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

# Quickstart

> Install the Cascade SDK and send your first trace

Get up and running with Cascade in minutes. This guide covers installation, API key setup, and sending your first trace.

## Install the SDK

Install the Cascade SDK from PyPI:

```bash theme={null}
pip install cascade-sdk
```

<Note>
  Requires Python 3.8 or higher.
</Note>

## Set your credentials

Get your API key and endpoint from the [Cascade Dashboard](https://dashboard.runcascade.com). Both are provided per customer.

Create a `.env` file in the root of your project:

```bash .env theme={null}
CASCADE_API_KEY="csk_live_..."
CASCADE_ENDPOINT="https://your-endpoint.runcascade.com/v1/traces"
```

Or pass them directly in code:

```python theme={null}
from cascade import init_tracing

init_tracing(api_key="csk_live_...", endpoint="https://your-endpoint.runcascade.com/v1/traces")
```

## Initialize tracing

Call `init_tracing()` once at the top of your application. Everything else is automatic.

```python theme={null}
from cascade import init_tracing

# With a project name (recommended - organizes traces in the dashboard)
init_tracing(project="customer_support_chatbot")
```

## Send your first trace

Wrap your agent's entry point with `trace_run()` and use `wrap_llm_client()` to automatically capture all LLM interactions:

```python my_agent.py theme={null}
from cascade import init_tracing, trace_run, wrap_llm_client
from anthropic import Anthropic

# Initialize tracing
init_tracing(project="my_first_agent")

# Wrap your LLM client - all calls are now automatically traced
client = wrap_llm_client(Anthropic())

# Create a traced agent run
with trace_run("SimpleAgent"):
    response = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=100,
        messages=[
            {"role": "user", "content": "Say hello and introduce yourself in one sentence."}
        ]
    )
    print(response.content[0].text)
```

Run the script:

```bash theme={null}
python my_agent.py
```

<Check>
  Open the Cascade Dashboard to see your trace with full details including prompts, completions, token counts, latency, and cost.
</Check>

## Next steps

<CardGroup cols={2}>
  <Card title="Sessions & Tracing" icon="route" href="/agent-performance/tracing">
    Learn about tracing runs, sub-agents, tools, and LLM clients.
  </Card>

  <Card title="Evaluation SDK" icon="clipboard-check" href="/agent-performance/evals">
    Score your agent's performance with built-in and custom evaluators.
  </Card>

  <Card title="Integrations" icon="plug" href="/integrations/langgraph">
    Auto-instrument LangGraph, OpenAI Agents, and Claude Agents.
  </Card>

  <Card title="Model providers" icon="microchip" href="/model-providers/overview">
    Trace any LLM provider through a unified wrapper.
  </Card>
</CardGroup>