Random Projects

As a developer I run into problems every day. Whenever possible, I try to publish my solutions as open source software so others can benefit and build upon them.

Some projects are NPM packages or CLI applications, others are full blown web applications or SaaS products and others are shell scripts to automate tedious "borings" tasks.

These are projects that i have a big hand in the creation of or i built myself. click the project titles / names to view the repo

Talana

is an AI-powered information kiosk built entirely from scratch, designed to let students access campus-related information through a React-based kiosk interface.

It features voice and text input, runs on low-resource machines, and handles over 1,000 multi-context queries per day.

The kiosk queries a Supabase-hosted database with embedded knowledge entries managed through a separate Svelte-based CMS.

When a query is made, the system performs a semantic search using pgvector to find the most relevant information, then injects that data—alongside recent chat history—into a high-parameter AI model hosted serverlessly via Groq for response generation.

Embeddings are computed locally using Xenova to reduce cloud overhead, while voice input is transcribed into text before processing. The entire retrieval and response logic was written from scratch, with no external AI orchestration tools used.

Every part of the system—from UI to AI pipeline—was built and integrated manually, with a strong focus on performance, clarity, and deployment constraints.

Nerd-Necking

is an AI-powered information kiosk built entirely from scratch, designed to let students access campus-related information through a React-based kiosk interface.

It features voice and text input, runs on low-resource machines, and handles over 1,000 multi-context queries per day.

The kiosk queries a Supabase-hosted database with embedded knowledge entries managed through a separate Svelte-based CMS.

When a query is made, the system performs a semantic search using pgvector to find the most relevant information, then injects that data—alongside recent chat history—into a high-parameter AI model hosted serverlessly via Groq for response generation.

Embeddings are computed locally using Xenova to reduce cloud overhead, while voice input is transcribed into text before processing. The entire retrieval and response logic was written from scratch, with no external AI orchestration tools used.

Every part of the system—from UI to AI pipeline—was built and integrated manually, with a strong focus on performance, clarity, and deployment constraints.

Todo-app

is an AI-powered information kiosk built entirely from scratch, designed to let students access campus-related information through a React-based kiosk interface.

It features voice and text input, runs on low-resource machines, and handles over 1,000 multi-context queries per day.

The kiosk queries a Supabase-hosted database with embedded knowledge entries managed through a separate Svelte-based CMS.

When a query is made, the system performs a semantic search using pgvector to find the most relevant information, then injects that data—alongside recent chat history—into a high-parameter AI model hosted serverlessly via Groq for response generation.

Embeddings are computed locally using Xenova to reduce cloud overhead, while voice input is transcribed into text before processing. The entire retrieval and response logic was written from scratch, with no external AI orchestration tools used.

Every part of the system—from UI to AI pipeline—was built and integrated manually, with a strong focus on performance, clarity, and deployment constraints.