Highlights
Highlight PDFs in five colours or your own, and edit notes in place.
Features
From the first PDF to the chart in your thesis, on your own computer. The README lists what each setting sends and where.

Highlight PDFs in five colours or your own, and edit notes in place.

Every note keeps its page and passage, and says who wrote it.
![A question and an AI answer citing [C1] and [C2]; hovering [C1] shows its page and section, a line leads to that passage flashed on the page, and part of the answer is saved as an AI note.](/PaperLab/shots/feature-ask-a-paper.webp)
Chat with a paper; every answer cites the passage it used.

Hover [51] to see which paper it is, then open or add it.

Capture a table or a number, chart it next to your own CSV.

Drop in PDFs; they are extracted, split and indexed in the background.

Group papers by project; chat across a whole workspace.

What a paper cites and who cited it since, ranked for your library.

Citations, authors, topics, notes and similar content, in five views.

macOS, Windows and Linux; announces updates, never installs them.
Search arXiv, Crossref, CORE, Unpaywall and Semantic Scholar at once.
Ollama, Anthropic or any OpenAI-compatible server, picked per question.
Search passages by meaning, with a built-in model or one you pick.
An MCP server lets Claude search and quote your library.
One user, one machine, no account; you choose what leaves it.
Search free sources, screen in two stages, snowball and count for PRISMA.
PaperLab is free, open source and built by one person. A star helps other researchers find it and puts each new release in your GitHub feed. The PaperLab page on LinkedIn posts a weekly breakdown of how one feature works.