Tiny Tools for Big Impact: Local and Lightweight LLMs for Journalists
Nick Hagar , Mandi Cai , Jeremy Gilbert
SRCCON (Conference on Community and Collaboration), 2025
Unofficial wrapper for Substack APIs to fetch newsletters, posts, and more.
Data collection code for 50+ LLM training datasets.
CLI for collecting website data from the Internet Archive, GDELT, and more.
Open source contributions and experiments in data science, web scraping, and journalism tools
Cross-provider LLM memory management tool.
An early attempt to automatically generate schema for structured outputs with LLMs.