grobidOrg/grobid

Health v2 · maintenance only

Adoption not part of the score

5105 stars · 567 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

GROBID is a Java machine learning library that extracts, parses, and re-structures raw documents such as PDFs into structured XML/TEI, focused on technical and scientific publications. It provides header extraction, reference parsing, citation context resolution, and full-text document segmentation, with a REST API and Docker deployment.

Use cases

• extract metadata (title, authors, abstract) from scientific PDFs
• parse bibliographic references from scholarly articles
• convert PDF papers into structured TEI XML
• resolve citation contexts to full references
• segment and structure full text of academic PDFs
• batch process large corpora of scientific publications

When to choose

• you need high-accuracy extraction of bibliographic data from scholarly PDFs
• you want structured XML/TEI output from unstructured scientific documents
• you need a self-hosted, Docker-deployable PDF parsing service
• you are building scholarly search, citation analysis, or literature review tooling

When to avoid

• you only need simple text extraction without structure (pdftotext suffices)
• your documents are not technical/scientific publications
• you cannot run a JVM-based service or ML models
• you need extraction from scanned PDFs without OCR preprocessing

Facets

library · maturity active

machine-learning nlp pdf parser ocr machine-learning pdf developer-tools jvm cross-platform pdf-parsing tei-xml scholarly-documents bibliographic-references metadata-extraction deep-learning crf transformers natural-language-processing docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="grobidOrg/grobid")