Hi Product Hunt! When building a small AI demo, working with APIs usually feels simple. You pick a model, send a request, test the response, and move on. But once the project grows, the workflow becomes more complicated. The hard part is often not the model itself, but everything around it: - Where do you compare available models?
- How do you track usage across projects?
- Where do developers find integration docs?
- How do teams keep API access organized?
- How do you avoid switching between too many dashboards? This is the operational layer of AI development, and it is easy to underestimate. We built ChinaRouter to make this layer easier to manage. ChinaRouter is a unified AI API gateway and admin dashboard for model access, usage lookup, documentation, and dashboard workflows. Website: https://chinarouter.net/ For people building AI products: what part of AI API management becomes painful first?
Hi Product Hunt! AI API usage often starts as an individual developer workflow. One person tests a model, writes the integration, and ships a feature. But once a team starts building more AI-powered features, API management becomes a shared problem. Teams need visibility into: - Which models are being used
- Where documentation lives
- How usage is tracked
- How API access is managed
- How different workflows connect Without a clear system, the workflow becomes scattered and hard to maintain. ChinaRouter is built around this problem. It provides a unified AI API gateway and admin dashboard for developers, AI builders, and teams. Website: https://chinarouter.net/ Curious to hear from teams building AI products: how do you currently manage model access and usage?
I m building TransferIQ, a tool that compares traditional remittance providers, banks, crypto exchanges, P2P routes, and stablecoin-based transfers using the final amount received not just the advertised fee.
The core comparison tool works, but I ran into a product problem:
International transfers are low-frequency.
Even if users find the comparison useful, they may not have a reason to return until their next transfer.
I m building Crazy Sajangnim, an early-stage platform that combines discounted fashion discovery with a shared community blog.
The name comes from the Korean phrase , which roughly means The boss has gone crazy. Korean retailers often use it playfully to advertise prices so low that the owner must be crazy. I wanted the name to preserve that part of Korean shopping culture while building something that connects Korean and U.S. fashion retailers.
However, the question I m most interested in testing isn t simply whether people want another place to find discounted products. It s whether a blog can recreate some of the social experience of shopping together.
The idea is to let shoppers post clothing photos, share deals, ask for sizing or styling advice, compare products, and get opinions before purchasing. Rather than evaluating everything alone across multiple tabs, shoppers could bring their discoveries and questions into one shared feed.
Over the past few weeks, I built a reproducible benchmark to explore a practical question:
Can a local language model correct writing effectively while also explaining the user s mistakes?
This work is part of LinguaPilot AI, a Windows writing coach designed to improve the user s own draft and explain the corrections, rather than automatically writing everything on their behalf.
Hi all, I'm Jon, and I built Ifarlo. It's launching on Product Hunt next month, so I thought I'd introduce it early.
My background is product management for sales and marketing platforms. I've spent 16 years working in and around enterprise CRM, and have experienced first hand how much time and money is spent on development, configuration, and change management to make one actually fit a business.
I wanted to come at it from the other direction. A CRM that's as easy to pick up and use as your phone, and provides you the information you need without having to search for it or struggle with reports.
Just launched AnShare today - mobile build distribution without TestFlight or Google Play Console.
The problem we're solving: every time a mobile team needs to share a build with a client or tester, they hit a wall - TestFlight review delays, Play Console setup, managing tester lists, clients who can't figure out how to install.
Hi Product Hunt Community! Do you often miss out on precious moments in your busy life, or wish you could better record your feelings and daily stories?
MovingDay is your countdown buddy, helping you cherish each moment and look forward to birthday, anniversary, or special event D-Day together. No more missed celebrations! Record your daily moods and moments, and exchange diaries with your loved one turning ordinary days into beautiful shared memories.
MovingDay was created by a two-person Hong Kong team a programmer and an animation/UI designer. This is our first app published on the App Store , and we would be thrilled if you take a look!
At Jinny Labs, we believe great ideas should never be hidden by a lack of writing skills. We are on a mission to help marketing agencies, creators, and business owners focus on their original ideas rather than repetitive drafting.
