Interactive language map of multilingual open source, built from the GitHub Multilingual Repositories Dataset — non-English README vs issue vs PR asymmetry across 40M+ repositories.

Copilot CLI plugin to verify AI document analysis with screenshots from the actual source material

VS Code extension that allows you to record and play back guided tours of codebases, directly within the editor.

Data Journalist Agent: Transforming Data into Verifiable Multimodal Story

Block cartograms for Python, land area and population, clearly explained

Classify GitHub repos into NAICS codes using semantic search and LLM validation

Crowdsourced tool for locating and reporting ALPRs

The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription

A free, open source, and extensible speech-to-text application that works completely offline.

An open source multi-tool for exploring and publishing data

Human-AI Collaborative Data Science Using Visual Workflows

Design posters showcasing your country's electrical grid

OSS Legal AI Platform

Multi-platform SDK for integrating GitHub Copilot Agent into apps and services

Contributor context cards for new PRs. Helps maintainers review contributions from new contributors.

GPT capability test

Chrome extension that dims low-information filler text. Runs locally.

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

Embedding Vector Oriented Clustering

An official OpenAI toolkit for social scientists and data scientists to measure quantitative attributes in text, images, or audio using the GPT API.

Course materials for ECBS5256: Managing Data Science Teams - a workshop-driven intensive on analytics leadership at Central European University

A concise API for exploratory data visualization implementing a layered grammar of graphics

Perfect Green Screen Keys

Fast, accurate and scalable probabilistic data linkage with support for multiple SQL backends

Measuring the software complexity of nations

skimpy is a light weight tool that provides summary statistics about variables in data frames within the console.

Difference-in-Differences causal inference in Python. Callaway-Sant'Anna, Synthetic DiD, Honest DiD, event studies. sklearn-like API, validated against R.

Tools for coding, teaching, and presentations with AI assistance

Chess via DM. Pure ASCII, no third-party app connections.