100% FREE Serverless AI Chat on Cloudflare Open-source AI chat app running entirely on Cloudflare...100% FREE Serverless AI Chat on Cloudflare Open-source AI chat app running entirely on Cloudflare...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
100% FREE Serverless AI Chat on Cloudflare Open-source AI chat app running entirely on Cloudflare Workers, R2, and Workers AI. No traditional backend - inference lives at the edge. Code: https://github.com/ranajahanzaib/waichat Click to Deploy on Cloudflare: https://deploy.workers.cloudflare.com/?url=https://github.com/ranajahanzaib/WaiChat/tree/v0.1.5-alpha.2 Most AI chat apps assume a conventional backend: a server somewhere, a managed database, an API layer in between. WaiChat doesn't have one. It runs entirely on Cloudflare's edge primitives - Workers for compute, D1 for storage, and Workers AI for inference - so there's no origin server to provision, patch, or scale. That's a different set of constraints than a typical Node backend. Workers have execution limits and a stateless-by-default model, D1 is SQLite at the edge rather than a full Postgres, and inference has to run through Workers AI's model catalog rather than an arbitrary hosted API. Building a real chat experience inside those constraints means the request path, the data model, and the inference calls all have to be designed for the edge from the start, not adapted to it afterward. I built WaiChat solo, open source, as exactly that kind of project - no client, no spec, just deciding what a chat app should look like when it's edge-native end to end. It's on GitHub for anyone who wants to see how the pieces fit together.
Post image
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started