I’ve been building software and contributing to open source since the early days of Linux. Here are some projects I’ve built, contributed to, and experimented with over the years.

github · PRs contributed · Issues contributed

⭐️ Current Projects

LLM Evals and Tools

Practical LLM Evals⭐️ Practical LLM Evals

Model visualizers, developer utilities for testing inference, and more.

Repo ↗

ZebraBench⭐️ ZebraBench

Benchmark LLM inference endpoints right in your browser: speed, latency, accuracy, and cost.

Repo ↗

FUN LLM Evals / Games

Doodle Derby⭐️ Doodle Derby

You draw, and AI vision models race to guess what it is.

Repo ↗

LLM Derby⭐️ LLM Derby

A carnival-style horse race where LLMs answer trivia questions. First to the finish line wins.

Repo ↗

LLM Snake Arena⭐️ LLM Snake Arena

LLMs compete in the classic Snake game

Repo ↗

Visualizations / Explainers / Slide Decks

Visual Stories⭐️ Visual Stories

Use AI to create engaging animations and stories. Direct your agent by chatting, and reproduce, remix, and share the open-source results.

Repo ↗

Experiments & Utilities

CFP Tracker⭐️ CFP Tracker

Collect conference CFPs from public sources in Obsidian. Sort by deadline, filter by topic, and track submissions.

Repo ↗

Built / Maintained

Allycat⭐️ Allycat

End-to-end open-source RAG pipeline for website content.

Repo ↗

Data Prep Kit Examples⭐️ Data Prep Kit Examples

Companion examples repo for Data Prep Kit

Repo ↗

WorkshopsWorkshops

Hands-on workshops on LLMs, coding agents, open models and AI.

Repo ↗

⭐️ Token Factory Cookbook

Examples and tutorials for Nebius Token Factory

Repo ↗

Data Prep Kit⭐️ Data Prep Kit

Open-source tools to cleanse, transform and enrich unstructured data at scale for LLM / RAG workloads.

Repo ↗

Open Source Project Contributions

Spark Job Server

Submitted multiple patches and pull requests to Spark Job Server.

HBase

Contributed performance and documentation patches to Apache HBase, a distributed NoSQL database, including HBASE-4440 and HBASE-5555.


Earlier Open Source Projects

Dockerized Data & AI StacksDockerized Data & AI Stacks

Ready-to-run Docker environments for Kafka, Spark, machine learning, and deep learning.