What are you building, and what does your stack look like?
by•
I am a Computer Science student doing research into how solopreneurs and small startups create new apps and what their stack looks like. Particularly, I'm interested in how you handle things like authentication, billing, and permissions/authorization in your apps.
Let me know what you're working on below and how you're going about it -- I'd love to connect for some quick calls to learn about your product and talk about your process in building it!
1.3K views
Replies
building an open-source AI dashboard for PM teams. the interesting part right now is the governance layer - tracking and triage are mostly automated, but who governs what the agents decide is still wide open. that's the part most tools skip.
Building TokenBar, a macOS menu bar app that tracks AI token usage and spending across 20+ providers (OpenAI, Anthropic, Cursor, Gemini, Copilot, OpenRouter, etc.).
Stack: Swift + SwiftUI, native macOS. No Electron, no web views. Everything runs locally on your Mac. I chose native because menu bar apps need to be lightweight and fast. Nobody wants a 200MB Electron app just to show a number in their menu bar.
The trickiest part of the stack was handling all the different provider APIs. Each one returns usage data in a completely different format, different auth methods, different rate limits. It is basically 20+ micro-integrations stitched together.
tokenbar.site if anyone wants to check it out. $5 one-time purchase.
Building TokenBar (tokenbar.site) - a native macOS menu bar app that tracks your AI spending across 20+ providers in real time.
Stack: Swift + SwiftUI for the entire app. No Electron, no web views, fully native. Uses each provider's API to pull usage data and processes everything locally on the user's machine. Zero cloud infrastructure needed which keeps costs at basically zero.
The idea came from my own frustration. I was paying for ChatGPT Plus, Claude Pro, Copilot, Cursor, and making API calls for side projects. Had no idea I was spending $180+/month until I manually added it all up. Built TokenBar to automate that tracking.
Pricing: $5 one-time (Basic) / $10 one-time (Pro). No subscriptions - which feels right for a tool that helps you manage subscription fatigue.
Biggest challenge so far: each AI provider has a different API format for usage/billing data. Normalizing all of that into a clean unified view took way more work than expected. But the result is you just see one number in your menu bar and can drill down by provider, day, week, or month.
Would love feedback from anyone here who uses multiple AI tools daily. What providers would you most want to track?