Skip to main content

INTEGRATIONS

How does Huitzo connect to my existing stack?

Out-of-the-box integrations with the tools you already use. Plug-and-play architecture, no glue code, and a custom-driver pattern for anything proprietary.

Huitzo is a self-hosted AI runtime that connects to your existing stack through one Python interface. Cloud AI platforms such as AWS Bedrock or Azure AI lock integrations into their own connector catalog. Built-in integrations for OpenAI, Anthropic, S3-compatible storage, and email work out of the box. Databases, cloud services, and internal systems plug in through the custom-driver pattern, which mirrors how Linux device drivers extend the kernel: implement the interface, register it, and call it from any Intelligence Pack. A custom driver is typically live in weeks, not the 12-18 months a custom integration layer takes to build from scratch.

FIG. 01. THE PORT ON THE WALL.

YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS YOUR NETWORK BOUNDARY YOUR DATA POSTGRES FILES YOUR INFRASTRUCTURE HUITZO RUNTIME ONE INTERFACE INTELLIGENCE PACKS INTAKE REVIEW AUDIT DRIVER MODEL PROVIDERS OPENAI ANTHROPIC PROMPTS LEAVE YOUR DATA STAYS
Drivers are the port on your network boundary. Built-in or custom, it is one interface either way.

ONE INTERFACE

How does Huitzo replace separate SDKs for every AI provider and service?

No separate SDKs. No separate credentials. AI models, storage, email, and HTTP, all accessible through a single context object. Configured and ready at runtime.

AI Models
Language models
File Storage
Object and local storage
Email
Transactional email
HTTP APIs
REST APIs and webhooks
Messaging
Bot messaging

One interface for all services

AI, storage, email, and HTTP through one interface

Zero credential setup

Platform handles secrets at runtime

Built-in resilience

Retries and error handling on every call

Swap providers in config

Switch from OpenAI to Anthropic without code changes

THE CATALOG

Available Integrations

From AI providers to business tools, connect with the services your workflows need.

Built-in

Ready out of the box through the runtime's one shared interface. Configure credentials in the platform and every Intelligence Pack can use it.

Custom Connector

Build a custom connector to add support for any service or protocol.

AI / LLM

OpenAI

Built-in

GPT-4, GPT-3.5, embeddings

Language models

Anthropic

Built-in

Claude models

Language models

Communication

SendGrid

Built-in

Transactional email

Email

SMTP

Built-in

Standard email protocol

Email

Telegram

Built-in

Bot messaging

Messaging

Slack

Custom Connector

Team messaging

Messaging

Storage & Database

Files

Built-in

S3, Azure Blob, GCS, local

File storage

PostgreSQL

Custom Connector

Relational database

Database

Redis

Custom Connector

In-memory cache

Cache

Cloud Providers

AWS

Custom Connector

Amazon Web Services

Cloud services

Azure

Custom Connector

Microsoft Azure

Cloud services

GCP

Custom Connector

Google Cloud Platform

Cloud services

DevOps

Docker

Custom Connector

Container runtime

Containers

GitHub

Custom Connector

Git & CI/CD

Code and CI

Business Tools

Stripe

Custom Connector

Payments

Payments

Zapier

Custom Connector

Workflow automation

Automation

HubSpot

Custom Connector

CRM

CRM

Notion

Custom Connector

Documentation

Documentation

FLEXIBLE ARCHITECTURE

What happens if Huitzo doesn't have a built-in integration for my tool?

Ship your packs with exactly the integrations you need, or none at all.

01

Ship Without

Pure Logic Packs

Build Intelligence Packs that contain pure business logic with no external dependencies. Perfect for data transformations, calculations, and algorithmic workflows.

02

Ship With Built-in

Declare and Use

Declare required integrations in your pack manifest. The platform handles credentials and configuration at runtime. Your code just uses the context object.

03

Add Custom Connectors

Extend the Runtime

Need to connect to proprietary systems? Licensed deployments can add custom connectors for any service or protocol.

CUSTOM CONNECTORS

Can I build a custom connector for a proprietary internal system?

Huitzo's platform separates your AI logic from integration details. Extend the platform with custom connectors for any system your team uses.

  • Connect to legacy internal systems (SAP, Oracle, mainframes)
  • Integrate proprietary algorithms (Risk models, pricing engines)
  • Support future hardware (Specialized accelerators, IoT devices)
  • Deploy on your infrastructure (On-premises, private cloud)
Schedule a Call
Core
Huitzo Platform
Runtime, Scheduling, Context Management
Integration Interface
Built-in
LLM
Email
HTTP
Files
Custom
SAP
Legacy DB
IoT Hub
Your System
Included
Custom connector
Unlimited
custom integrations

QUESTIONS

Integration questions

Does Huitzo work with OpenAI?

Yes. Huitzo is model-agnostic. Intelligence Packs can call OpenAI models, Anthropic models, open-weight models, or models the customer hosts internally, all through one Python interface.

Can I add a custom integration?

Yes. Custom drivers let teams extend Huitzo to internal systems and proprietary services. The driver pattern is the same as adding a Linux device driver: implement the interface, register it, and use it from any Intelligence Pack.

What protocols are supported out of the box?

HTTP and HTTPS for REST APIs, native SDKs for major AI providers (OpenAI, Anthropic), S3-compatible object storage, and transactional email. Databases such as PostgreSQL and Redis, along with internal infrastructure, are reached through custom drivers.

Does Huitzo run inside an air-gapped environment?

Yes. Self-hosted deployment is the default. An Intelligence Pack can run entirely behind the customer's firewall, including with self-hosted models, with no external network calls.

Can I integrate with my existing identity provider?

Yes. Authentication and access control plug into the customer's existing identity provider (Okta, Azure AD, internal SSO) rather than creating a parallel user directory.

How do Intelligence Packs share state across integrations?

Through one shared context interface. A Pack can call a model, read from object storage, and write to a database without bridging code between services.

AI operating system for regulated companies

Simple by design. Built to scale. Runs where your data lives.

Product access
Huitzo Hub is available by invitation for teams evaluating the product.
Book a working session
Read the specification SPEC v0.1. DRAFT. Inspect a sample audit record SAMPLE. VERIFIED AT BUILD TIME.