- Home
- Systematic Review Software
- Universal SLR Assistant
Universal SLR Assistant
What it is
Universal SLR Assistant is a free, open-source application for systematic and scoping review workflows. It provides a desktop GUI and a browser-based Web App intended for local use. Researchers can import RIS, BibTeX, CSV, and plain-text references, including exports from PubMed, Scopus, and Web of Science. The workflow supports abstract screening, full-text PDF processing, structured data extraction, and exports in Excel, CSV, JSON, Markdown, and plain text. Likely duplicate references are identified through DOI matching and fuzzy title matching. Workspace mode stores references, PDF metadata, review items, decisions, and audit events in a local SQLite workspace while separating AI suggestions from human decisions. Export packages can include decision files and logs, exclusion reasons, PRISMA-ready counts, a methods disclosure draft, and a manifest. Cloud and local AI providers are supported. Cloud providers receive submitted paper text; Ollama or another local endpoint can keep it on the user’s computer or network. Human verification and final decisions remain necessary.
For and against
For
- Imports RIS, BibTeX, CSV, and plain-text references
- Supports systematic and scoping review workflows
- Flags likely duplicates using DOI and fuzzy titles
- Exports decisions, logs, counts, and methods drafts
- Offers desktop and local browser interfaces
Against
- AI output still requires human verification
- Cloud providers receive submitted paper text
- Cloud AI provider API fees may apply
- Web App is not intended as public multi-user service
The verdict
Universal SLR Assistant covers reference intake through screening, extraction, and reproducible export, with local workspace controls and many AI-provider choices. It is free and open source, but reviewers remain responsible for every final inclusion, exclusion, extraction, and reporting decision.
Who it suits
This software suits PhD students, researchers, professors, evidence-synthesis teams, and authors of systematic or scoping reviews. It fits users who want local workspace storage and configurable cloud or local AI providers.
Plans and prices
Free and open source
MIT License · cloud AI provider API fees may apply
Read 15 Oct 2026 · sadeghanisi.github.io
On the record
- Abstract screening
- AI evaluates titles and abstracts against user criteria and returns Include, Exclude or Maybe recommendations for human review.sadeghanisi.github.io · read 15 Oct 2026
- AI providers
- Provider options include OpenAI, Anthropic Claude, Google Gemini, Ollama, OpenRouter, DeepSeek, Mistral, Kimi, xAI, LM Studio, vLLM, LocalAI, and custom OpenAI-compatible endpoints.github.com · read 30 Sep 2026
- API and extensibility
- The Web App exposes workspace review and export HTTP endpoints, and contributors can add providers through the LLM interface or OpenAI-compatible profiles.github.com · read 15 Oct 2026
- Audit ledger
- Each run can create a JSONL ledger containing provider, model, hashes, cache status, parsing status and retry metadata without storing API keys or full paper text.sadeghanisi.github.io · read 15 Oct 2026
- Caching
- Configuration-aware JSON caching keys results by text, stage, provider, model, prompts and extraction settings.github.com · read 15 Oct 2026
- Cloud data transmission
- When cloud providers are selected, submitted paper text is sent to the provider's API; router providers add another intermediary.sadeghanisi.github.io · read 15 Oct 2026
- Data transmission
- Cloud providers receive submitted paper text, while Ollama or another local endpoint can keep paper text on the user's computer or local network.sadeghanisi.github.io · read 30 Sep 2026
- Deduplication
- Duplicate detection combines DOI matching with fuzzy title matching and leaves final review to the researcher.sadeghanisi.github.io · read 15 Oct 2026
- Developer post: automation
- A mirrored developer post lists automated deduplication and extraction as product capabilities.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Developer post: cost
- A mirrored developer post says the tool has no monthly fees and is free under the MIT license.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Developer post: local integration
- A mirrored developer post highlights local Ollama integration and processing PDFs on the user's own machine.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Developer post: platforms
- A mirrored developer post names Windows, macOS and Linux as supported desktop platforms.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Developer post: privacy
- A mirrored developer post claims local LLM use can keep data from leaving the user's hardware.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Developer post: providers
- A mirrored developer post describes support for more than nine AI providers, including OpenAI, Claude, Gemini and DeepSeek.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Developer profile
- A public profile identifies Mo Anisi as holding a BSc in Biology, an MSc in Cognitive Science and an MSc in Health and Social Welfare.ngntipkolamrenang.twstalker.com · read 15 Oct 2026
- Documentation
- Documentation includes a 1,550-line complete user guide, in-app help, troubleshooting guidance, tests and GitHub issues.github.com · read 15 Oct 2026
- Exports
- Workspace exports include decision CSV/XLSX files, AI and human decision logs, exclusion reasons, PRISMA-ready counts, a methods draft and a manifest.github.com · read 15 Oct 2026
- Hardware guidance
- The user guide lists 4 GB RAM and 2 GB disk as minimums, with 8 GB RAM and 5 GB disk recommended; Ollama guidance lists at least 8 GB RAM and 10 GB disk.github.com · read 15 Oct 2026
