Skip to content

Quick Start

This guide gets you from zero to a working Omnodex installation with live risk detection. The whole process takes under five minutes.

  1. Install Omnodex:

    Terminal window
    git clone https://github.com/omnodex/omnodex.git
    cd omnodex
    npm install && npx tsc -b
    npm install -g .

    The omnodex command is now available globally, pointing at your source build. The source build always has the latest features and fixes.

  2. Install the hook into your agent:

    Terminal window
    omnodex install claude-code

    This registers Omnodex as a Claude Code hook. The next time Claude Code runs, all tool calls will be traced automatically.

  3. Connect to the cloud dashboard (optional):

    This starts a device code flow: the CLI displays a short code and a URL. Open the URL in your browser, sign in (or create an account) at dashboard.omnodex.com, and enter the code. The connection completes automatically - your API token and sync passphrase are configured for all future sessions. The passphrase is transferred end-to-end encrypted (the server never sees it).

    Skip this step if you only want the local dashboard.

  4. Run your agent normally. There is nothing else to configure. Omnodex intercepts in the background with zero impact on the agent’s behavior.

  5. View results:

    Terminal window
    omnodex dashboard

    Opens the Omnodex dashboard at http://localhost:7890 with a real-time view of all traced events and risk findings.

After running your agent with Omnodex installed, the dashboard shows:

  • A timeline of all tool calls and actions the agent took
  • Risk indicators flagging any concerning behavior (credential exposure, sensitive file access, unexpected network calls)
  • Full context for each event - what was called, with what parameters, and what it returned