Universal SLR Assistant

Universal SLR Assistant is a free tool for researchers carrying out systematic or scoping reviews. Its best fit is an author or evidence synthesis team that wants screening, extraction and reporting in one workflow, with a local workspace and a choice of AI providers. It offers a substantial review trail, but AI output must be checked and final decisions remain human responsibilities.

Overview

The workflow spans reference import, abstract screening, full-text PDF processing, structured extraction and export. It accepts RIS, BibTeX, CSV and plain-text files, including exports from PubMed, Scopus and Web of Science. DOI and fuzzy-title matching flag likely duplicates, helping reduce clutter before screening; those matches should not be treated as confirmed duplicates without review.

Workspace mode stores references, PDF metadata, review items, decisions and audit events in a local SQLite workspace. Crucially, it distinguishes AI suggestions from human decisions. Exports include decision CSV and XLSX files, separate AI and human decision logs, full-text exclusion reasons, PRISMA-ready counts, a methods disclosure draft and a manifest. That combination is useful for researchers who need a traceable process and organized outputs, rather than just a tool for finding papers.

Key features

Broad AI provider choice, with a privacy trade-off

Provider options include OpenAI, Anthropic Claude, Google Gemini, Ollama, OpenRouter, DeepSeek, Mistral, Kimi, xAI, LM Studio, vLLM, LocalAI and custom OpenAI-compatible endpoints. This range accommodates both cloud services and local setups. Cloud providers receive submitted paper text; Ollama or another local endpoint can keep it on the user's computer or local network. The choice therefore has practical privacy consequences, and users should select a provider with their data-handling needs in mind.

Local workspace and safeguards

The browser-based Web App binds to 127.0.0.1 for local use; it is not intended to serve as a public multi-user service. API keys are not written to the desktop or Web App settings files, and audit ledgers do not store keys or full paper text. These are useful boundaries, but they do not remove the need to consider what is sent to a cloud provider. AI is assistance only: people must verify outputs and make the final inclusion, exclusion, extraction and reporting decisions.

Support routes include the Complete User Guide, in-app Help panel, output logs, tests and GitHub issues.

Pricing

Universal SLR Assistant is free and open source under the MIT License: free. There is no paid plan described. Cloud AI provider API fees may apply, so the software's free price does not necessarily make every workflow cost-free. Its free plan includes screening, AI paper summaries, full-text analysis, systematic review support, reference deduplication, data extraction and full-text storage. Exports include Excel (.xlsx), CSV, JSON, Markdown and plain text.

Platforms

It supports Linux, macOS, Windows and web, with a desktop GUI as well as a browser-based local Web App. The Web App's localhost binding makes it suitable for individual local use, not a public shared service.

Who it's for

PhD students, researchers, professors, evidence synthesis teams and authors of systematic or scoping reviews are the intended audience. It is particularly well suited to people who want a structured path from references to documented decisions and exports, and who can review AI assistance rather than delegate final judgments to it. It is a weaker fit for teams seeking a public multi-user Web App or anyone who expects automated decisions to stand without human verification.

Pros and cons

Pros

• Review workflow covers multiple stages: import, screening, full-text processing, extraction and export live in one tool.
• Useful audit and reporting outputs: separate decision logs, exclusion reasons, PRISMA-ready counts and a methods disclosure draft support traceability.
• Local and cloud AI options: users can choose a local endpoint to keep paper text on their computer or local network, or select among numerous providers.
• Free and open source: the MIT-licensed plan has no software price, though cloud API charges may apply.

Cons

• Human review remains essential: AI suggestions do not replace verification or final review decisions.
• Cloud use sends submitted paper text to providers: users concerned about transmission must choose a local endpoint or otherwise account for that exposure.
• The Web App is not a public team service: its localhost-only design limits its role in shared deployments.

Alternatives

Systematic Review Software and AI Literature Review Software are directories for comparing options by category.

Choose ReviewAid if you want another free, open-source option available on Linux, macOS, Windows, web and self-hosted platforms; its listed plan is free under Apache 2.0.

ASReview is another free, open-source option, with Linux, macOS, web, API and self-hosted platforms. Its ASReview LAB plan is free, though running your own hardware or server may cost money.

RevMan is worth considering if you prefer a freemium product with a free plan and a free trial.

Pick Bango if you want a free researcher-focused option whose plan is described as having no subscription, paywall or limits.

Rayyan offers a free plan with limits of three active reviews, two free reviewers, one sample and limited mobile app access; its Android, iOS and web support may suit readers seeking mobile access.

Catchii is a web-based free option described as supporting multiple users without subscriptions, paid upgrades or advertisements.

Covexe is a web-based freemium alternative whose free plan includes an AI co-pilot with 100 messages per day.

HAWC is a free web option for exploring public assessments; creating assessments requires requesting an account.

Verdict

Universal SLR Assistant is a strong choice for review authors who want a free, end-to-end systematic or scoping workflow with local workspace storage and detailed decision and reporting exports. Its central advantage is the combination of structured review records and flexible AI-provider choice. Look elsewhere if you need a public multi-user Web App, and keep human verification central—especially when submitting paper text to a cloud provider.