Stories by Applied-AI-Dev

From 300KB to 69KB per Token: How LLM Architectures Solve the KV Cache Problem

Some uncomfortable truths about AI coding agents

A 100% serverless RAG that extracts complex tables better than NotebookLM

We've had front end reactivity since 2018 – via Async Iterables

Show HN: Etnamute – local AI mobile developer that runs on Claude Code

Show HN: AfterTheCall – AI summaries and action items for client calls

Show HN: Unwind – I built a security proxy for AI agents on a Raspberry Pi

RegalMail – give your AI agents a real email inbox

Idea Killshot: stress-test your startup idea before the market does

Show HN: Parsing hostile industrial data in 64MB WASM sandboxes

Show HN: Mengram – Open-source memory layer for AI agents

Show HN: Autonomous Prover Running > 1hr

GrantAi – Deterministic memory for AI agents (exact recall, 90% fewer tokens)

Claude AI Gets Weirdly Slow After 9 PM (I Noticed It While Reviewing Code)

Base25 – Feedback, roadmap, and changelog in one place

Show HN: Aurion OS – A 32-bit GUI operating system written from scratch in C

Ask HN: Should training bottleneck detection be a product or just a feature?

Extra Timezones on You Mac Menubar

Show HN: Aacyn v0.7.0 – A bare-metal observability engine (5M events/SEC)

I made a tool that scores your startup, app or business "objectively"

1 2 3 4 5 6 7 8 9 10