Skip to content
Protect your AI agent host

3 steps. Agent guardrails on the machine.

Install InnerWarden, connect the agent path, and start with local monitoring before you turn enforcement up.

01Install02Connect03Guard
  1. 01
    Install

    Put the guard on the host.

    Installs InnerWarden on the Linux machine where your AI agent runs. It sets up the local service, CLI, sensor, dashboard, and safe defaults so you can observe first before blocking anything.

    curl -fsSL https://www.innerwarden.com/install | sudo bash

    Want to inspect first? Run curl -fsSL https://www.innerwarden.com/install | less

  2. 02
    Connect

    Show InnerWarden where the agent acts.

    Run the setup flow, enable AI-agent protection, and connect the agent or tool path you want watched. InnerWarden starts by recording decisions locally so you can see what the agent is trying to do.

    innerwarden setup
    sudo innerwarden agent scan
    sudo innerwarden agent connect

    Start in monitor mode for a new agent. You get the audit trail first, then decide what should require review or block.

  3. 03
    Guard

    Let the agent work. Watch the risky parts.

    InnerWarden checks commands, suspicious destinations, shell activity, and host-level signals around the agent. You can keep simple actions quiet while risky actions get logged, reviewed, or blocked.

    innerwarden get status
    innerwarden get incidents
    innerwarden system test

Your agent gets a safer machine.

InnerWarden gives the host around your AI agent local visibility, command review, network signals, eBPF-backed detection, and an audit trail you keep. Start in monitor mode, then tighten the guardrails as the agent earns trust.