> ## 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.

# Observability Overview

> Comprehensive observability and tracing for PraisonAI agents with 20+ provider integrations

# Observability Suite

PraisonAI provides a unified observability suite with support for 20+ observability providers. All integrations use lazy loading for zero performance impact when not in use.

## Quick Start

### Init-Only Auto-Instrumentation (Recommended)

The simplest way to add observability - just call `obs.init()` once and all agent operations are automatically traced:

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools.observability import obs

# Auto-detect provider and auto-instrument all agents
obs.init()

# That's it! Everything below is now traced automatically
from praisonaiagents import Agent

agent = Agent(name="Assistant", instructions="You are helpful.")
agent.chat("Hello!")  # Auto-traced to your provider
```

<Note>
  Auto-instrumentation patches `Agent.chat()`, `Agent.start()`, `Agent.run()`, and `Agents.start()` to create spans automatically. No explicit `obs.trace()` wrappers needed!
</Note>

### Explicit Provider Selection

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools.observability import obs

# Specify provider explicitly
obs.init(provider="langfuse")

# Or disable auto-instrumentation for manual control
obs.init(auto_instrument=False)
```

## Supported Providers

| Provider                                      | Environment Variables                        | Install                                                     |
| --------------------------------------------- | -------------------------------------------- | ----------------------------------------------------------- |
| [AgentOps](/observability/agentops)           | `AGENTOPS_API_KEY`                           | `pip install agentops`                                      |
| [Langextract](/observability/langextract)     | – (local HTML)                               | `pip install 'praisonai[langextract]'`                      |
| [Langfuse](/observability/langfuse)           | `LANGFUSE_PUBLIC_KEY`, `LANGFUSE_SECRET_KEY` | `pip install langfuse` †                                    |
| [LangSmith](/observability/langsmith)         | `LANGSMITH_API_KEY`                          | `pip install opentelemetry-sdk opentelemetry-exporter-otlp` |
| [Traceloop](/observability/traceloop)         | `TRACELOOP_API_KEY`                          | `pip install traceloop-sdk`                                 |
| [Arize Phoenix](/observability/arize-phoenix) | `PHOENIX_API_KEY`                            | `pip install arize-phoenix`                                 |
| [OpenLIT](/observability/openlit)             | -                                            | `pip install openlit`                                       |
| [Langtrace](/observability/langtrace)         | `LANGTRACE_API_KEY`                          | `pip install langtrace-python-sdk`                          |
| [LangWatch](/observability/langwatch)         | `LANGWATCH_API_KEY`                          | `pip install langwatch`                                     |
| [Datadog](/observability/datadog)             | `DD_API_KEY`                                 | `pip install ddtrace`                                       |
| [MLflow](/observability/mlflow)               | `MLFLOW_TRACKING_URI`                        | `pip install mlflow`                                        |
| [Opik](/observability/opik)                   | `OPIK_API_KEY`                               | `pip install opik`                                          |
| [Portkey](/observability/portkey)             | `PORTKEY_API_KEY`                            | `pip install portkey-ai`                                    |
| [Braintrust](/observability/braintrust)       | `BRAINTRUST_API_KEY`                         | `pip install braintrust`                                    |
| [Maxim](/observability/maxim)                 | `MAXIM_API_KEY`                              | `pip install maxim-py`                                      |
| [Weave](/observability/weave)                 | `WANDB_API_KEY`                              | `pip install weave`                                         |
| [Neatlogs](/observability/neatlogs)           | `NEATLOGS_API_KEY`                           | -                                                           |
| [LangDB](/observability/langdb)               | `LANGDB_API_KEY`                             | -                                                           |
| [Atla](/observability/atla)                   | `ATLA_API_KEY`                               | `pip install atla-insights`                                 |
| [Patronus](/observability/patronus)           | `PATRONUS_API_KEY`                           | `pip install patronus`                                      |
| [TrueFoundry](/observability/truefoundry)     | `TRUEFOUNDRY_API_KEY`                        | -                                                           |

† **Langfuse** can be enabled via `praisonai --observe langfuse` **as well as** `obs.langfuse()`.

## Core Concepts

### Traces and Spans

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools.observability import obs
from praisonai_tools.observability.base import SpanKind

obs.init(provider="langfuse")

# Create a trace for a workflow
with obs.trace("my-workflow", session_id="user-123"):
    # Create spans for individual operations
    with obs.span("llm-call", kind=SpanKind.LLM) as span:
        span.model = "gpt-4o-mini"
        span.input_tokens = 100
        span.output_tokens = 50
        # ... your LLM call
    
    with obs.span("tool-call", kind=SpanKind.TOOL) as span:
        span.tool_name = "search"
        # ... your tool call
```

### Logging LLM Calls

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
obs.log_llm_call(
    model="gpt-4o-mini",
    input_messages="What is 2+2?",
    output="4",
    input_tokens=10,
    output_tokens=1,
)
```

### Logging Tool Calls

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
obs.log_tool_call(
    tool_name="search",
    tool_input={"query": "PraisonAI"},
    tool_output={"results": [...]},
)
```

### Decorators

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
@obs.decorator("my-function", SpanKind.CUSTOM)
def my_function():
    return "result"
```

## Multi-Agent Tracing

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools.observability import obs
from praisonai_tools.observability.base import SpanKind

obs.init(provider="langfuse")

with obs.trace("multi-agent-workflow"):
    # Agent 1
    with obs.span("agent-1", kind=SpanKind.AGENT) as span:
        span.attributes["agent_name"] = "Researcher"
        # ... agent 1 work
    
    # Agent 2 (child of same trace)
    with obs.span("agent-2", kind=SpanKind.AGENT) as span:
        span.attributes["agent_name"] = "Writer"
        # ... agent 2 work
```

## CLI Commands

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Health check
python -m praisonai_tools.observability.cli doctor

# Health check (JSON output)
python -m praisonai_tools.observability.cli doctor --json

# Verify traces in backend (LangSmith)
python -m praisonai_tools.observability.cli verify --provider langsmith --project "My First App"

# Also available via praisonai wrapper
praisonai obs doctor
praisonai obs verify --project "My First App"
```

## Diagnostics

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Check observability status
print(obs.doctor())
# Output: {'enabled': True, 'provider': 'langfuse', 'connection_status': True, ...}
```