EvidenceGrid AI vs RobotReviewer
EvidenceGrid AI
evidencegrid.appRobotReviewer
robotreviewer.netSide by side
| Figure | EvidenceGrid AI | RobotReviewer |
|---|---|---|
| Price from | Free | 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 | 1 | 2 |
| Spec score · AI Literature Review Software | 7.5 (#24) | 8.4 (#6) |
| Purpose | EvidenceGrid AI automates paper screening, data extraction, and conflict resolution for systematic reviews. | RobotReviewer automatically annotates clinical trial PDFs with PICO characteristics and likely bias assessments using the Cochrane Risk of Bias tool. |
| Support | The feedback page lets users send a message for support and directs suspended account holders to its Contact tab. | The project directs users to an email address for questions and integration assistance. |
Plans
In their own words
EvidenceGrid AI
EvidenceGrid AI is a web platform for research teams conducting systematic literature reviews. It automates paper screening, data extraction, and conflict resolution. Searches run across PubMed, OpenAlex, arXiv, Europe PMC, and CORE at the same time. AI pre-screens papers against review criteria and flags borderline cases for human review, while kappa scores are calculated during screening. Reviewers can upload PDFs or fetch open-access versions, then annotate them in the built-in reader. Teams define custom extraction fields; AI finds values in full text for approval or editing. Decisions are timestamped and attributed, and exports include approval audit trails. Evidence grids export to Excel, CSV, or structured JSON with PRISMA flow counts. Co-reviewers can receive role-based access and shared annotations. The workflow guide says it aligns with PRISMA 2020 and Cochrane standards. The Free plan costs nothing, includes 10 papers and 3 AI extractions, and requires no credit card.
RobotReviewer
RobotReviewer analyzes clinical trial reports by annotating PDFs with PICO characteristics and likely bias assessments using the Cochrane Risk of Bias tool. Uploading PDFs on the website extracts key data and presents a summary table. Its REST API can process groups of clinical trial reports to synthesize results across trials. The project is open source under GNU GPL version 3.0 and is free to use. It can run locally as Docker services, with a web app and API server exposed on local ports. The self-hosted processing setup uses Grobid, RabbitMQ, Celery, and SciBERT through bert-as-a-service. Docker instructions cover GPU use, and the worker can also run CPU-only. Manual setup calls for Python 3.6, TensorFlow 1.12.0, and the associated processing services. Installation is documented as tested on Ubuntu and Mac OS; Windows works with substantial installation difficulty. Maintainers ask users to cite the 2017 ACL paper and invite questions by email, including requests for help integrating RobotReviewer into other software.