Hi, I am Aayush Shrestha

I'm a problem solver at heart, and software just happens to be my favorite tool for the job at the moment. This is my space where I share what I'm building and whatever I pick up along the way. When I'm not tinkering with code, you'll find me out hiking, taking photographs, or lost in a good sci-fi or thriller. Looking for a recommendation? Anything by Blake Crouch (Dark Matter, Recursion, Upgrade) or Dan Brown, and if you're feeling adventurous, Matt Dinniman’s Dungeon Crawler Carl :)

Recent Blogs

Review Rambling

Omarchy Quattro

Aug 19, 2026 / Review, Rambling

A tiling shell, a unified look across every tool, and a floating bongo cat that bongs when I type.

Build

Calmly, part two: I broke both of my own rules

Aug 10, 2026 / Build

A follow-up on Calmly, my local news reader. I finished the list from last time, replaced Gemini with LiteLLM, added multilingual dedup with vector embeddings and a tool-calling chat agent, then deleted the two rules I'd have defended hardest: no background polling, no notifications.

Rambling Review

My Obsidian second brain (and the AI that's going to power it)

Jul 3, 2026 / Rambling, Review

A month into using Obsidian daily as a second brain, daily notes, a predefined tag system, Kanban, finances and todos all linked together, plus why paper, Notion and Logseq didn't stick, and my plan to build an AI assistant that reads it all back to me.

Build

Calmly: a quiet, self-tuned news reader

Jun 25, 2026 / Build

I built Calmly, a local Python tool that tracks the news sites I trust, detects new posts by diffing homepages, and uses Gemini to filter by topic and rewrite everything into simple English, so I can keep up without feeling dismay.

See all blogs

Career

July 2025 - Present : Data Engineer at Ankamala Research Pvt. Ltd.

I build web data extraction pipelines and OSINT tools that turn messy, unstructured web data into useful insights. My work covers the whole flow: ingesting raw web data, extracting the important bits (NER, heuristic/rule-based parsing, and LLM-driven methods), and storing it in a clean, structured form (relational tables, JSON, graph databases, and RDF triples). Right now I'm working on Entity Resolution and Linkage: figuring out when two records from completely unrelated sources point to the same real-world thing, and modeling the results in an RDF data store.

See My Resume

Education

2022-2026 : Bsc CSIT (Computer Science and Information Technology)

St. Xavier's College, Kathmandu, Nepal.

2025 : Fathers Locke and Stiller Research Awards(LSRA)

Completed my research thesis on 'Using Machine Learning to Predict Crop Yield in Nepal', from data collection to model training and deployment, under a supervisor

2024 : Presenter in ICSXC 2024

Presented my abstract on Machine Learning in Agriculture at the International Conference held in St. Xavier's College.

Recent projects

Build

Sabda, A Nepali vocabulary Building Mobile App

Jun 7, 2024 / Build

Sabda is a mobile app for learning Nepali vocabulary using structured lessons, quizzes, and spaced repetition. Built with Flutter and Firebase, it offers a modern UI, offline support, and secure data handling.

Build

Relevancite: your personal research validating AI assistant

Nov 28, 2025 / Build

RelevanCite is an offline, privacy-preserving AI assistant that automates citation validation for research using NLP, NLI, and modular architecture. All processing is local, ensuring data security and reproducibility.

Build

OMR

May 4, 2025 / Build

A Python-based project that automates the evaluation of OMR answer sheets using OpenCV for image processing and Tesseract for OCR, exporting results in CSV format.

Build

PAYO – An Offline Customer Initiated One-Time-QR code based Payment System

May 4, 2025 / Build

PAYO is a secure, offline-first digital payment solution using one-time QR codes, built with React Native, TypeScript, ExpressJS, and MongoDB. It enables real-time payments with minimal connectivity and robust security features.

See all projects