Urgent.News

What's breaking now, across thousands of outlets.

AI

I Built a Personal AI That Remembers Everything I Type

What if your keyboard remembered everything — every conversation, every mood — and your AI talked back like you? I built exactly that: an Android app with a system-level AI keyboard where everything I type flows to an AI backend, gets stored via RAG, and becomes memory I can ask about any time. The Idea: An AI That Lives in My Phone I am Divyaraj Kush — I have been building apps and doing digital…

I am Divyaraj Kush, a long-time app builder and digital marketer. A recurring idea in my mind was the concept of an AI that stays exclusive to my phone, one that remembers my conversations and knows me intimately. My vision was simple - every time I type through my keyboard, all of my conversations should be directed to my AI backend system. This AI would remember everything I say, store it using Retrieval Augmented Generation (RAG), and become a part of my personal memory.

The AI system would be capable of understanding my queries like "kal maine kisi se kya baat ki thi?" (What conversation did I have yesterday?) or "kal mera mood kaisa tha?" (How was my mood yesterday?). It would listen to my words, process them, and respond to me just like any human conversation. The core design principle was that the AI reads what I type and speaks with me in a manner similar to how I engage with the world.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

NVIDIA's 64GB DGX Spark makes local AI a working-set decision

Illustrative photo by Sven Alleblas on Unsplash , free to use under the Unsplash License. This is not a product photograph.

  • NVIDIA introduces 64GB DGX Spark for local AI development
  • Configuration includes 20-core Arm CPU and 273 GB/s memory bandwidth
  • Memory usage and performance should be measured before purchase

I Built an AI System for 80+ Microservices. Six Months Later, My Whole Team Uses It.

In April I wrote about a system I built on Claude Code that takes an epic to PR-ready code across 80+ microservices. If you read that post, I sounded like someone who had finished something. I hadn't.

  • Author built AI system for 80+ microservices in April.
  • Consolidated rules into single file with short IDs to reduce drift.
  • Implemented read-only agents for safe functionality access.

Cloud Run instances : héberger un agent IA qui tourne en continu

Les agents IA ne se contentent plus de répondre à une question. Certains travaillent en fond: un digest de veille au réveil, le programme de la journée en podcast, les alertes de la nuit déjà triées…

  • Cloud Run instances can host continuously running AI agents
  • Three requirements for permanent agents: continuous operation, information retention, simplicity
  • Cloud Run option offers fixed address, storage, weekly restarts

More from Friday 2 October →