Paper Tracker
A minimal keyword-based tool that queries arXiv, OpenAlex and PubMed for new academic papers, deduplicates results across sources, and can translate and summarize them with a language model.
Paper Tracker queries multiple academic paper databases, arXiv, OpenAlex and PubMed, by keyword across fields such as title, abstract, author, journal and category, combining terms with AND, OR and NOT logic and an optional filter that applies to every query. Results from different sources are aggregated and deduplicated against each other and stored in a local SQLite database so a paper is not reported twice across runs, and it can also backfill older papers to reach a configured target count.
Output can be generated as JSON, Markdown or HTML using a replaceable template, and an optional integration with an OpenAI-compatible endpoint can translate and summarize a paper's abstract into a configured target language. It runs from the command line against a YAML configuration file, and notes that its OpenAlex source is still unstable and may return results unrelated to the search topic.