> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# obs • AI Agent SDK
> Observability interface for PraisonAI Agents.
# obs
AI Agent
Observability interface for PraisonAI Agents.
This module provides the protocol and types for observability/tracing.
Implementations are provided by the wrapper layer (praisonai\_tools.observability).
Usage (simplest - recommended):
from praisonaiagents import Agent, obs
obs.auto() # Auto-detect from env vars; instruments the LLM client globally
agent = Agent(name="Assistant")
agent.chat("Hello!") # Auto-traces to configured provider
Alternative (explicit provider - call before creating the agent):
obs.langfuse() # Langfuse
obs.langsmith() # LangSmith
obs.agentops() # AgentOps
obs.arize() # Arize Phoenix
obs.datadog() # Datadog
## Import
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import obs
```
## Classes
Represents a span in a trace.
Represents a complete trace.
Protocol for observability adapters.