This paper presents Zotero RDF Server (ZRS), a modular framework that reimagines the ubiquitous reference manager Zotero as a federated knowledge graph platform tailored to the specific but often shared needs of humanities scholars, especially in settings where large made-to-measure infrastructures are unavailable, slow to deploy, or overly expensive. On a methodological level, the tool presents a potential solution to a notorious problem: a digital reproducible workflow for individual scholars working with scarce resources and with no or little quantitative methods. With ZRS, these scholars not only enhance their work’s replicability by producing interoperable data and queries. The paper argues that scholars also gain digital literacy, taking off from a workflow they use already leading to a Semantic Web representation of their own data.

Zotero is widely used in everyday scholarship for collaborative bibliographic control, note-taking, as well as PDF storage and annotation. Yet its potential as a rich semantic knowledge graph connected to external vocabularies and structured data workflows is still underexplored. ZRS leverages Zotero’s open API to generate RDF triples that retain familiar user practices while adding semantic interoperability, on the fly and with almost no additional effort. The system ingests multiple Zotero libraries, applies configurable RDF/OWL mapping rules to identify entities (e.g., creators, places), and persists them in an embedded Oxigraph triple store that exposes a SPARQL endpoint. Additionally, it performs OCR (Kraken/Transformer) and ingests texts and embeddings in an OpenSearch index for deterministic queries.