Hi there! Welcome to our first blog post. We’ll have more substantive content here soon, but for starters we thought we’d kick it off by introducing ourselves and sharing a bit about what we’re building.

Who are we?

We are a small team of engineers and machine learning enthusiasts. Our mission is to make machine learning more accessible. People creating machine learning models should be able to share them in a way that other people can use, and people who want to use machine learning should be able to do it without getting a PhD.

To learn more about our team and philosophy, check out our about page.

What is Cog?

Cog is an open-source tool that lets you package machine learning models in a standard, production-ready container. You can use Cog to deploy your packaged model to Replicate, or your own infrastructure.

To get started using Cog, check out the GitHub repository at replicate/cog.

What is Replicate?

Replicate is a place to share and run your machine learning models.

You use Cog to push your model to Replicate, and we take care of running it in the cloud. We use the interface you’ve defined for your Cog model to build a web page where anyone can run your model.

What are you building?

Are you working on a model that you’d like to share with the world? Let us know about it!

Replicate is not open for everyone to create models just yet, but we’ve started adding folks to our private beta. Join our waitlist and we’ll notify you when we’re ready for new users. You can also join our Discord server to chat with our team, or send us a good old-fashioned email at team@replicate.com. We’d love to hear from you.

✌️