Rapidly iterate your AI on your own infra

Runhouse OSS πŸƒβ€β™€οΈ

A magical AI/ML DevX: Develop, debug, and run Python directly on your own infrastructure.

Get started

Runhouse Den 🏠

A collaborative home for your AI stack: share and reuse living functions, environments, and compute.

Book a demo

Runhouse OSS

Effortlessly iterate and deploy your AI apps as shareable, reusable services.

Easy to get started

No-stress installation.
Anywhere you use Python.

$pip install runhouse

Reduce research-production time

Runhouse enables high iteration and rapid experimentation on real infrastructure with real data. Move from AI research to production faster.

Graphic showing a laptop with a Python logo connecting to modules and functions running on cloud compute

Get more out of your own compute

Compatible with all your favorite cloud providers.
Select from the most available or cost-effective.

List of cloud provider logos: AWS, Google, Azure, Kubernetes, AWS Lambda, and SageMaker

Turn your scripts into services in less than 10 lines of code.

import runhouse as rh # Easily provision clusters with the resources you want, # optimizing cost my_cluster = rh.cluster( "my_cluster", instance_type="A10G:1", provider="cheapest" ) # Send your existing Python code def local_preproc_fn(dataset, filters): ... remote_preproc_fn = rh.function(local_preproc_fn).to(my_cluster) # Call it normally, but it's running remotely processed_data = remote_preproc_fn(dataset, filters)

Sub-second redeployment

so you can iterate live on the real infra

Works with your existing code

so you can focus on AI, not DSLs and packaging

A real high-performance service

so you can use it from anywhere, in any language

Use Cases

AI Primitives

Model InferenceTrainingPreprocessing

Deploy Llama3 on AWS EC2

Higher-Order Services

Inference pipelinesWorkflow pipelines

LangChain RAG app with OpenAI and Chroma

Controls & Safety

Content moderationPII Obfuscation

Coming soon...

Data Access

Data lake viewKey value store

Coming soon...

Runhouse Den

Your AI foundation all in one place. Iterable, flexible, and collaborative.

Line illustration showing researchers and engineers connected to an AI app or code via lines before and after changes

Before: Tightly Coupled and Brittle

Difficult to update, A/B test, or scale to new infrastructure

Line illustration showing researchers and engineers connected a block "/team/bert_preprocessing" that decouples a connection to changing AI code

With Den: Decoupled and Nimble

Easily update and scale services without breakage

AI platform excellence out of the box.

Try it out
Screenshot of a search interface with a search bar and listed resources

Search & Sharing

Runhouse Den provides you with an interface to explore your AI services. Easily share with your teammates, search through your applications, and view details all in one place.

Screenshot of a line graph and list of user requests

Observability

Gain insights by viewing how your teammates consume your AI apps and services. Explore changes over time and make better decisions based on trends.

Screenshot of a resource page and user access list

Auth & Access Control

Den makes it easy to control access to your services. Provide individual teammates with read or write access, or choose "public" visibility to expose public API endpoints.

Start building your AI foundation.

Book a demo