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

# Quick Start

> Get monitoring in under 5 minutes

## Option A: OpenTelemetry (Zero Code if Already Instrumented)

Already emitting OpenTelemetry traces from your agents? Point your existing OTLP exporter at MeshAI and you are done. No SDK, no proxy, no code changes.

<Steps>
  <Step title="Get a telemetry key">
    Go to [app.meshai.dev](https://app.meshai.dev) -> Connect -> Create telemetry key. The key needs only the `telemetry:write` scope.
  </Step>

  <Step title="Point your exporter at MeshAI">
    ```bash theme={null} theme={null} theme={null} theme={null}
    export OTEL_EXPORTER_OTLP_ENDPOINT=https://api.meshai.dev/api/v1/ingest
    export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer msh_YOUR_API_KEY"
    export OTEL_SERVICE_NAME=my-agent
    ```
  </Step>

  <Step title="Run your agent">
    MeshAI auto-discovers agents from the `service.name` resource attribute and extracts token usage from `gen_ai.*` conventions. Agents appear in the registry as telemetry arrives. See the [OpenTelemetry guide](/getting-started/opentelemetry) for details on what gets extracted.
  </Step>
</Steps>

## Option B: Proxy (Fastest, Zero Code)

The MeshAI proxy sits between your agents and LLM providers. One env var change and you're monitoring.

<Steps>
  <Step title="Get your proxy key">
    Go to [app.meshai.dev](https://app.meshai.dev) → Settings → Proxy Keys → Create.
  </Step>

  <Step title="Set the env var">
    ```bash theme={null}
    # For Anthropic
    export ANTHROPIC_BASE_URL=https://proxy.meshai.dev/v1/anthropic/k/YOUR_PROXY_KEY

    # For OpenAI
    export OPENAI_BASE_URL=https://proxy.meshai.dev/v1/openai/k/YOUR_PROXY_KEY
    ```
  </Step>

  <Step title="Run your agent">
    No code changes needed. All requests automatically flow through MeshAI.
  </Step>
</Steps>

## Option C: Python SDK

<Steps>
  <Step title="Install">
    ```bash theme={null}
    pip install meshai-sdk
    ```
  </Step>

  <Step title="Initialize and register">
    ```python theme={null}
    from meshai import MeshAI

    client = MeshAI(api_key="msh_...", agent_name="my-agent")
    client.register(
        framework="crewai",
        model_provider="openai",
        model_name="gpt-4o",
    )
    ```
  </Step>

  <Step title="Enable auto-tracking">
    ```python theme={null}
    # Automatic heartbeats
    client.start_heartbeat()

    # Track usage (or use framework wrappers)
    client.track_usage(
        model_provider="openai",
        model_name="gpt-4o",
        input_tokens=1500,
        output_tokens=800,
    )
    ```
  </Step>
</Steps>

## What You'll See

After connecting, your [dashboard](https://app.meshai.dev) shows:

* **Agent Registry**: all your agents with status, framework, model
* **Cost Attribution**: spend per agent, team, and model
* **Anomaly Detection**: cost spikes, behavioral drift, security alerts
* **Governance**: policy enforcement, audit trail, compliance score

## Next Steps

<CardGroup cols={2}>
  <Card title="OpenTelemetry Ingestion" icon="diagram-project" href="/getting-started/opentelemetry">
    OTLP endpoints, span conventions, and what gets extracted
  </Card>

  <Card title="Proxy Setup Guide" icon="bolt" href="/proxy/setup">
    Detailed proxy configuration for all providers
  </Card>

  <Card title="Framework Guides" icon="code" href="/framework-guides/openai">
    Auto-tracking for OpenAI, Anthropic, CrewAI, LangChain, AutoGen
  </Card>

  <Card title="Create Policies" icon="shield-halved" href="/governance/policies">
    Set up your first governance policy
  </Card>

  <Card title="API Reference" icon="book" href="/api-reference/overview">
    Full API documentation
  </Card>
</CardGroup>