I don't think that's an alternative to US hyperscalers. Scaleway is the closest thing there is. Replacing a single service with 10 others is not really an alternative in my opinion.
Not putting all your eggs in one basket is a good choice. I think the AWS service catalog makes you adopt more than you need or want anyway, it is a great way of locking people into one vendor.
I would argue that with AI, this becomes less of an issue. Connect N services, deploy to bare metal. Granted, AI is an additional cost now local or remote. But so is the MacBook people use to develop their software.
Isn't the whole point of Cloudflare's Workers to pay per function? If it is self-hosted, you must dedicate hardware in advance, even if it's rented in the cloud.
Many companies run selfhosted servers in data centers still need to run software on top of this. Not every company needs to pay people to do things they are capable themselves.
Having options that mimic paid services is a good thing and helps with adoptability.
I get the point. But those are incomparable. Hyperscalers don't compete on price, they compete on scale and services offered. The compliance, the security, the support, the integrations, the backups.
Can you host your own object storage open source software, key vault OSS, VPN, queue service, container registry, logging, host your own Postgres/MySQL? Sure, but you will need to research what is best, what is supported, keep it maintained, make sure to update it and that those updates don't break anything, wake up in the middle of the night when it breaks, make sure it's secure. And you would still need to handle access control across those services. And you would still need a 3rd party service for DDoS protection, likely CDN too. And you would likely need some identity provider.
