# Agents

import { CardGrid } from "@astrojs/starlight/components"
import LinkCard from "@/components/starlight/LinkCard.astro"

Agents are the central primitive in Ren: versioned, configurable definitions that run autonomous reasoning loops. But agents don't work alone. They compose [skills](/docs/deep-dives/concepts/agents/skills/) for on-demand capabilities, [MCPs](/docs/deep-dives/concepts/agents/mcps/) for external tool access, and [cron triggers](/docs/deep-dives/concepts/agents/cron-triggers/) for scheduled execution. Together, these form the capability stack that defines what an agent can do.

<CardGrid>
  <LinkCard title="Agents" icon="rocket" href="/docs/deep-dives/concepts/agents/agents/">
    Versioned definitions that run.
  </LinkCard>
  <LinkCard title="Skills" icon="puzzle" href="/docs/deep-dives/concepts/agents/skills/">
    Reusable capabilities agents compose.
  </LinkCard>
  <LinkCard title="MCPs" icon="seti:plan" href="/docs/deep-dives/concepts/agents/mcps/">
    External tools via Model Context Protocol.
  </LinkCard>
  <LinkCard title="Cron triggers" icon="seti:clock" href="/docs/deep-dives/concepts/agents/cron-triggers/">
    Run agents on a schedule.
  </LinkCard>
</CardGrid>