Bio

I'm a full-stack software engineer dedicated to human-centered artificial intelligence, specializing in AI-driven interface development. My passion lies in crafting interactive experiences enhanced by intelligent systems.

Currently, I work at Stellar Cyber, developing AI-driven interfaces for threat hunting [AIM Research, 2024] and human-augmented autonomous cybersecurity operations powered by agentic AI [Business Wire, 2025]. Additionally, I'm the creator of GONEXT, a generative AI tool providing personalized, game-specific analytics for League of Legends players.

Outside of work, I am either at music festivals, backpacking, or working out. My favorite artist is Subtronics, and my favorite country I've visited is Peru.

Current Work

GONEXT.lol   Website   GitHub

GenAI Agentic AI RAG

An AI-powered analytics tool for League of Legends that provides real-time, personalized strategies, matchups, synergies, and builds. It uses the Riot API to gather live game data, which is then processed by language models to deliver tailored, game-specific guidance to players.

Screenshot of GONEXT.lol

This open-source Model Context Protocol (MCP) server empowers LLMs with comprehensive access to League of Legends game data through the Riot Games API. It features over 35 tools and resources for retrieving player statistics, match history, champion information, tournament data, and real-time game monitoring, supporting both stdio and SSE transports for seamless client integration. It is shipped as a Python package and a Docker container. Additionally, a demonstrative MCP client chatbot, leveraging a ReACT agent, is also provided to showcase the server's extensive capabilities and practical usefulness.

docker pull kostadindev/league-mcp pip install league-mcp

League MCP Server Demo

Python package for converting diverse content into a search-engine-friendly knowledge base. It effortlessly ingests files (PDFs, DOCXs, spreadsheets), websites, and GitHub repositories, then leverages LLMs to generate a Markdown knowledge base. Ideal for creating structured and crawlable formats like llms.txt and llms-full.txt, supporting Retrieval-Augmented Generation (RAG) applications, or synthesizing unstructured data from multiple sources. Capable of summarizing an entire github repostory or website in two lines of code.

pip install knowledge-base-builder

Knowledge Base Builder Merge Tree Algorithm
See completed projects