But maybe there is some cool stuff here. A lot of prolific AI-assisted engineers I know have their own advanced plan modes, and the CEO plan mode in the repo is interesting (although very token heavy)
In v0, people can add e.g. Supabase, Neon, or Stripe to their projects with one click. We then auto-connect and auth to the integration’s remote MCP server on behalf of the user.
v0 can then use the tools the integration provider wants users to have, on behalf of the user, with no additional configuration. Query tables, run migrations, whatever. Zero maintenance burden on the team to manage the tools. And if users want to bring their own remote MCPs, that works via the same code path.
We also use various optimizations like a search_tools tool to avoid overfilling context
But then the LLM needs to write its own tools/code for interacting with said service. Which is fine, but slower and it can make mistakes vs officially provided tools
My friend and I were able to give claude a (no longer updated) unity arcade game. It decompiled it and created a one-to-one typescript port so it can run in the browser and now we're adding multiplayer support (for personal use, don't worry HN - we won't be distributing it). I'm very excited for what AI can do for legacy software.
v0 actually can directly copy files out of its examples and then apply edits. This saves it from having to write out the long examples verbatim. The rest of your comment is accurate
We've merged several duplicate threads on this topic. Please keep the discussion substantive and avoid personal attacks.
Also, yes, my username is silly. The previous dang retired in 2031 and I lost a bet.
A lot of react native apps do not feel native. Even more are just low quality. Many v0 users were asking us how exactly we did X or Y to make it feel so good, which is what this post is for.
I like it. This post is the perfect level of detail for people obsessed about UX minutiae.
Personally, I'm not a huge Vercel fan (IMO: lots of hype, business model encourages developer ecosystem lock-in), but this post gave me more trust in the design/UX care that goes into their products (which is a core Vercel strength).
You accumulate web frameworks and maintainers similar to the winning strategy at Monopoly, until you have implicit control over entire ecosystems. Whether you actually seize that control or not doesn’t even matter, because you are in a position to do so—by strategic neglect, or increased attention to whatever project supports your current business goals best.
No single entity should have that much power, especially no venture-capital backed one.
You might want to look at the comments in this thread [1], to get a feeling of the "accusations", as you want to call it... I'm not "accusing" anything, I really couldn't care less, I don't use Vercel/Next.js and never will, but maybe you should read the linked thread, too see how people (at least on HN) see your company.
I think the fact that OpenNext can exist speaks to the opposite
A Next.js project can be deployed to a Docker image very easily [1]. If you want to use a provider that has their own infrastructure setup, then yes you need to do some work (that OpenNext does for you). But that's true of practically any framework deploying to a host that does more than just serve the docker container.
Looks good, I appreciate the level of detail especially as bad UX can cause churn on mobile. Since it's React Native, are there plans for an Android version? I guess you guys wanted to get an iOS version out first instead of releasing both in parallel, for bug testing, improvements etc?
Overall, our focus right now is iOS, but we want to do Android at some point. Even though we used React Native, we also wrote a good amount of native Swift code under the hood to power native modules.
It seems especially good at threejs / 3D websites. Gemini was similarly good at them (https://x.com/aymericrabot/status/1991613284106269192); maybe the model labs are focusing on this style of generation more now.
But maybe there is some cool stuff here. A lot of prolific AI-assisted engineers I know have their own advanced plan modes, and the CEO plan mode in the repo is interesting (although very token heavy)
https://github.com/garrytan/gstack/blob/main/plan-ceo-review...