Read with source context
Keep PDFs, metadata review, highlights, source-linked notes, tags and project notes together.
Version 1.2.0 · Windows 10/11 · x64
Read and compare research PDFs, keep notes tied to their pages, search for exact words or related ideas, and prepare citation drafts in one Windows project.
No account required
Good fit for: Researchers who already have their PDFs and want to read, compare, search, and cite them in one local project.
Choose exact search for known terms, optional semantic search for related wording and OCR for image-only pages. Reopen the source before relying on any result.
Keep PDFs, metadata review, highlights, source-linked notes, tags and project notes together.
Read two sources side by side. Citation-aware copy works from the built-in reader, and Citation History can reopen evidence in its original source context.
Use exact search without a model or install E5 or BGE-M3 for optional local semantic suggestions.
Run local OCR, then create APA 7, MLA 9, Chicago 18, or IEEE citation drafts to check against the source.
Choose it when you already have research PDFs and want to read, compare, search, and organize their evidence in one local project.
Choose other services for shared cloud editing, database discovery, formal systematic-review screening, protocol reporting or a full writing editor.
Scroll the table horizontally on a narrow screen.
| What you need | Start with | What to check |
|---|---|---|
| Known word, author or identifier | Exact search | PDF text layer or OCR output |
| Related ideas with different wording | Multilingual E5 Large INT8 | About 557 MiB and 8 GB RAM recommended |
| Larger semantic model | BGE-M3 Full Precision | About 2.13 GiB and 16 GB RAM recommended |
| Scanned or image-only PDF | OCR, then exact or semantic search | Selected OCR language; names, numbers and quotations checked against the page image |
Product facts and standalone file verified August 27, 2026.
Use a documented discovery method, then add the PDFs that belong in the local project.
Keep a note or copied passage connected to the source page and compare sources when needed.
Use exact, semantic or OCR-assisted search, then reopen the page before using the evidence.
See the portfolio-level explanation in Network & data.
These previews show six parts of the research workflow. The sections below explain what each tool does and what you need to check.






Microsoft Store is recommended for the simplest install and update path. A standalone EXE and verification details remain available below.
System: Windows 10 version 1809 (build 17763) or later, or Windows 11; x64 architecture; model-specific memory requirements apply
Direct download for Windows
Windows SmartScreen checks publisher and reputation information for downloaded EXE files. If Windows shows a notice, confirm that you used the download link on this page before continuing. Understand Windows download notices.
File: CiteFlow-Setup-1.2.0-x64.exe
Size: 64,215,549 bytes (61.24 MiB)
Authenticode: Not signed
567243d0619b15062cf3920295fe1ad67d8d5df5754626729763237ef6b93c8cVerified August 27, 2026 with two local hashing tools. A match confirms identical bytes; it does not add a publisher signature or guarantee that a file is safe.
View this SHA-256 on VirusTotalDownload the file from an official link, then compare its name, size, and SHA-256 with the values above. The illustrated SHA-256 guide shows every step.
Use the primary link above first. This source provides the same verified release file.
No. CiteFlow never uploads the PDF library. It checks update metadata when the six-hour interval is due and requests the public supporter list when Donate first opens. A selected DOI lookup sends bibliographic query data. Title translation sends the selected title to MyMemory, then Google and LibreTranslate in that order after a failed response.
No. Exact search works without E5 or BGE-M3 and depends on the PDF text layer or OCR output.
No. Semantic Search is beta. It can miss relevant passages or return irrelevant results, and similarity is not proof of a claim.
E5 Large INT8 is about 557 MiB with 8 GB RAM recommended. BGE-M3 Full Precision is about 2.13 GiB with 16 GB RAM recommended.
Yes. The optional managed OCR component supports eight text languages plus script detection, but names, numbers, tables and citations must be checked against the page image.
Version 1.2.0 supports APA 7, MLA 9, Chicago 18 author-date, Chicago 18 notes-and-bibliography and IEEE drafts.
No. It supports local evidence organization after collection and does not replace database searching, protocol registration, formal screening, deduplication or critical appraisal.