Parsifal vs Universal SLR Assistant

Parsifal is a web tool for planning, conducting and reporting systematic literature reviews. Its planning process covers objectives, PICOC, research questions, keywords, search strings, selection criteria, quality questions and data extraction forms. Researchers can import BibTeX records from Scopus, Web of Science, IEEE, ACM and PubMed, or use API imports. The platform supports article screening against inclusion and exclusion criteria, duplicate detection, quality assessment and snowballing through references and citations. Review owners can invite co-authors to edit protocols, screen articles and generate content, or share a public read-only link. Parsifal can create PRISMA diagrams and export review data to Excel or CSV, with papers in Word, LaTeX or PDF. It lists more than 45 community templates across 12 domains and 6 languages, and connections to services including ASReview, OpenAlex and Semantic Scholar. Its optional AI assistant can help with screening, assessment, extraction and paper sections, but requires the user's Anthropic or OpenAI API key; AI usage is billed directly by the AI provider. Imported articles, screening decisions and extraction data are stored in the user's account database.

Universal SLR Assistant supports systematic and scoping reviews with AI-assisted screening, extraction, and reproducible outputs. It provides a desktop interface and a browser-based local Web App, and imports RIS, BibTeX, CSV, and plain-text references, including exports from PubMed, Scopus, and Web of Science. Its workflow covers abstract screening, full-text PDF processing, structured extraction, and export; likely duplicates are identified by DOI and fuzzy title matching. Workspace mode stores references, PDF metadata, review items, decisions, and audit events in a local SQLite workspace, separating AI suggestions from human decisions. Exports can include decision files and logs, exclusion reasons, PRISMA-ready counts, a methods disclosure draft, and a manifest. The project supports a range of cloud and local AI providers. Cloud providers receive submitted paper text, while Ollama or another local endpoint can keep it on the user's computer or local network. AI results are assistance only: people must verify them and make final review and reporting decisions. The software is free under the MIT License; cloud AI provider API fees may apply.