Colandr
What it is
Colandr is a free, web-based platform for evidence reviews and other document reviews and syntheses. Machine learning ranks citations by relevance to help reviewers screen titles and abstracts, while natural language processing classifies included documents into user-defined categories and assists with full-text data extraction. Reviewers retain the final decisions about inclusion, exclusion, and classification, and teams can collaborate and cross-check decisions. Citation files can be imported in TXT, RIS, or BIB formats, with a 40 MB limit for a single import. Screening decisions and extracted data export as CSV. Colandr does not connect directly to citation databases, so users export citations elsewhere; it can help generate Boolean search strings. Reviewers must locate full-text papers themselves and import papers individually, because there is no mass-upload feature. Relevance rankings update after every 10 citations screened, and metadata extraction suggestions begin after 50 hand-coded extractions in a review. Colandr describes itself as open-source and open-access and runs on an AWS server hosted by Conservation International.
For and against
For
- Free open-access platform
- Machine learning ranks citation relevance
- Supports collaborative screening and cross-checking
- Exports decisions and data as CSV
- Open-source front-end and back-end code
Against
- No direct citation-database connections
- Full texts require one-at-a-time imports
- Single citation import capped at 40 MB
- Volunteer support may require waiting
The verdict
Colandr provides a free workflow for screening, classification, collaboration, and extraction in evidence reviews. Its manual citation and full-text preparation requirements should be considered before adoption.
Who it suits
Colandr suits review teams conducting evidence screening, systematic reviews, or related document syntheses in a browser. It is useful for groups that can prepare citation exports and manage full-text imports themselves.
Plans and prices
Free
Open access · collaborative reviews
Read 7 Oct 2026 · colandrcommunity.com
On the record
- Citation screening
- Machine learning sorts citations by relevance to help reviewers screen titles and abstracts.colandrcommunity.com · read 7 Oct 2026
- Collaboration
- The platform supports collaborative teams and cross-checking between review team members.colandrcommunity.com · read 7 Oct 2026
- Data extraction
- Natural language processing helps classify included documents into user-defined categories and supports full-text data extraction.colandrcommunity.com · read 7 Oct 2026
- Full-text uploads
- Users must find and import full-text papers themselves, one paper at a time; the FAQ says there is no mass-upload feature.colandrcommunity.com · read 7 Oct 2026
- Hosting
- The Colandr community site says the platform runs on an AWS server hosted by Conservation International.colandrcommunity.com · read 7 Oct 2026
- Human oversight
- Reviewers make the final inclusion, exclusion, and classification decisions.colandrcommunity.com · read 7 Oct 2026
- Import limits
- Supported citation import formats are TXT, RIS, and BIB, and a single import can be up to 40 MB.colandrcommunity.com · read 7 Oct 2026
- Imports and exports
- Colandr supports citation uploads in BibTeX and RIS formats and exports screening decisions and extracted data as CSV.colandrcommunity.com · read 7 Oct 2026
- Launch
- The Colandr community site says the platform launched in July 2017.colandrcommunity.com · read 7 Oct 2026
- Machine-learning thresholds
- Citation relevance ranking updates after every 10 citations screened, while metadata extraction suggestions begin after 50 hand-coded extractions in a review.colandrcommunity.com · read 7 Oct 2026
- Open source
- Colandr describes itself as an open-source, open-access tool and links to front-end and back-end code repositories.colandrcommunity.com · read 7 Oct 2026
- Purpose
- Colandr is a web-based platform for conducting evidence reviews and can be used for different types of document reviews and syntheses.colandrcommunity.com · read 7 Oct 2026
- Search databases
- Colandr does not connect to citation databases; users export citations from another system, while Colandr can help generate Boolean search strings.colandrcommunity.com · read 7 Oct 2026
- Support
- The team directs users to its help email and bug-reporting form, and asks users to allow time for responses because volunteers run the project.colandrcommunity.com · read 7 Oct 2026
