Covexe vs Universal SLR Assistant
Covexe
covexe.comUniversal SLR Assistant
sadeghanisi.github.ioSide by side
| Figure | Covexe | Universal SLR Assistant |
|---|---|---|
| Price from | $8.25/mo | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | Yes |
| Web | Yes | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| API | — | Yes |
| Self-hosted | — | Yes |
| Plans published | 4 | 1 |
| Spec score · Systematic Review Software | 8.1 (#7) | 8.2 (#6) |
| AI providers | Users can connect their own API key for OpenAI, Anthropic, or Google AI features. | Provider options include OpenAI, Anthropic Claude, Google Gemini, Ollama, OpenRouter, DeepSeek, Mistral, Kimi, xAI, LM Studio, vLLM, LocalAI, and custom OpenAI-compatible endpoints. |
| Intended users | Covexe says it is built for evidence-synthesis researchers and organizations including universities, research laboratories, public health institutes, hospitals, and independent researchers. | It is intended for PhD students, researchers, professors, evidence synthesis teams, and systematic or scoping review authors. |
| Privacy | Covexe says it does not use tracking or advertising cookies or third-party analytics scripts. | The Web App binds to 127.0.0.1 for local use and is not intended as a public multi-user service. |
| Purpose | Covexe is a browser-based platform for systematic reviews, meta-analysis, evidence synthesis, and applied statistics. | Universal SLR Assistant supports systematic and scoping review workflows with AI-assisted screening, extraction, and reproducible outputs. |
| Reference imports | Screening can import references in RIS, NBIB, BibTeX, PubMed XML, CSV, and Excel formats and detects duplicates by DOI and PMID. | It accepts RIS, BibTeX and CSV references, including exports from PubMed, Scopus and Web of Science. |
| Review workflow | Its review module covers question and search, screening, full-text review, extraction, appraisal, synthesis, and reporting. | The workflow covers reference import, abstract screening, full-text PDF processing, structured extraction, and export. |
| Support | Email support is available at [email protected], with replies stated to arrive within 1–2 business days. | The project directs users to the Complete User Guide, in-app Help panel, output logs, tests, and GitHub issues for support. |
Plans
In their own words
Covexe
Covexe is a browser-based platform for systematic reviews, meta-analysis, evidence synthesis, and applied statistics. Its review workflow spans question and search, screening, full-text review, extraction, appraisal, synthesis, and reporting. It supports systematic, scoping, network meta-analysis, diagnostic accuracy, umbrella, rapid, and narrative reviews. Methods include pairwise and network meta-analysis, GRADE ratings, risk-of-bias tools, and a PRISMA 2020 flow diagram; the statistics suite covers regression, survival analysis, diagnostic accuracy, and other methods checked against R packages and implementations. References can be imported in RIS, NBIB, BibTeX, PubMed XML, CSV, and Excel formats, with duplicates detected by DOI and PMID. Users can connect their own OpenAI, Anthropic, or Google AI key. The co-pilot pauses for approval at checkpoints, and AI screening will not exclude a study without user approval. Signed-out work stays in the browser; signed-in reviews are stored for cloud sync and sharing. The free plan costs nothing, while Pro costs $99 a year. Team costs $150 a year per seat with a three-seat minimum.
Universal SLR Assistant
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.