- Home
- AI Literature Review Software
- ASReview
ASReview
Utrecht, Netherlands
What it is
ASReview uses AI-aided active learning to prioritize records for systematic review screening while keeping a human screener involved in decisions. The site says it can reduce screening workload by up to 95%. Users can simulate AI-aided reviewing to compare models, and teams can screen in parallel with Crowdscreen, where administrators control access through a private login system. Described model series include ELAS-Ultra, ELAS-Heavy, and language-agnostic ELAS-L; ELAS-Heavy and ELAS-L require the Dory package. ASReview works with EndNote, PubMed, and other reference managers, and imports and exports CSV, RIS, and XLSX files. Documentation includes a Python API, while institutional workflows also mention a REST API and command-line interface. In the default local setup, data remains on the user's computer; server deployments keep it within the organization's environment and policies. ASReview is free and open source, with no licensing fees or subscriptions, though running hardware or a server may incur costs. Support resources include documentation, tutorials, videos, community discussion, workshops, and consultancy.
For and against
For
- Keeps a human screener in the decision loop.
- Supports parallel screening through Crowdscreen.
- Imports and exports CSV, RIS, and XLSX.
- Free and open source, with no licensing fees.
Against
- Running hardware or a server may incur costs.
- Some model series require the Dory package.
- No AI paper summaries or full-text management.
The verdict
ASReview provides screening prioritization with human decisions retained, plus options for simulation and team screening. Its local data setup and file support are useful points to weigh against server costs or model dependencies.
Who it suits
ASReview suits screeners and information specialists conducting systematic reviews, as well as data scientists, developers, institutions, and students. Its team screening and APIs may also suit collaborative or automated workflows.
Plans and prices
Free and open-source ASReview LAB
core screening software · local, server or Docker deployment · no paid tier stated
Read 15 Oct 2026 · asreview.nl
ASReview LAB
Free and open source · no licensing fees or subscriptions · running your own hardware or server may incur costs
Read 28 Sep 2026 · asreview.nl
On the record
- AI models
- Version 2 presets include ELAS-ultra, ELAS-heavy and ELAS-lang, with configurable classifiers, feature extractors and query strategies.asreview.nl · read 15 Oct 2026
- API
- ASReview documentation includes a Python API, and the institutional page also mentions a REST API and CLI for automated workflows.asreview.nl · read 28 Sep 2026
- API maturity
- The API documentation warns that the API is still under development and may change without warning.asreview.readthedocs.io · read 15 Oct 2026
- Citation-manager integrations
- Documented citation-manager compatibility includes EndNote, Excel, Mendeley, RefWorks and Zotero through supported export formats.asreview.readthedocs.io · read 15 Oct 2026
- Company description
- LinkedIn describes ASReview as open-source software developed at Utrecht University for active-learning screening of scientific papers, policy reports and social-media data.nl.linkedin.com · read 15 Oct 2026
- Company headquarters
- LinkedIn lists Utrecht, Netherlands as the headquarters and primary location.nl.linkedin.com · read 15 Oct 2026
- Company size
- LinkedIn lists the organization size as 11–50 employees.nl.linkedin.com · read 15 Oct 2026
- Crowdscreen
- Crowdscreen lets AI agents propose records to a crowd of experts.asreview.nl · read 15 Oct 2026
- Custom models
- Model extensions can add classifiers, query strategies, balancing strategies and feature-extraction methods.asreview.readthedocs.io · read 15 Oct 2026
- Dataset quality requirement
- Official documentation says models work best when duplicates are removed and titles and abstracts are complete for most records.asreview.readthedocs.io · read 15 Oct 2026
- Documentation depth
- The documentation covers user, server and technical guides, including authentication, command-line use, APIs and extension development.asreview.readthedocs.io · read 15 Oct 2026
- Documentation support
- The maker directs users to more than 500 pages of documentation and a GitHub community for help.asreview.nl · read 15 Oct 2026
- Double-screening limitation
- The independent review describes ASReview as a single-screener prioritization engine without multi-reviewer blind screening.augmentedscholars.com · read 15 Oct 2026
- Extension system
- Python extensions can add model, subcommand and dataset functionality through setuptools entry points.asreview.readthedocs.io · read 15 Oct 2026
- Formats
- The institutional workflow page describes CSV, RIS, and XLSX import and export.asreview.nl · read 28 Sep 2026
- Full-text limitation
- ASReview focuses on title-and-abstract screening and does not provide downstream full-text review or data-extraction workflows.augmentedscholars.com · read 15 Oct 2026
- Human decisions
- Human reviewers label records while the model continuously updates the ranking.augmentedscholars.com · read 15 Oct 2026
- Independent praise: auditability
- RSRCHDB describes the open code and peer-reviewed benchmarks as useful when screening decisions must survive audit.rsrchdb.com · read 15 Oct 2026
