# kevin2li/pdf-guru

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/kevin2li-pdf-guru).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,113 stars · 335 forks · Vue · AGPL-3.0

## Links

- GitHub: https://github.com/kevin2li/PDF-Guru
- Homepage: https://guru.kevin2li.com/
- awesome-repositories: https://awesome-repositories.com/repository/kevin2li-pdf-guru.md

## Topics

`ai-flashcards` `anki-flashcards` `anki-to-pdf` `excel-to-anki` `markdown-to-anki` `mindmap-to-anki` `mubu-to-anki` `pdf-to-anki` `pdf-toolbox` `pdf-watermark` `wereader-to-anki` `word-to-anki`

## Description

PDF-Guru is an AI-powered document processor and study material converter designed to transform textbooks, research papers, and multimedia content into structured flashcards for spaced repetition systems like Anki. It functions as a content pipeline that uses language models to extract key concepts and facts from unstructured documents to generate question-and-answer pairs, cloze deletions, and multiple-choice cards.

The system distinguishes itself through a comprehensive PDF management suite and multi-format parsing. It provides advanced document utilities including optical character recognition for creating searchable PDFs, batch annotation, and low-level page manipulation such as merging, splitting, cropping, and rotating. It also supports the conversion of diverse inputs, including spreadsheets, mind maps, e-books, and videos—complete with timestamped frame captures—into study assets.

Beyond content generation, the project includes tools for card and deck management, such as bulk field editing and template configuration. It supports data synchronization across devices via local networks, remote servers, or self-hosted backends, and integrates with Zotero research libraries. The platform also handles asset optimization by replacing embedded images with cloud links to reduce storage and synchronization time.

Users can export their reading notes and card decks into multiple formats, including Markdown, TXT, XLSX, and PDF.

## Tags

### Artificial Intelligence & ML

- [AI Document Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-document-processors.md) — A system that uses language models to extract key concepts and facts from textbooks and research papers for study.
- [Image Text Extractions](https://awesome-repositories.com/f/artificial-intelligence-ml/image-text-extractions.md) — Extraction of text from images to create searchable dual-layer PDFs. ([source](https://cdn.jsdelivr.net/gh/kevin2li/pdf-guru@main/README.md))
- [Document Knowledge Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/knowledge-retrieval-and-documents/document-knowledge-extraction.md) — Uses large language models to automatically extract structured knowledge and create Q&A pairs from unstructured documents.
- [Cloze Exercise Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/interactive-topic-hierarchies/mind-maps/cloze-exercise-generation.md) — Hides specific words from mind map text to create interactive fill-in-the-blank study exercises. ([source](https://guru.kevin2li.com/docs/anki-toolbox/mind-card/))
- [Q&A Pair Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/interactive-topic-hierarchies/mind-maps/q-a-pair-generation.md) — Generates flashcards formatted as questions and answers based on hierarchical mind map content. ([source](https://guru.kevin2li.com/docs/anki-toolbox/mind-card/))
- [Study Card Conversions](https://awesome-repositories.com/f/artificial-intelligence-ml/interactive-topic-hierarchies/mind-maps/study-card-conversions.md) — Transforms conceptual diagrams and hierarchical maps into a sequence of structured study cards. ([source](https://guru.kevin2li.com/docs/anki-toolbox))

### Education & Learning Resources

- [Flashcard Generators](https://awesome-repositories.com/f/education-learning-resources/flashcard-generators.md) — Provides AI-powered generation of Anki-compatible flashcards by extracting key concepts and facts from documents. ([source](https://guru.kevin2li.com/docs/intro))
- [Content Pipelines](https://awesome-repositories.com/f/education-learning-resources/spaced-repetition-systems/content-pipelines.md) — A workflow for transforming multimedia content and reading notes into a digital knowledge base for active recall.
- [Cloze Deletion Generators](https://awesome-repositories.com/f/education-learning-resources/cloze-deletion-generators.md) — Automatically generates fill-in-the-blank cloze deletion flashcards to test specific knowledge gaps. ([source](https://guru.kevin2li.com/docs/word-card))
- [Study Material Converters](https://awesome-repositories.com/f/education-learning-resources/custom-study-material-management/study-material-converters.md) — A tool that transforms spreadsheets, mind maps and videos into question-and-answer pairs for educational software.
- [Knowledge Management](https://awesome-repositories.com/f/education-learning-resources/knowledge-management.md) — Provides comprehensive management of spaced repetition cards, including bulk editing, tagging, and template configuration.
- [Question and Answer Sets](https://awesome-repositories.com/f/education-learning-resources/question-and-answer-sets.md) — Production of flashcards with a distinct question on the front and an answer on the back. ([source](https://guru.kevin2li.com/docs/word-card))
- [Multiple Choice Generators](https://awesome-repositories.com/f/education-learning-resources/flashcard-generators/multiple-choice-generators.md) — Builds flashcards that present a question alongside several options to test selection accuracy. ([source](https://guru.kevin2li.com/docs/word-card))
- [Language Learning Workflows](https://awesome-repositories.com/f/education-learning-resources/language-learning-workflows.md) — Facilitates language acquisition by creating specialized vocabulary cards and audio assets from text.
- [Multimedia Flashcard Generation](https://awesome-repositories.com/f/education-learning-resources/multimedia-flashcard-generation.md) — Produces study cards incorporating various media types to improve memory retention through multisensory learning. ([source](https://guru.kevin2li.com/docs/anki-toolbox))
- [Timestamped Video Note Capture](https://awesome-repositories.com/f/education-learning-resources/timestamped-video-note-capture.md) — Capture of notes from videos with embedded timestamps and screenshots linked to playback moments. ([source](https://guru.kevin2li.com/docs/anki-toolbox/video-notes))

### Graphics & Multimedia

- [Study Card Conversions](https://awesome-repositories.com/f/graphics-multimedia/document-to-text-conversions/study-card-conversions.md) — Transforms PDFs, Word documents, Excel files, and mind maps into structured study flashcards. ([source](https://guru.kevin2li.com/docs/intro))
- [Video Conversions](https://awesome-repositories.com/f/graphics-multimedia/document-to-text-conversions/study-card-conversions/video-conversions.md) — Creation of study cards using content extracted from video recordings. ([source](https://guru.kevin2li.com/docs/anki-toolbox))
- [Searchable PDF Layers](https://awesome-repositories.com/f/graphics-multimedia/searchable-pdf-layers.md) — Creates searchable PDFs by overlaying machine-readable text on image-based document layers using OCR.
- [Video Frame Capture](https://awesome-repositories.com/f/graphics-multimedia/video-frame-capture.md) — Marking of key frames and timestamps from videos to create summary notes and cards. ([source](https://guru.kevin2li.com/docs/intro))

### Part of an Awesome List

- [Study Card Extractions](https://awesome-repositories.com/f/awesome-lists/ai/question-answering/study-card-extractions.md) — Extraction of information from PDF documents to create pairs for active recall. ([source](https://guru.kevin2li.com/docs/pdf-card))
- [PDF Text Extractors](https://awesome-repositories.com/f/awesome-lists/data/document-parsing-and-extraction/pdf-text-extractors.md) — Recognition and conversion of images of text within a PDF into machine-readable text. ([source](https://guru.kevin2li.com/docs/pdf-toolbox))
- [Timestamped Video Notes](https://awesome-repositories.com/f/awesome-lists/productivity/note-taking/timestamped-video-notes.md) — Links specific video playback timestamps to captured screenshots and notes for contextual study recall.
- [PDF](https://awesome-repositories.com/f/awesome-lists/more/pdf.md) — Listed in the “PDF 工具” section of the Great Open Source Project awesome list.

### Business & Productivity Software

- [Annotation to Note Conversions](https://awesome-repositories.com/f/business-productivity-software/annotation-to-note-conversions.md) — Transforms highlights, mind maps, and research notes into structured formats for active recall.
- [Automated Card Generation](https://awesome-repositories.com/f/business-productivity-software/note-taking-applications/study-notes/automated-card-generation.md) — Automatically generates Q&A, cloze deletions, and multiple choice cards from text notes. ([source](https://guru.kevin2li.com/docs/anki-toolbox/text-card))
- [Vocabulary Cards](https://awesome-repositories.com/f/business-productivity-software/note-taking-applications/study-notes/automated-card-generation/vocabulary-cards.md) — Generation of dedicated study cards for words and phrases to improve language acquisition. ([source](https://guru.kevin2li.com/docs/anki-toolbox/vocab-card))

### Content Management & Publishing

- [Searchable PDF Generation](https://awesome-repositories.com/f/content-management-publishing/pdf-document-generation/searchable-pdf-generation.md) — Generation of PDFs with an invisible text layer over an image layer for document searching. ([source](https://guru.kevin2li.com/docs/pdf-toolbox))
- [PDF Document Management](https://awesome-repositories.com/f/content-management-publishing/pdf-document-management.md) — A utility for editing, merging, compressing and performing OCR on PDF documents to prepare them for learning. ([source](https://guru.kevin2li.com/docs/price))
- [PDF Format Converters](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/format-conversion-toolkits/pdf-format-converters.md) — Implements tools to transform PDF files into other document formats and vice versa for better accessibility. ([source](https://cdn.jsdelivr.net/gh/kevin2li/pdf-guru@main/README.md))
- [Document Processing Pipelines](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/pdf-processing-engines/pdf-processing/document-processing-pipelines.md) — Implements a multi-step processing pipeline for PDF operations including cropping, merging, splitting, and rotating.
- [Content Extractions](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing/document-splitting-and-merging/multi-document-pdf-splitters/pdf-page-extraction/content-extractions.md) — Extraction of specific pages, text blocks, or images out of a PDF into separate files. ([source](https://cdn.jsdelivr.net/gh/kevin2li/pdf-guru@main/README.md))
- [Note-to-Card Extractions](https://awesome-repositories.com/f/content-management-publishing/e-book-platform-integrations/note-to-card-extractions.md) — Extracts highlighted or noted text from digital reading platforms to create targeted study cards. ([source](https://guru.kevin2li.com/docs/anki-toolbox))
- [Flashcard Layout Mapping](https://awesome-repositories.com/f/content-management-publishing/model-card-generation/template-based-generation/flashcard-layout-mapping.md) — Applies layout rules to map extracted content into structured flashcard formats like cloze deletions and multiple-choice.
- [Reading Note Extractions](https://awesome-repositories.com/f/content-management-publishing/reading-note-extractions.md) — Automatic import of highlights and annotations from reading platforms into flashcards. ([source](https://guru.kevin2li.com/docs/intro))

### Data & Databases

- [Multi-Format Document Parsers](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-extraction-ingestion/data-ingestion/document-parsing-pipelines/excel-file-parsing-pipelines/multi-format-document-parsers.md) — Parses diverse inputs including PDFs, spreadsheets, and mind maps into a standardized schema for study cards.
- [Excel Data Import](https://awesome-repositories.com/f/data-databases/excel-data-import.md) — Imports data from Excel spreadsheets to create structured study cards based on row and column values. ([source](https://guru.kevin2li.com/docs/anki-toolbox))

### Development Tools & Productivity

- [Cross-Device Document Syncs](https://awesome-repositories.com/f/development-tools-productivity/cross-device-document-syncs.md) — Synchronizes flashcard decks and media across different devices using local networks or self-hosted servers.

### DevOps & Infrastructure

- [Backend Sync Servers](https://awesome-repositories.com/f/devops-infrastructure/application-server-deployments/backend-sync-servers.md) — Provides a self-hosted backend server to synchronize study decks and media assets across multiple devices.
- [Remote Server Synchronization](https://awesome-repositories.com/f/devops-infrastructure/remote-server-synchronization.md) — Synchronizes study data across multiple devices by connecting to a remote server. ([source](https://guru.kevin2li.com/docs/anki-toolbox))
- [Sync Servers](https://awesome-repositories.com/f/devops-infrastructure/self-hosted-chat-servers/sync-servers.md) — Implements a self-hosted synchronization server to increase transfer speeds for decks and media. ([source](https://guru.kevin2li.com/docs/anki-toolbox/sync_server))

### Networking & Communication

- [Network Storage Synchronizations](https://awesome-repositories.com/f/networking-communication/network-storage-synchronizations.md) — Synchronizes study decks and media across devices within a local area network. ([source](https://guru.kevin2li.com/docs/intro))