Writing
Notes on LLMs, side projects, and making technology more accessible.
Building an AI agent business from scratch
What I'm building with Hyperflash, why selling AI agent setups to small businesses is harder than building them, and what I've learned so far.
Contact
Get in touch with me for collaboration, questions, or to say hello.
Self-hosted SMS gateway with an old Android phone
How I built a self-hosted SMS gateway using a spare Android phone, a custom FastAPI relay, and Tailscale for secure, zero-cost text messaging from my AI agent.
EduForge: AI-Powered Educational Resource Generation
An open-source pipeline that generates K-12 educational materials using LLMs and global curriculum standards.
Building an offline Quran verse recogniser from scratch
How I'm building a system that listens to Quran recitation and identifies the exact verse, fully offline, using a Whisper encoder, CTC, and finite state transducers.
Fixing Quran Audio Segment Timings with WhisperX
How I used WhisperX forced alignment to fix inconsistent word timings in a Quran reading app.
QuranZen: A Hybrid Architecture Quran App
Building a full-stack Quran exploration app with React 19, FastAPI, and a hybrid database design.
Building a VPS Metrics Dashboard
A lightweight, self-hosted VPS monitoring solution with Python, Docker, and a web dashboard.
Running LLMs on a Steam Deck in 5 minutes
A step-by-step guide to setting up your Steam Deck to run local Large Language Models (LLMs) using llama.cpp and a Distrobox container.
Fine-tuning a 3B Model for Transcript Analysis: Better Than 70B Models?
How I fine-tuned Llama 3.2 3B to process transcripts locally, achieving better results than models 5-8x larger through specialized training.
ToddlerTones: offline, toddler-proof soundboard
Designing and building a distraction-free Android app in Kotlin/Compose with low-latency audio and a gentle 'Find it' game.
Democratizing Education: An AI Tutor for Every Child
A plan to build a small local offline AI tutor for children in underserved communities.
Reluctant Buddha: Fine-Tuned LLM for shitty insights
Turning a 1B LLM into a deranged cosmic entity running on CPU only.
Projects
A collection of side projects, tools, and experiments I've built across AI, web, infrastructure, and beyond.
About
Platform Operations Engineer, AI tinkerer, and builder of things that occasionally work.