How it works

Architecture and deployment

The runtime, Intelligence Packs, drivers, and how a deployment fits inside a customer environment.

Huitzo is a self-hosted AI runtime for regulated enterprises. It runs AI applications — Intelligence Packs — inside your existing infrastructure, so sensitive data never leaves your environment. Unlike cloud AI platforms (AWS Bedrock, Azure AI), Huitzo is model-agnostic and deploys in weeks instead of the 12-18 months a custom build typically requires.

The runtime

Like the Linux kernel hosts processes, the Huitzo runtime hosts Intelligence Packs. It is deployed inside the customer environment as a single Linux service.

Intelligence Packs

An Intelligence Pack is an AI application — the unit a team builds, tests, and deploys. Like a containerized application on a Linux host, but with one shared interface to models, storage, and drivers.

Drivers

Drivers extend Huitzo to external and internal systems — like Linux device drivers extend the kernel. Standard drivers ship for OpenAI, Anthropic, S3-compatible storage, and SQL. Custom drivers connect the runtime to proprietary systems.

Deployment in five steps

  1. Step 1

    Provision the runtime host

    Stand up a Linux host inside the customer environment. The runtime needs network access to the chosen model provider — or to a self-hosted model — and to the systems the Intelligence Pack will integrate with.

  2. Step 2

    Install the Huitzo runtime

    Run the Huitzo install script. The runtime is a self-contained service. No data is sent outside the host during installation.

  3. Step 3

    Configure drivers

    Drivers connect the runtime to model providers, object storage, and internal systems. Standard drivers ship out of the box; custom drivers extend the runtime to anything proprietary.

  4. Step 4

    Deploy an Intelligence Pack

    An Intelligence Pack is the application unit that runs on the runtime. Build locally with the Python SDK, then deploy to the runtime.

  5. Step 5

    Connect the Hub

    The Hub is the operations dashboard for monitoring and managing deployed Intelligence Packs. Authentication plugs into the customer identity provider.

How it works — questions

What gets installed on customer infrastructure?
A single Linux service — the Huitzo runtime — plus the Intelligence Packs the customer chooses to deploy. There is no Huitzo-managed cloud component on the data path.
Where do AI models run?
Huitzo is model-agnostic. The customer chooses: a hosted provider (OpenAI, Anthropic) reached over the network, or a self-hosted model on customer infrastructure for fully air-gapped deployments.
How long does deployment typically take?
Most production deployments take weeks rather than the 12-18 months a custom build typically requires. Air-gapped environments take longer because of additional integration scope.
How do Intelligence Packs differ from containers?
An Intelligence Pack is a Huitzo-runtime application — like an ELF binary on Linux. It runs on top of the runtime, which provides the shared interface to models, storage, and drivers. A container is a packaging format; an Intelligence Pack is an application unit.