Big news: We’re joining Cloudflare.
Replicate’s going to carry on as a distinct brand, and all that’ll happen is that it’s going to get way better. It’ll be faster, we’ll have more resources, and it’ll integrate with the rest of Cloudflare’s Developer Platform.
The API isn’t changing. The models you’re using today will keep working. If you’ve built something on Replicate, it’ll keep running just like it does now.
So, why are we doing this?
At Replicate, we’re building the primitives for AI: the tools and abstractions that let software developers use AI without having to understand all the complex stuff underneath.
We started with Cog, an open-source tool which defines a standard format for what a model is. Then, we created Replicate, a platform where people can share models and run them with an API. We’ve defined what a model is, how you publish it, how you run it, how you get data in and out.
These abstractions are like the low-level primitives of an operating system. But what’s interesting is that these primitives are running in the cloud. They have to — they need specialized GPUs and clusters to scale up in production. It’s like a distributed operating system for AI, running in the cloud. In other words, the network is the computer.
Who has the best network? Cloudflare.
Cloudflare has built so many other parts of this operating system. Workers is the perfect platform for running agents and glue code. Durable Objects for managing state, R2 for storing files, WebRTC for streaming media.
Now that we’ve got these low-level abstractions, we can build higher-level abstractions. Ways to orchestrate models and build agents. Ways to run real-time models, or run models on the edge.
... continue reading