Today we're open-sourcing the AI Model Directory, the most comprehensive, automatically updated list of AI models and their metadata available today. It's the data layer that powers model selection in AgentOne, and now it's free for anyone to use, fork, or contribute to. If you'd rather just look at models, we also built a browser for the directory at models.agent-one.dev where you can search, sor
A College Project That Planted a Seed Years ago I was on a university team trying to build a Go AI. We explored monte carlo simulation for lookahead search, basic neural networks for pattern recognition, and expert systems for encoding domain knowledge. None of them worked well enough on their own. Go's branching factor is enormous, so brute-force search fails quickly. Neural networks without th
If you’ve been building with AI recently, you’ve probably seen these terms everywhere: AI Gateway. And depending on where you read, they either sound like the same thing… or completely different systems. Some vendors use them interchangeably. Others define only one and ignore the rest. And if you try to piece it together yourself, you end up with a vague understanding that doesn’t really help when
Introduction Building a mobile application that handles sensitive financial data — crypto transactions, KYC verification, gift cards — means security is not an afterthought. It is a core deliverable. During the development of a cross-platform fintech application, one of the non-negotiables on the security checklist was runtime application self-protection (RASP). After evaluating our options, we
React Native's New Architecture — JSI, Fabric, and TurboModules — has been "coming soon" for long enough that some teams wrote it off as vaporware. It shipped. It is now default in new React Native projects. And it meaningfully changes how the framework works at the performance-critical boundaries between JavaScript and native code. This post is not a getting-started guide. It is an honest account
Originally published on rohitraj.tech UPI fraud hit ₹805 cr in India last year. Cloud APIs leak data. So I built ScamRakshak — fully on-device scam detection. 3-tier inference engine: Gemma 4 LLM — context-aware classification LiteRT — fast pattern model Regex fallback — when battery low Full architecture write-up: https://rohitraj.tech/en/notes/build-on-device-ai-scam-detector-android-gemma Read
It's a one-line item on the roadmap. "Send a push notification when X happens." Estimate is two days, three if the backend doesn't have FCM credentials yet. There's a library for it. The library is the visible part. The other 90% is platform lifecycle, registration state machines, race conditions with navigation, payload archaeology, and a half-dozen iOS and Android quirks. Nobody writes them down
I have been building web apps for 12 years. In that time I never wrote a single line of mobile code. Not Swift, not Kotlin, not even a basic React Native hello world. That changed last month because of my wife. She has been using Synapse, the AI companion I built for her, every day from her phone browser. If you are new here, Synapse is a personal AI that uses a temporal knowledge graph instead of