MinerU: Turn PDFs and Office Files into Clean Markdown (GitHub, Scanned)
Converts PDFs, scans and Office documents into Markdown or JSON that a language model can read.
Scanned 4 min read
Loading…
/** @github-tools */
Best Document & Research Tools on GitHub
These tools convert, read, organise and research documents: PDF toolkits, OCR, Markdown converters, note apps, ebook managers and feed readers. The good ones keep your files on your own device and stay actively maintained. Choose by the job you face most, whether that is fixing PDFs, converting files, feeding documents to AI or keeping up with reading, and prefer an app over a library unless you code.
23 repos, each cloned and scanned
// top 10, ranked
Updated 30 October 2026 · moves since 26 October 2026 · re-ranked every 3 days on what readers use, never sponsored
- 1
BentoPDF: A Private PDF Toolkit That Runs in Your Browser (GitHub, Scanned)
no changeOver 50 PDF tools for merging, splitting, compressing and editing that run in your browser, so files never leave your device.
- 2
Joplin: Private Markdown Notes With Encrypted Sync (GitHub, Scanned)
no changeAn offline first Markdown notes app with encrypted sync, a solid free swap for Evernote.
- 3
calibre: Manage, Convert and Read Every Ebook (GitHub, Scanned)
no changeThe free ebook manager for organising, converting and sending books to your e-reader.
- 4
Docling: Documents to Clean Markdown and JSON (GitHub, Scanned)
no changeConverts PDFs and Office files into clean Markdown or JSON with tables intact, great for feeding AI.
- 5
OCRmyPDF: Make Scanned PDFs Searchable (GitHub, Scanned)
no changeAdds a searchable text layer to scanned PDFs offline, in over 100 languages.
- 6
Open Notebook: A Self-Hosted NotebookLM (GitHub, Scanned)
no changeA self hosted NotebookLM for chatting with your PDFs, videos and pages, and making audio summaries.
- 7
Folo: An Open Source AI RSS Reader for Everything You Follow (GitHub, Scanned)
no changeA modern RSS reader that gathers feeds, newsletters and videos, with AI summaries to cut through them.
- 8
PDFMathTranslate: Translate PDFs, Keep the Layout (GitHub, Scanned)
no changeTranslates scientific PDFs into a bilingual copy that keeps formulas and layout, ideal for researchers.
- 9
GPT Researcher: An Open Deep-Research Agent With Citations (GitHub, Scanned)
no changeA research agent that searches the web and your files and writes a cited report.
- 10
VERT: Convert Files in Your Browser, Not a Cloud (GitHub, Scanned)
no changeConverts documents, images and audio between over 250 formats right in your browser, with no uploads.
// all 23 in Documents & Research
calibre: Manage, Convert and Read Every Ebook (GitHub, Scanned)
The free ebook manager: organise, convert, edit and read books, and send them to your e-reader.
Scanned 3 min read
Logseq: Private, Open-Source Outliner for Notes and Knowledge (GitHub, Scanned)
A privacy-first outliner for notes, journals and linked knowledge, stored on your own device.
Scanned 6 min read
Joplin: Private Markdown Notes With Encrypted Sync (GitHub, Scanned)
An offline-first Markdown notes app for desktop and mobile, with end-to-end encrypted sync.
Scanned 6 min read
OCRmyPDF: Make Scanned PDFs Searchable (GitHub, Scanned)
Adds a searchable, copyable text layer to scanned PDFs, offline, in over 100 languages.
Scanned 3 min read
SiYuan: Self-Hosted, Privacy-First Knowledge Base (GitHub, Scanned)
A self-hostable, privacy-first notes workspace with block references, Markdown WYSIWYG and AI.
Scanned 6 min read
Readest: A Modern Open-Source Ebook Reader for Every Device (GitHub, Scanned)
An ebook reader for EPUB, PDF, MOBI and more, with highlights, TTS and sync across devices.
Scanned 5 min read
SurfSense: Private, Offline NotebookLM Alternative (GitHub, Scanned)
A desktop AI agent that researches and edits your documents on your own machine, NotebookLM style.
Scanned 6 min read
BentoPDF: A Private PDF Toolkit That Runs in Your Browser (GitHub, Scanned)
50+ PDF tools that run entirely in your browser, so your files never leave your device.
Scanned 4 min read
VERT: Convert Files in Your Browser, Not a Cloud (GitHub, Scanned)
A file converter that runs in your browser with WebAssembly, for over 250 file formats.
Scanned 3 min read
AppFlowy: The Open-Source Notion Alternative You Can Self-Host (GitHub, Scanned)
Docs, wikis, databases and kanban boards in one workspace, open source and yours to self-host.
Scanned 5 min read
Marker: Convert PDFs and Documents to Clean Markdown (GitHub, Scanned)
Turn PDFs, Office files and ebooks into clean Markdown, JSON or HTML, tables and equations intact.
Scanned 5 min read
Folo: An Open Source AI RSS Reader for Everything You Follow (GitHub, Scanned)
An open source RSS reader that gathers feeds, newsletters and videos, then summarises them with AI.
Scanned 5 min read
Open Notebook: A Self-Hosted NotebookLM (GitHub, Scanned)
A self-hosted NotebookLM: chat with your PDFs, videos and web pages, and turn them into podcasts.
Scanned 5 min read
PDFMathTranslate: Translate PDFs, Keep the Layout (GitHub, Scanned)
Translate scientific PDFs into a bilingual copy that keeps formulas, charts and layout intact.
Scanned 4 min read
PaddleOCR: Turn Images and PDFs Into Structured Text (GitHub, Scanned)
Baidu's OCR toolkit that reads text in 100+ languages and turns documents into Markdown or JSON.
Scanned 5 min read
Read Frog: AI Bilingual Translation for Learning Languages (GitHub, Scanned)
A browser extension that translates pages side by side with AI and turns what you read into flashcards.
Scanned 5 min read
Resume Matcher: Tailor Your Resume to Every Job With AI (GitHub, Scanned)
Tailors your resume and cover letter to each job description, scores the match, exports a PDF.
Scanned 5 min read
GPT Researcher: An Open Deep-Research Agent With Citations (GitHub, Scanned)
An open-source research agent that searches the web and your files and writes a cited report.
Scanned 4 min read
Firecrawl: Turn Any Website into LLM-Ready Data (GitHub, Scanned)
A web data API that searches, scrapes and crawls sites into clean Markdown or JSON for AI agents.
Scanned 6 min read
Crawl4AI: Open-Source Web Crawler for LLMs (GitHub, Scanned)
A Python crawler that turns websites into clean Markdown for RAG and agents, with a CLI and Docker server.
Scanned 5 min read
Docling: Documents to Clean Markdown and JSON (GitHub, Scanned)
Converts PDFs, Office files, HTML and more into clean Markdown or JSON, with tables and reading order intact.
Scanned 4 min read
MarkItDown: Convert Any File to Markdown for LLMs (GitHub, Scanned)
Microsoft's small Python tool that turns PDFs, Office files, HTML and more into Markdown for LLMs.
Scanned 4 min read
// How we scan
Before a repository gets a post here we clone it and run the same checks on every one. The scanner is a script in this site's own repository, its findings are written out with file and line, and a person reads every hit before writing the verdict in the post. The last full run was on Oct 28, 2026.
- Pinned commit
- A fresh clone of the default branch. The commit and date are on every report, so the findings are about one snapshot, not the repository in general.
- Secrets
- Credential patterns with a known shape: cloud access keys, API tokens for OpenAI, Anthropic, Slack, GitHub, Google and Stripe, chat webhooks, private key blocks.
- Suspicious code
- Code that decodes a string and then executes it, pipes a download straight into a shell, opens a raw socket to a shell, reaches a known exfiltration service, mines cryptocurrency, or looks packed.
- Install-time code
- npm lifecycle scripts, setup.py command classes, Cargo build scripts, and installer shell scripts: whether they use sudo, edit your shell profile, or fetch and run remote code.
- Committed binaries
- Executables and compiled objects identified by their bytes, not their file extension, so a renamed binary still shows up.
- CI workflows
- GitHub Actions that run on pull_request_target and check out the pull request head (a classic way to leak secrets), write-all permissions, and third-party actions pinned to a tag instead of a commit.
- Network hosts
- Every host the source code talks to, so an unexpected one stands out.
- Known vulnerabilities
- Every pinned dependency in the repository's lockfiles looked up in OSV.dev, counted by severity. Includes development dependencies, which is why the counts are not zero for a large web app.
- Project hygiene
- A security policy, automated dependency updates, CodeQL, a licence, contributing guidelines.
- OpenSSF Scorecard
- The Open Source Security Foundation's independent score, where the project has one.
Safe means no credential patterns, no decode-and-execute code, no exfiltration hosts, no undocumented install-time behaviour, no risky workflow, and nothing in the findings a reviewer could not explain. Anything you should know before installing (an installer that pipes to a shell, a tool that reads a credential you already have, a licence with conditions, or a lockfile with unpatched advisories) is the note beside the badge.
Not covered: we do not run the software, audit its logic, or review commits made after the scan. The date and commit are on every report. Check them, and read the code yourself before you trust it with anything that matters.
// Questions
- Are these GitHub AI tools free to use?
- All of them are free to download, run and modify. The licences differ: most are MIT or Apache 2.0, ComfyUI is GPL-3.0, and Open WebUI and Dify ship their own licences with conditions on rebranding and multi-tenant hosting. Each post says which licence applies and what it asks of you.
- What does it mean that a repository was scanned?
- We cloned it at a specific commit and ran the checks listed under How we scan: credential patterns, decode-and-execute code, install-time scripts, committed binaries, risky CI workflows, every host the code talks to, known vulnerabilities in pinned dependencies, and project hygiene. Every hit was read by a person before the verdict was written, and the findings are in each post.
- Why do known vulnerabilities show up in a scan marked safe?
- Because a lockfile pins development dependencies too. A large web app carries thousands of packages and OSV knows of advisories in some of them; most affect build tooling and never reach a user. Each post shows the counts per lockfile and the worst entries so you can see where they sit, and the notes say whether any of it ships to you.
- How current is a scan?
- The date and commit are printed in every post. Active projects merge dozens of commits a week, so treat a report as a snapshot of that commit, not a standing guarantee, and re-check the repository before installing anything on a machine you care about.
- Which of these should I start with?
- To run a model on your own computer, install Ollama and add Open WebUI for a chat interface. For images and video, ComfyUI. To build an app or agent without much code, Dify. To let an agent write code or use a browser, OpenHands, Codex or browser-use. If you already use Claude Code or Codex, cost-xray shows what each session actually costs.