You’re not locked into a model, but you likely are locked in to a platform. This DX and convenience just shifts within the stack where the lock in occurs. Not criticizing - just a choice people should be conscious of.
Another useful question to ask: since you’re likely using 1 of 3 frontier models anyway, do you believe Claude Agent SDK will increasingly become the workflow and runtime of agentic work? Or if not Claude itself, will that set the pattern for how the work is executed? If you do, why use a wrapper?
Re: lessons from coding agents, we're building some of the key abstractions like sandboxes, filesystem, skills/knowledge as Mastra primitives in over the next month.
For any agent you're shipped to production though you probably want a harness that's open-source so you more fully control / can customize the experience.
I think that’s fair, totally, but I also think a Skill would be considered a primitive in and of itself by Anthropic. So to me it’s still wrapping an open primitive. Anyway, trade offs.
This product barely works. It can't connect to the browser extension and when I share folders for it to access, nothing happens. I love early previews but maybe one more week?
I started with an Apple Lisa. I’ve never enjoyed Apple products less than I do right now. And there were some rough days in the 90s! I switched from a AW Ultra 3 to a Garmin. Considering an S26 because of the semi-matte screen. The Mac, though, I probably can’t replace, but man Tahoe/Liquid Glass sucks.
Commercialization may be a net good for open source, in that it helps sustain the project’s investment, but I don’t think that means that you’re somehow entitled to a commercial business just because you contributed something to the community.
The moment Tailwind becomes a for-profit, commercial business, they have to duke it out just like anyone else. If the thing you sell is not defensible, it means you have a brittle business model. If I’m allowed to take Tailwind, the open source project, and build something commercial around it, I don’t see why OpenAI or Anthropic cannot.
The difference is that they are reselling it directly. They charge for inference that outputs tailwind.
It's fine to have a project that generates html-css as long as the users can find the docs for the dependencies, but when you take away the docs and stop giving real credit to the creators it starts feeling more like plagiarism and that is what's costing tailwind here.
I wonder if this is all due to AI, or whether shadcn/ui's popularity (and blocks, and themes, and registry of paid component libraries) has also impacted them. That's my personal go to, and not Tailwind UI paid, and that's not because of LLMs.
Another useful question to ask: since you’re likely using 1 of 3 frontier models anyway, do you believe Claude Agent SDK will increasingly become the workflow and runtime of agentic work? Or if not Claude itself, will that set the pattern for how the work is executed? If you do, why use a wrapper?
reply