If we jack the financial penalties up, it will just screw over the consumers. We need to send people to prison. Bankrupting the company is an interesting strategy, but I think that'd just result in more consolidation.
So we're re-creating the Apollo 8 Mission 60 years later. 60 years after swinging around the moon, we are going to attempt the feat again. I'm having a hard time getting excited... Especially when some say it may not survive reentry because of politics (https://idlewords.com/2026/03/artemis_ii_is_not_safe_to_fly....)
One added benefit of knowing how to do this stuff is even when you hire it out, you typically get much better work out of contractors for a better price. If for no other reason than you can more effectively communicate requirements and handle potential surprises/changes (which is guaranteed to happen when renovating)
I think the project is a great idea. Really a structured framework around local, persistent memory with semantic search is the most important bit, IMO. (The SOUL feature already exists for most LLMs in the form of persistent markdown files.)
I also think it'd be a great starting point for building a private pub/sub network of autonomous agents (e.g. a company that doesn't want to exfil its password files via OpenClaw)
The name, however, is a problem. LocalGPT is misleading in 2 ways.
1. It is not Local, it relies on external LLM providers.
2. It is not a Generative Pretrained Transformer.
I'd highly recommend changing the name to something that more accurately portrays the intent and the method.
As a Wayland (and Sway) user; Overall, I have loved the Wayland experience. I am very grateful to all of the devs who've worked to make this happen.
That said, I feel that Wayland devs (and users) are just now (re)learning the ecosystem catch-22 problem. The ecosystem hasn't caught up with Wayland's new architecture because the layers don't line up the same way. This means entirely new layers (or adapters) need to be created all the way up the stack.
Also, this new design and these interfaces are almost completely undocumented, so it makes it very hard for a non-waylander to step in and contribute. I made a couple attempts to fix bugs, but after wading through Github issues for 4 hours, and getting no help on IRC, I gave up.
Unfortunately the ecosystem is responsible for building the rest of the stack, but it's hard, because there isn't much in the way of documentation or examples in the ecosystem. That's the catch. The ecosystem is expanding very slowly because there isn't much of an ecosystem.