Ghosts in node_modules: I trained an open model to predict which packages will be abandoned
DepForecast: A Weather Forecast for the Ghosts in Your node_modules (work in progress) This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine What I Built Abandoned dependencies are ghosts in the machine: code whose maintainers are gone but which still runs in production. Developers usually find out only after something breaks or a vulnerability goes…
DepForecast is a local, open-source CLI tool designed to predict which npm dependencies in a project are likely to become abandoned within the next 12 months. It provides a weather forecast for dependencies, alerting developers when "current" is about to stop existing. The tool uses the TabPFN-3.5 model, a tabular foundation model, trained on a dataset of 250 popular JS/TS repositories, 5,118 distinct dependencies, and 3,719 GitHub repositories.
The model outputs a risk score and an explanation of why a dependency may become abandoned. DepForecast categorizes dependencies into three states: RESTING for dead packages, HAUNTING for at-risk ones, and ALIVE for healthy ones. The tool also offers resources to help maintainers revive abandoned packages, such as funding links, "help wanted" issues, and contributing guides.
The project is currently in progress, with the data foundation and core components built using open-source AI models and free APIs.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
