LitFlow vs RobotReviewer

LitFlow is an AI-augmented workspace for systematic literature reviews, covering search, screening, extraction, synthesis, and reporting. Search includes database queries, snowballing, and AI-generated synonyms. For each record, AI proposes per-criterion verdicts with confidence scores, explanations, and links to source passages, while researchers make the decisions. Custom extraction schemas can receive LLM pre-fill with source links, and a qualitative coding board supports thematic structure. Reports include PRISMA information, Cohen’s κ, and an audit trail in a publication-ready methods report. AI suggestions and human decisions are logged with timestamps, actors, and rationales. Users can bring keys for Gemini, Claude, OpenAI, or Mistral, or use open-source models hosted by the University of Münster. The closed alpha runs on University of Münster infrastructure in the EU under GDPR, with pseudonymised personal data in research outputs. Operated by the university’s LitFlow research project in Münster, it is free for academic use, requires maintainer approval, and has no commercial tier listed.

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.