ASReview is a free, open-source tool that uses AI-aided active learning to prioritize records for systematic review screening while keeping a human screener in the decision loop. Its site says the approach can reduce screening workload by up to 95%. Users can simulate AI-aided screening to compare models, and teams can screen in parallel through Crowdscreen, where administrators manage access with a private login system. Described model series include ELAS-Ultra, ELAS-Heavy, and language-agnostic ELAS-L; the latter two require the Dory package. ASReview works with reference managers including EndNote and PubMed, and supports CSV, RIS, and XLSX import and export. Documentation includes a Python API, as well as a REST API and CLI for automated workflows. The default local setup keeps data on the user's computer; server deployments keep data within the organization's environment and apply its policies. The project offers documentation, tutorials, videos, community discussion, workshops, and consultancy.
Who it is for
ASReview suits screeners and research teams who need to prioritize records for systematic reviews while keeping decisions with a human. Its collaboration, automation, and organizational support options may also suit institutions and developers.
What is good
- Free and open source, with no licensing fees or subscriptions
- Human screeners remain in the decision loop
- Supports parallel screening through Crowdscreen
- Imports and exports CSV, RIS, and XLSX
- Local setup keeps data on the user's computer
What to know first
- ELAS-Heavy and ELAS-L require the Dory package
- Running your own hardware or server may incur costs
- AI paper summaries are not included
- Full-text management is not included
Freedom251 review
ASReview: the full review
ASReview offers active-learning prioritization, team screening, and workflow automation for systematic reviews. Its local setup keeps data on the user's computer, while organizations can deploy it within their own environment.
ASReview is a free tool for researchers screening records in a systematic review. It is best suited to people who want AI to prioritize their next decisions without removing the human screener from the process. Its strongest case is a local, flexible workflow; it is less suitable if you need built-in full-text management or AI paper summaries.
Overview
ASReview applies active learning to help screeners work through records, with the site saying it can reduce screening workload by up to 95%. That is a potential reduction, not a guaranteed outcome, so teams should treat it as a way to prioritize work rather than a substitute for screening judgment.
The workflow supports recommendations and systematic reviews, but does not include full-text management or AI paper summaries. It can exchange CSV, RIS, and XLSX files and is described as compatible with EndNote, PubMed, and other reference managers. For broader comparisons, see our AI Literature Review Software, Literature Review Software, and Systematic Review Software lists.
Key features
Active learning and simulation
As screening decisions accumulate, ASReview uses them to prioritize which records a human should assess next. Simulation tools let users compare models and review performance before applying an AI-aided workflow. Named model families include ELAS-Ultra, ELAS-Heavy, and language-agnostic ELAS-L; the latter two require the Dory package. This makes the tool more compelling for researchers who want to examine model behavior, though the named models do not remove the need for human decisions.
Team screening and automation
Crowdscreen supports parallel team screening, with administrators controlling access through a private login system. A Python API, REST API, and command-line interface provide routes to automate workflows, which is useful for technical teams and institutions managing repeatable processes. CSV, RIS, and XLSX import and export also help teams move records between ASReview and reference-management workflows.
Privacy and support
The default setup keeps data on the user's computer. Organizations can instead deploy ASReview within their own environment, where their policies apply. The site describes the software as GDPR compliant, says it has no tracking cookies, and says it provides security updates. Free documentation, tutorials, videos, and community discussion support are available; organizations can also seek in-house workshops and custom consultancy.
Pricing
ASReview LAB costs 0.00 USD per free. It is free and open source, with no licensing fees or subscriptions. There is no free trial because the software is free. The trade-off is operational rather than a subscription tier: running your own hardware or server may incur costs. The free plan supports screening workflows, systematic-review tools, collaboration, recommendations, and CSV, RIS, and XLSX exports, but not AI paper summaries or full-text management.
Platforms
ASReview supports API, Linux, macOS, self-hosted, web, and Windows environments. The local-first option suits individual researchers who want data to remain on their computer; self-hosting gives organizations control over deployment within their own environment.
Who it's for
ASReview is a strong fit for screeners, information specialists, students, and research teams that need to prioritize records for a systematic review while keeping people in the decision loop. Data scientists and developers can make use of its APIs and automation interfaces, while institutions can use team screening and deploy within their own environment. Look elsewhere if your core requirement is a single tool that also manages full text or generates AI paper summaries.
Pros and cons
- Pros: Free, open-source access avoids licensing fees and subscriptions, making it practical for individual researchers and teams willing to manage their own setup.
- Pros: Local use and in-environment deployment give users and organizations control over where review data resides.
- Pros: Simulation, multiple model families, team screening, and APIs support workflows ranging from model comparison to institutional automation.
- Cons: Running hardware or a server may still cost money, so free software does not necessarily mean a cost-free deployment.
- Cons: No full-text management or AI paper summaries means users needing either capability will need another tool or workflow.
- Cons: ELAS-Heavy and ELAS-L require the Dory package, adding a dependency for users who want those models.
Alternatives
Choose Buhos if you want another free option that supports API, Linux, macOS, self-hosted, web, and Windows deployments. RevMan is worth considering if you prefer a freemium product with a free trial and support across Linux, macOS, web, and Windows. If an open-source R package with a web interface is a better fit, Bibliometrix is free and offers the Biblioshiny web interface.
EviSynth is a free, open-source option for academic use with unlimited collaborators, available on Android, iOS, and web. Rayyan may suit readers who want a freemium workflow with mobile apps; its free plan is capped at three active reviews and two free reviewers, with limited mobile access. Elicit is a freemium alternative with unlimited search across more than 138 million papers, unlimited summaries, and unlimited chat with papers on its Basic plan, though usage for Research Agent and Research Reports is limited.
EPPI-Reviewer is a paid alternative with a free trial. Litmaps is a freemium web alternative; its free plan allows up to 20 inputs, 100 articles, and one Litmap, with no collaboration.
Verdict
Choose ASReview if you need a free, open-source way to prioritize systematic-review screening while keeping people responsible for decisions and retaining control over data location. Its combination of simulation, team screening, and automation is persuasive for research groups and institutions. Look elsewhere if summaries or full-text management are central to your review, or if you need a workflow that avoids managing local or organizational infrastructure.
ASReview plans and pricing
All plansCompared on AI literature review software
- Free plan
- Yes
- Screening workflow
- Yes
- AI paper summaries
- No
- Systematic review support
- Yes
- Export formats
- CSV, RIS, XLSX





