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

# Build a presence.

> Persistent agents with memory, relationships, tools, and bodies that meet you where you are.

<img className="ngram-brand-image" src="https://mintcdn.com/ngram-5d1444b0/4-GYn2c5Km93evwO/ngram.png?fit=max&auto=format&n=4-GYn2c5Km93evwO&q=85&s=36169a420f0a47aaa9d32aef39112517" alt="ngram — white globe mark on periwinkle" width="2000" height="2000" data-path="ngram.png" />

Give an agent continuity beyond a conversation. Build its memory, connect its tools, and bring it into the room.

<div className="ngram-start-actions">
  <a href="/quickstart">Start building <span aria-hidden="true">↗</span></a>
  <a href="/spatial/overview">Explore spatial <span aria-hidden="true">→</span></a>
</div>

ngram is an open engine for persistent agents. The **Entity** holds identity, memory, relationships, and judgment. The **harness** runs it. A **shell** gives it a body. You can change the model or the surface while keeping the same Entity.

## Choose your first build

* [Quickstart](/quickstart): choose hosted or local inference, create an identity, and start a conversation.
* [Spatial setup](/spatial/quickstart): connect a WebXR shell and build a shared scene.

## Continuity is the architecture

A message from Telegram and a request from a headset reach the same running Entity. Its inference provider generates responses; its runtime owns the state that makes those responses part of a continuing history.

<CardGroup cols={2}>
  <Card title="Shape an identity" icon="fingerprint" href="/guides/creating-entities">Define traits, voice, knowledge, and the way your Entity meets people.</Card>
  <Card title="Build in the room" icon="cube" href="/spatial/recipes">Combine spatial tools into diagrams, demonstrations, and shared environments.</Card>
  <Card title="Understand the runtime" icon="layer-group" href="/architecture/overview">Follow a turn through cognition, retrieval, tools, memory, and presence.</Card>
  <Card title="Operate deliberately" icon="sliders" href="/guides/usage-and-controls">Control background activity, context, cost, and when an Entity stops.</Card>
</CardGroup>

## Start small. Keep the same Entity.

You do not need a headset, GPU, Railway deployment, or Cloudflare tunnel to begin. A hosted setup runs the Entity on your computer and sends inference requests to your chosen provider. A local setup runs those requests through Ollama.

Add messaging, spatial embodiment, or an always-on deployment when your project needs it. The [core concepts](/concepts) explain what moves between those environments and what stays with the Entity.

<Note>These docs describe the shipped **v1** runtime. Runtime features and registered tools depend on configuration and the connected surface. Check [surface capabilities](/spatial/capabilities) before assuming headset tracking or a backend is available.</Note>