Skip to main content

Omnigent quickstart

Beta

Omnigent is in Beta. For the open-source documentation, see the Omnigent documentation.

Omnigent runs as a managed deployment on Databricks: the server that coordinates your sessions is managed for you, and you sign in with your Databricks workspace identity. This page covers the setup that is specific to Databricks. See the open-source Omnigent documentation for more information about Omnigent features and functionality.

Prerequisites

You must have a workspace in a region that supports Databricks Unity AI Gateway. See Databricks feature availability by region.

To install Omnigent using the CLI, you must have:

  • Python 3.12+
  • Node.js 22 LTS with npm and tmux

Launch Omnigent on your own machine

Install Omnigent on your laptop or a Databricks VM, and register it as a host.

  1. Install Omnigent with the databricks extra, which adds the managed-platform integration.

    Bash
    curl -fsSL https://omnigent.ai/install.sh | sh -s -- --extra "databricks"
  2. Set up model credentials. Run omni setup, then add a credential for one or more agent harnesses:

    Bash
    omni setup

    Running omni setup in the terminal to start adding harness credentials.

    • To route models through AI Gateway, choose Databricks in the credential picker and enter your workspace URL.
    • Otherwise, provide your own API key, subscription, or gateway.
  3. Sign in with your Databricks identity and register the machine as an Omnigent host:

    Bash
    omni login <workspace-url>
    omni host --server <workspace-url>
  4. In your web browser, navigate to <workspace-url>/omnigent.

  5. Select New session.

  6. Open the host picker and select the machine you registered.

    The Omnigent workspace UI host picker with a registered local host selected.

  7. Describe a task in the composer and send it to start the session.

Connect the desktop app

The Omnigent desktop app is optional and is currently available on macOS only. Install the desktop app, then, once you have created a host, select Connect to new server in the app and enter your workspace URL.