LitFlow vs Scholarcy

LitFlow is an AI-augmented workspace for systematic literature reviews, covering search, screening, extraction, synthesis, and reporting. Search includes database queries, snowballing, and AI-generated synonyms. For each record, AI proposes per-criterion verdicts with confidence scores, explanations, and links to source passages, while researchers make the decisions. Custom extraction schemas can receive LLM pre-fill with source links, and a qualitative coding board supports thematic structure. Reports include PRISMA information, Cohen’s κ, and an audit trail in a publication-ready methods report. AI suggestions and human decisions are logged with timestamps, actors, and rationales. Users can bring keys for Gemini, Claude, OpenAI, or Mistral, or use open-source models hosted by the University of Münster. The closed alpha runs on University of Münster infrastructure in the EU under GDPR, with pseudonymised personal data in research outputs. Operated by the university’s LitFlow research project in Münster, it is free for academic use, requires maintainer approval, and has no commercial tier listed.

Scholarcy turns research material into interactive summary flashcards that highlight key information and provide context. It accepts research papers, PDFs, book chapters, online articles, plain text and YouTube videos. Users can add content by uploading or dropping files, entering a webpage URL, pasting text or using a browser extension. Enhanced summaries can be tailored to reading styles such as School level, General reader, Bulleted list, Undergrad level, One liner and Researcher. Research tools include cited-work findings, article prompts and questions, a Research Quality Indicator and comparisons with related research. Scholarcy imports directly from Zotero and exports referenced summaries to Markdown for tools including Roam, Obsidian and Notion. Extensions are offered for Chrome, Edge and Firefox; Safari is listed as coming soon. The free plan costs nothing and allows 10 summaries, with flashcards exported one at a time. Scanned PDFs without extractable text are unsupported unless OCR is run first, and URLs behind paywalls may not import. Scholarcy says customer data is encrypted at rest and in transit.