PaperPulse uses LangGraph multi-agent AI to audit papers for reproducibility

PaperPulse is a browser-integrated multi-agent system built on a LangGraph orchestrator that audits scientific papers, news articles and web content for methodological rigor, statistical validity and code-to-paper alignment. Four specialized agents handle extraction, GitHub code grounding, statistical critique and citation-grounded synthesis, producing a structured JSON report rendered as Markdown in a Chrome extension.