Now accepting pilot programs
Request Pilot
Integrations

Connect Everything, Effortlessly

Out-of-the-box integrations with the tools you already use. Plug and play architecture means zero setup code.

Integrations

One Object.
Every Service.

Traditional stacks mean separate SDKs, separate credentials, and dozens of lines of setup before you write business logic. Huitzo centralizes every service behind one interface — AI, storage, email, HTTP — configured and ready.

ctx.llm · ctx.files · ctx.email · ctx.http · ctx.telegram
invoice_processor.py
# Three SDKs, three credential systems
import openai
import boto3
import sendgrid
# Manual client setup
ai = openai.Client(api_key=os.environ["OPENAI_KEY"])
s3 = boto3.client(
"s3",
aws_access_key_id=os.environ["AWS_KEY"],
aws_secret_access_key=os.environ["AWS_SECRET"],
)
mail = sendgrid.SendGridAPIClient(
api_key=os.environ["SENDGRID_KEY"]
)
async def process_invoice(invoice):
summary = ai.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": invoice.text}]
)
s3.put_object(
Bucket="invoices",
Key=f"{invoice.id}.json",
Body=summary
)
mail.send(Mail(
from_email="billing@co.com",
to_emails=invoice.contact,
subject="Invoice processed",
html_content=summary
))
~35 lines of plumbing
The Traditional Way
invoice_processor.py
from huitzo import command, Context
@command("process_invoice")
async def process(invoice: Invoice, ctx: Context):
# Summarize with AI
summary = await ctx.llm.complete(invoice.text)
# Save to cloud storage
await ctx.files.write(f"invoices/{invoice.id}.json", summary)
# Notify via email
await ctx.email.send(
to=invoice.contact,
subject="Invoice processed",
body=summary
)
return summary
~15 lines same result
With Huitzo

~60% less code

Focus on your logic, not plumbing

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

Available Integrations

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

Built-in

Ready to use via ctx object. Configure credentials in the platform, use in your code.

Custom Connector

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

AI / LLM

OpenAI

Built-in

GPT-4, GPT-3.5, embeddings

ctx.llm

Anthropic

Built-in

Claude models

ctx.llm

Communication

SendGrid

Built-in

Transactional email

ctx.email

SMTP

Built-in

Standard email protocol

ctx.email

Telegram

Built-in

Bot messaging

ctx.telegram

Slack

Custom Connector

Team messaging

Custom connector

Storage & Database

Files

Built-in

S3, Azure Blob, GCS, local

ctx.files

PostgreSQL

Custom Connector

Relational database

Custom connector

Redis

Custom Connector

In-memory cache

Custom connector

Cloud Providers

AWS

Custom Connector

Amazon Web Services

Custom connector

Azure

Custom Connector

Microsoft Azure

Custom connector

GCP

Custom Connector

Google Cloud Platform

Custom connector

DevOps

Docker

Custom Connector

Container runtime

Custom connector

GitHub

Custom Connector

Git & CI/CD

Custom connector

Business Tools

Stripe

Custom Connector

Payments

Custom connector

Zapier

Custom Connector

Workflow automation

Custom connector

HubSpot

Custom Connector

CRM

Custom connector

Notion

Custom Connector

Documentation

Custom connector
Flexible Architecture

How It Works

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. 

@command("calculate")
async def calc(data: Input, ctx: Context):
    return process(data)
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 ctx. 

# manifest.yaml
integrations:
  - llm
  - email
03

Add Custom Connectors

Enterprise Extension

Need to connect to proprietary systems? Enterprise customers can extend the platform with custom connectors for any service or protocol. 

# Connect any system
async def query(self, ...):
    # Your implementation
Enterprise

Custom
Integrations

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 enterprise systems (SAP, Oracle, mainframes)
  • Integrate proprietary algorithms (Risk models, pricing engines)
  • Support future hardware (Specialized accelerators, IoT devices)
  • Deploy on your infrastructure (On-premise, 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
Enterprise Custom
Unlimited
custom integrations

Start integrating
today

Add powerful integrations to your intelligence applications in seconds. See how Huitzo connects to the tools your team already uses.

Schedule a Call See Platform Pricing