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

# Overview

> From local development to production Kubernetes cluster

Vision Agents can run as a single process on your laptop or as a scaled-out service in Kubernetes. This guide maps the self-hosted path from local dev to production. If you'd rather skip the infra, Stream also offers a [hosted Voice AI platform](https://getstream.io/video/voice-ai/) on the same edge network.

<Tip>
  **Prefer managed hosting?** [Stream Voice AI](https://getstream.io/video/voice-ai/) runs production voice agents on Stream's global edge, phone numbers, web and mobile clients, co-located STT/LLM/TTS, and built-in observability. [Join the waitlist](https://getstream.io/video/voice-ai/) for early access.
</Tip>

## The path to production

<Steps>
  <Step title="Run locally" icon="terminal">
    Start your agent as an HTTP server with session management. This is the foundation for everything that follows.

    ```bash theme={null}
    uv run agent.py serve
    ```

    The server handles session creation, health checks, authentication, and metrics out of the box.

    <Card title="Built-in HTTP Server" icon="server" href="/guides/http-server">
      API endpoints, session limits, and authentication
    </Card>
  </Step>

  <Step title="Containerize" icon="docker">
    Package your agent into a Docker image for deployment to any environment.

    <Card title="Docker Deployment" icon="docker" href="/guides/deployment">
      Dockerfiles for CPU and GPU, environment configuration
    </Card>
  </Step>

  <Step title="Scale out" icon="circle-nodes">
    Running multiple replicas? Add a Redis-backed session registry so any node can manage any session.

    <Card title="Horizontal Scaling" icon="circle-nodes" href="/guides/horizontal-scaling">
      Redis session store, custom backends, heartbeat mechanism
    </Card>
  </Step>

  <Step title="Orchestrate" icon="dharmachakra">
    The complete setup: Helm chart, health probes, Redis, Prometheus scraping, and a Grafana dashboard.

    <Card title="Kubernetes Deployment" icon="dharmachakra" href="/guides/kubernetes-deployment">
      Step-by-step guide with monitoring included
    </Card>
  </Step>

  <Step title="Observe" icon="chart-line">
    Track latency, token usage, and errors across all components with OpenTelemetry. Works at any stage, not just Kubernetes.

    <Card title="Telemetry & Metrics" icon="chart-line" href="/core/telemetry">
      Metrics reference, Prometheus queries, Jaeger tracing
    </Card>
  </Step>
</Steps>

## Pick your starting point

Not every project needs every step.

| Goal                          | Start here                                                       |
| ----------------------------- | ---------------------------------------------------------------- |
| Managed hosting (phone, web)  | [Stream Voice AI waitlist](https://getstream.io/video/voice-ai/) |
| Local development and testing | [HTTP Server](/guides/http-server)                               |
| Deploy a single container     | [Docker Deployment](/guides/deployment)                          |
| Run multiple replicas         | [Horizontal Scaling](/guides/horizontal-scaling)                 |
| Full production setup         | [Kubernetes Deployment](/guides/kubernetes-deployment)           |
| Add metrics to any setup      | [Telemetry & Metrics](/core/telemetry)                           |