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

# Brontes

> Brontes is the endpoint manager among the Myrmex AI agents — it keeps track of the health, configuration, and installed software of the assets you've registered in Myrmex.

import { CardGroup, Card, Note, Tip } from '@mintlify/components';

**Brontes** is the endpoint manager among the Myrmex AI agents. It knows the **assets you've registered in Myrmex** — their health, their configuration, and the software installed on them — and keeps that picture current so you can ask about your devices in plain language.

<Note>
  Brontes works over the **assets registered in Myrmex** — the devices running
  the Myrmex software agent that you've onboarded and authorized. It is not a
  discovery tool that scans your whole network for unknown machines.
</Note>

## What Brontes Tracks

For each registered device, Brontes maintains the same picture you see in a device's [System Info](/documentation/agent-endpoint-security/device-details):

<CardGroup cols={2}>
  <Card title="Health & status" icon="heart-pulse">
    Whether a device is online or offline, its agent version, and when it last
    reported in.
  </Card>

  <Card title="System information" icon="microchip">
    Operating system and version, CPU and memory, the device's Myrmex ID, and its
    public IP.
  </Card>

  <Card title="Installed software" icon="box">
    The applications and software inventory reported from the host.
  </Card>

  <Card title="Configuration" icon="sliders">
    How the device is set up and labeled — its role, folders, tags, and severity.
  </Card>
</CardGroup>

Ask Brontes things like *"which of my devices are offline?"*, *"what's installed on this server?"*, or *"show me the Windows machines running an old agent version"*, and it answers from the assets in your [context](/documentation/get-started/concepts).

## Brontes vs. Perseus

Brontes and [Perseus](/documentation/multi-agent-system/agent-endpoint-specialist) both work with endpoints, but they do different jobs:

* **Brontes manages** — it knows what your registered assets are, how they're doing, and how they're configured. Think visibility and organization.
* **Perseus acts** — it investigates a host in depth and runs response actions on it (isolate, quarantine, kill a process, remediate, harden).

When you need to *understand your fleet*, that's Brontes. When you need to *do something to a host*, [Centurion](/documentation/multi-agent-system/agent-orchestrator) brings in Perseus.

<Note>
  Brontes is an **AI agent**. The **software agent** is the program installed on
  each host that reports the telemetry Brontes reads. The two share the word
  "agent" but are distinct — Brontes interprets what the software agent collects.
</Note>

## Where to Go Next

<CardGroup cols={2}>
  <Card title="Endpoints view" icon="table-list" href="/documentation/agent-endpoint-security/endpoints-view">
    Browse and organize the device inventory Brontes tracks.
  </Card>

  <Card title="Device details" icon="desktop" href="/documentation/agent-endpoint-security/device-details">
    Open a single host to see the same information, focused.
  </Card>

  <Card title="Perseus" icon="terminal" href="/documentation/multi-agent-system/agent-endpoint-specialist">
    The specialist that acts on hosts.
  </Card>

  <Card title="Deploying the agent" icon="download" href="/documentation/agent-endpoint-security/installation">
    Register a new asset so Brontes can track it.
  </Card>
</CardGroup>

<Tip>
  Scope your question to one machine by `@`-mentioning the device — Brontes then
  answers about just that host.
</Tip>