What it does
GROBID reads scholarly PDF documents and pulls out their parts, such as title, authors, affiliations, abstract, references and the main text, in an organised format.
It uses machine learning to recognise these parts, and can match references to their official records. Its makers say it is used in production by many research and archive services.
It runs as a web service on your own server, and public demo servers are available for trying it out.
Who it's for
Libraries, research platforms and developers who process large numbers of scientific papers.
Can I use it without coding?
With some setup. You can try a public demo; serious use means running it with Docker or building it on Linux or Mac. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Linux, Mac, Server
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Try the public demo server mentioned in the README with a sample PDF.
- For regular use, run GROBID on your own machine with its Docker container and send PDFs to its web service.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe