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

# Capabilities Overview

> Discover what makes IronClaw unique

IronClaw combines long-term memory, event-driven automation, parallel execution, and strict isolation controls so agents can run real workflows safely.

<CardGroup cols={2}>
  <Card title="Security" icon="shield" href="/security">
    Defense-in-depth controls for prompt safety, sandboxing, leak detection, and network boundaries.
  </Card>

  <Card title="Memory" icon="database" href="/capabilities/memory/memory">
    Durable, searchable memory with identity files that persist behavior and context across sessions.
  </Card>

  <Card title="Routines" icon="clock" href="/capabilities/routines/cron">
    Scheduled, heartbeat, and reactive execution models for proactive and event-driven automation.
  </Card>

  <Card title="Jobs" icon="suitcase" href="/capabilities/jobs/jobs">
    Parallel job orchestration with state transitions, retries, and self-repair for stuck execution.
  </Card>

  <Card title="Skills" icon="sparkles" href="/capabilities/skills">
    Context-activated prompt extensions with scoring, gating, and trust-based tool attenuation.
  </Card>

  <Card title="Sandboxed Tools" icon="cubes" href="/capabilities/sandboxed-tools">
    Wasm-based tool isolation with explicit capabilities, resource limits, and controlled I/O.
  </Card>
</CardGroup>