Skip to content
DocumentationTry Hanzo
Serverless Computing

Hanzo Functions

Functions that run on Kubernetes. Hand it a handler and a runtime; it builds the image, deploys it, routes to it, and keeps as many copies alive as the traffic needs — down to none.

export async function handler(req, res) {
// Process incoming data
const { data } = await req.json();
const result = await processData(data);

// Return JSON response
return Response.json({
success: true,
data: result
})
}

What you get

A handler file, a trigger, and the cluster you already run

Python, Go, Node.js, Rust

Name a runtime and point at a handler file. When the language you want is not one of them, bring a container you built yourself and deploy that instead.

Warm before the request

Pools are prewarmed, so a function is not booting on the request that needed it. Scale to zero is still the default when nothing is calling.

On your own cluster

Install it with Helm into Kubernetes you already run. Functions are ordinary workloads there, so quotas, node pools and network policy keep meaning what they meant.

A GPU is a normal ask

A function can request an NVIDIA GPU and be scheduled onto a node that has one. That is what lets model work be a function instead of a service somebody has to keep alive.

Triggers, not just HTTP

An HTTP route, a cron schedule, a Kafka topic, a RabbitMQ queue. The trigger is its own object, so the same handler can answer to several without knowing about any of them.

Versions you can move between

Blue/green and canary between versions of a function, so backing out a bad deploy is a traffic decision rather than another build.

Common Use Cases

Hanzo Functions powers a wide range of serverless applications

API Backends

Build complete REST or GraphQL APIs with automatic scaling and no server management.

  • Custom middleware for authentication and validation
  • API versioning and documentation generation
  • Automatic OpenAPI schema generation

Real-time Processing

Process events in real-time with automatic scaling for traffic spikes.

  • Webhook handlers for third-party services
  • Event-driven data transformation and enrichment
  • Real-time analytics processing

AI/ML Inference

Deploy machine learning models for inference with built-in GPU acceleration.

  • Image and text classification
  • AI chatbots and virtual assistants
  • Real-time recommendations

Scheduled Tasks

Run tasks on a schedule without maintaining a dedicated server.

  • Periodic data cleanup and maintenance
  • Scheduled reports and notifications
  • Recurring data integration and ETL processes

Ready to Build?

Get started with Hanzo Functions today and deploy your first serverless function in minutes.

Get started with Functions

Open source

License: Apache-2.0hanzoai

Get Functions

Serverless functions