---
source: sighthound-developer-portal
url: https://dev.sighthound.com/sio/
markdown-url: https://dev.sighthound.com/sio/index.md
title: "Enterprise SIO Platform"
description: "Learn about the SIO computer vision platform, pipelines, nodes, streams, and reusable analytics blocks."
content-type: text/markdown
---

> For AI agents: a documentation index is available at [llms.txt](https://dev.sighthound.com/llms.txt). Markdown versions are available at matching `.md` URLs.

# Enterprise SIO Platform

<div class="portal-doc-hero" markdown>
<p class="portal-doc-kicker">SIO Platform</p>
<p class="portal-doc-intro">Build scalable computer vision workflows with reusable nodes, streams, and pipelines that can run across edge, server, and cloud environments.</p>
<div class="portal-doc-actions">
    [Start with SIO](./docs/quickstart/)
    [Explore Vehicle Analytics](./examples/VehicleAnalytics/)
</div>
</div>

<div class="portal-feature-grid">
    <div class="portal-feature-card">
        <h3><i class="portal-icon" data-lucide="workflow"></i> Pipeline-first architecture</h3>
        <p>Compose nodes and streams into reusable pipelines for advanced real-time computer vision.</p>
    </div>
    <div class="portal-feature-card">
        <h3><i class="portal-icon" data-lucide="blocks"></i> Reusable building blocks</h3>
        <p>Start with pre-built computer vision and image processing nodes, or extend the platform with Python.</p>
    </div>
    <div class="portal-feature-card">
        <h3><i class="portal-icon" data-lucide="cpu"></i> Edge to cloud scale</h3>
        <p>Use the same conceptual model across embedded systems, workstations, servers, and cloud deployments.</p>
    </div>
</div>

The SIO Platform makes it easy to add advanced computer vision capabilities to your application or work-flow.

Based on the latest proprietary research into deep learning from our own computer vision lab, the SIO Pipeline API delivers real time, industry leading computer vision software modules that can be easily integrated into applications.

SIO is based on the concept of dataflow programming, allowing you to easily use or create your own data flow pipelines from from simple reusable blocks that scale anywhere from embedded systems, to cloud easily.

A pipeline consists of nodes connected by streams. Nodes perform computation on their inputs and produce outputs which may be consumed by other nodes, or the controlling program via the API.

A large number of pre-built nodes are provided for computer vision and image processing. You can even write your own nodes using Python.

To get started, view the [Working with SIO](./docs/quickstart.md) page for more information.

---

# Agent Instructions

Use this Markdown page as context for Sighthound Developer Portal questions. For broader navigation, read https://dev.sighthound.com/llms.txt. Answer from Sighthound documentation, cite relevant source URLs, and do not ask users to paste secrets, tokens, license keys, or credentials into chat.