I use Claude Code and Codex for coding but don't want my regular chats in those apps. I prefer to keep all my chats in one place so I can go back and search easily, that is why I built Vinaa.
Nowadays I'm more curious about how I can use AI for marketing. I'm experimenting it with building an SEO agent system
yes totally agree. I build macOS apps and found out that not every apps support this. One of the reason people buy my file search app https://www.fileminutes.com/ is, it is fully keyboard driven. I'm trying the same with my new AI chat app https://www.vinaa.ai/
While everyone is making their desktop AI app to do both coding and chat in the single app, I'm focusing on chat as first class citizen as I think coding/work and chat are two different things and need different dedicated apps.
While there are tons of similar apps out there, Vinaa is differentiate it from others in terms of user experience and performance. Download it to see it yourself. It is free during beta.
The issue is most of these demo are created by developers. Most of the developers don't have interests or skills in product and design. So they use AI to write code, not build product.
Another mistake everyone making is not building better and bigger products. What is used to take a month to develop is now possible in few days but most don't put the same effort as before to make bigger and better products. They just do they same as what they used to do before but quickly. This is a mistake. AI uplifted everything so products built with AI should go to next level.
I'm an indie mac app developer. My first product took me 6 months to develop without much AI. I just released my second app ( https://www.vinaa.ai/ ) but took the same time to develop as I wanted it to be the best AI chat app. So I spent a month building my own markdown renderer in TextKit as existing library are not fast enough. I wouldn't done this if I don't use AI.
I have recently completed building a large native macOS app and my take is that, for 90% of work, SwiftUI is good but for the 10% you would need AppKit.
For my app which is a AI chat app, I needed to load and show a large number of chat items in a list, SwiftUI is really bad at this. Another issue is, most of Swift markdown libraries don't perform perform well because each elements are rendered as SwiftUI views which introduced a lot of issues So I built my own renderer using TextKit. Even basic things like Settings window is broken. But I still prefer using SwiftUI as It gets the work done faster and I can always fallback to AppKit.
I find that web tech like React are worst than SwiftUI. React also has re-rendering and state management issues
Claude should have gone for native apps and demonstrated that it is possible to do anything with their AI.
I'm currently building a macOS AI chat app. Generally SwiftUI/AppKit is far better than Web but it performs bad in few areas. One of them is Markdown viewer. Swift Markdown libraries are slow and lacks some features like Mermaid diagrams. To work around this, some of my competitors use Tauri/Electron and few others use WKWebView inside Swift app.
Initially I tried WKWebView. Performance was fine and the bridge between JS and Swift was not that hard to implement but I started seeing few problems especially due to the fact that WebView runs as separate process and usually a single WebView instance is reused across views.
After few attempts to fix them, I gave up the idea and tempted to go fully with Web rendering with Tauri but as a mac developer I couldn't think about building this app in React. So I started building my own Markdown library. After a month of work, I now have a high-performance Markdown library built with Rust and TextKit. It supports streaming and Markdown extensions like Mermaid.
Most of the code was written by Claude Opus, and some tricky parts were solved by Codex. The important lesson I learned is that I’m no longer going to accept limitations in tech and stop there. If something isn’t available in Swift but is available in JS, I’m going to port it. It’s surprisingly doable with Claude.
> Claude should have gone for native apps and demonstrated that it is possible to do anything with their AI.
Using IntelliJ I actually find myself wishing for an integrated webview of Github Copilot. The native view is absolutely terrible, jumping up and down non stop.
I'm working on a decade old problem - searching files in macOS. Started building to solve my own issues after realising none of the tools supports what I need. Very excited about the upcoming feature that I'm releasing this week as it lets you search inside specific folders - something that is not offered by other tools
I use Claude Code and Codex for coding but don't want my regular chats in those apps. I prefer to keep all my chats in one place so I can go back and search easily, that is why I built Vinaa.
Nowadays I'm more curious about how I can use AI for marketing. I'm experimenting it with building an SEO agent system
reply