Universal SLR Assistant

Overview

The workflow runs from importing references to abstract screening, processing full-text PDFs, structured data extraction, and exporting results. It accepts RIS, BibTeX, CSV, and plain-text references, including exports from PubMed, Scopus, and Web of Science. DOI and fuzzy-title matching help surface likely duplicates, a useful safeguard before screening—but duplicate matches still need appropriate review.

Workspace mode keeps references, PDF metadata, review items, decisions, and audit events in a local SQLite workspace. Separating AI suggestions from human decisions supports accountable review rather than treating model output as a verdict. Exports include decision files, separate AI and human decision logs, full-text exclusion reasons, PRISMA-ready counts, a methods disclosure draft, and a manifest. That breadth makes the tool more compelling for reproducible work than for casual paper discovery.

Key features

AI assistance with a human checkpoint

Users can choose among providers including OpenAI, Anthropic Claude, Google Gemini, Ollama, OpenRouter, DeepSeek, Mistral, Kimi, xAI, LM Studio, vLLM, LocalAI, and custom OpenAI-compatible endpoints. The range gives teams flexibility to use cloud services or a local endpoint, but provider choice does not remove the need to verify summaries, screening suggestions, and extracted data. Final inclusion, exclusion, extraction, and reporting decisions remain human responsibilities.

Local workspace and privacy choices

The browser-based Web App binds to 127.0.0.1 and is intended for local use, not as a public multi-user service. Cloud providers receive submitted paper text; Ollama or another local endpoint can keep that text on the user's computer or local network. API keys are not written to the desktop or Web App settings files, and audit ledgers omit keys and full paper text. Readers handling sensitive material should choose a provider with the transmission model in mind.

Pricing

Free and open source — 0.00 USD per free under the MIT License. The plan includes screening, AI paper summaries, full-text analysis and storage, systematic review support, data extraction, reference deduplication, and exports in Excel (.xlsx), CSV, JSON, Markdown, and plain text. There is no paid tier described; cloud AI provider API fees may still apply, so free software does not necessarily mean free AI use.

Platforms

Universal SLR Assistant supports Linux, macOS, and Windows, with both a desktop GUI and a browser-based local Web App. The local-only Web App model is suited to an individual or locally managed workflow, not teams seeking a remotely hosted shared workspace.

Who it's for

PhD students, researchers, professors, evidence synthesis teams, and authors of systematic or scoping reviews are the natural audience. It is especially suitable for people who need an auditable sequence of human decisions and structured outputs, and who can manage their own provider choice and paper-text handling. Those seeking automated final judgments or public multi-user access should look elsewhere.

Pros and cons

• Pros: Broad reference imports and duplicate detection reduce friction when assembling a review library.
• Pros: Local SQLite storage, decision separation, audit events, and detailed exports support reproducibility.
• Pros: Cloud and local AI endpoint options let users choose a paper-text transmission approach.
• Cons: AI output requires human verification, so it cannot replace reviewer judgment or final reporting responsibility.
• Cons: Cloud providers receive submitted paper text, making provider choice a substantive privacy decision.
• Cons: The local Web App is not designed as a public multi-user service, limiting its fit for distributed collaboration.
• Cons: Cloud API fees may apply despite the software's free license.

Alternatives

For a wider comparison, see AI Literature Review Software and Systematic Review Software.

• ASReview is another free, open-source option with Linux, macOS, Windows, web, API, and self-hosted availability; running your own hardware or server may cost extra.
• Rayyan may suit mobile users who want Android or iOS access; its free plan caps use at 3 active reviews and 2 free reviewers, with limited mobile app access.
• Elicit is a web-based alternative for paper search and summaries, including search across more than 138 million papers and unlimited summaries on Basic, with limited Research Agent and Research Reports usage.
• Axelium offers a free plan with one lifetime review and one seat, which may suit a one-off individual project.
• EPPI-Reviewer is a web-based alternative with a free trial.
• INRA is a web-based option with a Teams & Institutions plan at 7.50 USD per year; the stated terms specify $7.50 per seat per month billed yearly and a three-seat minimum.
• Mapped Research may suit users who want a free web plan capped at 1,000 screening citations, 200 AI-assisted screenings, and 3 collaborators.
• Moara offers a free web plan for libraries of up to 50 papers, with Google Scholar and Semantic Scholar search and viewer or editor collaboration.

Verdict

Choose Universal SLR Assistant if you want a free, open-source review workflow that keeps its working data local and produces decision-focused exports. Its combination of traceability, broad import support, and provider flexibility is the main reason to choose it. Look elsewhere if your priority is a hosted team workspace, or if you need AI to stand in for human screening and verification.