Paper Radar - What 28 AI labs published on arXiv, over any date range

paper-radar finds the AI papers 28 labs put on arXiv, over any date range you pick. Every count splits two ways — papers the lab led, and papers it merely appears on. Method: match against ROR and email domains, using the author block read off each paper's HTML. You need it because arXiv does not carry affiliation. The field has a 1% fill rate; Semantic Scholar reaches 7%; OpenAlex returns zero for preprints. So "what did Google publish in the last two weeks" has no API that answers it.

Hey Product Hunt 👋 We built Paper Radar around a question that sounded simple: “What did the major AI labs publish recently?” It turns out this is surprisingly hard to answer well. arXiv is great for tracking papers by date and category, but author affiliation data is largely missing. That means questions like “what did Google DeepMind publish in the last two weeks?” or “has Xiaomi published anything on self-evolving agents?” don’t have a reliable API answer. So we built Paper Radar to reconstruct that missing layer. It scans recent arXiv papers, extracts affiliations from the author block, resolves them against known institutions, and currently tracks 28 major AI labs. One distinction we cared about a lot is separating: • papers a lab appears on • papers the lab actually led Those can tell very different stories about research activity. Paper Radar is packaged as an agent skill, works with tools like Claude Code and Codex, uses only the Python standard library, and keeps the evidence behind each match so results can be checked. We’ve been using it for questions like: “What did big tech publish in the last two weeks?” “Which companies led the most agent-memory papers this month?” “Has company X published anything on topic Y?” Would love to hear what labs, research areas, or workflows you’d want us to support next. Thanks for checking it out!

Paper Radar - What 28 AI labs published on arXiv, over any date range

Replies