadog, Grafana, New Relic, and other observability stacks
Running in Kubernetes? Try the OpenLIT Operator
Automatically inject instrumentation into existing workloads without modifying pod specs, container images, or application code.