PaperLabYour papers and notes stay on your computer
PaperLab is local-first: one user, one machine, no accounts. Your PDFs, notes and search index live in a local Postgres database. With a local model, the text of your papers and notes never leaves your computer. A model or search source tagged “Cloud” receives what is sent to it, and PaperLab asks before the first send to a cloud search source. The README lists what every setting sends and where.
What you can do
- No account, no sign-up, no telemetry.
- PDFs, notes and the search index live in a local database.
- Local models keep all text on your machine; cloud ones are tagged “Cloud”.
- Metadata lookups send a DOI or title, never a paper’s text.
- The only automatic request is the update check, which you can turn off.
- AI text is stored apart from yours and always labelled.
Tips
- For unpublished work or peer reviews, use a local model and the built-in search model.
- Read the README’s Principles section: it lists every request, source by source.
Questions people ask
Is PaperLab GDPR-friendly?
With local models, your documents never leave your machine, which keeps most data-protection questions simple. Cloud models and sources are your choice, per connection.
Does PaperLab collect analytics?
No. The desktop app’s only automatic request is the update check.
Can I back up my library?
Yes. The app saves a backup before each upgrade, and a one-line command exports the database any time.
Works well with
Guides
- How to chat with a PDF locally, without uploading it — Ask papers questions with a local model, and check every answer against the page.
- Open-source alternative to ChatPDF, Elicit and SciSpace — Online AI paper tools compared with a local, open-source option.
- Running a local LLM for research — Hardware, Ollama, choosing a model, and making it answer well.