Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
html-to-markdown
AI repositoriesTurn messy, real-world HTML into clean Markdown, from every major language.
git clone https://github.com/xberg-io/html-to-markdown.git -
xberg
AI repositoriesThe fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
git clone https://github.com/xberg-io/xberg.git -
OCR Text Extraction API
MCP serversExtract text from images using OCR. Tesseract-powered. x402 micropayment.
-
pdf_oxide
AI repositoriesThe fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.
git clone https://github.com/yfedoseev/pdf_oxide.git -
PDF Text Extractor MCP
MCP serversExtract local PDF text with page-level paragraphs and English/German OCR fallback.
pdf-text-extractor-mcp@0.1.1 -
PDF Text Extractor
MCP serversExtract text, pages and metadata from PDFs in bulk, with OCR for scanned files.
-
Faceabot PDF text extractor
MCP serversRead the text of any public PDF, page by page, plus page count and metadata. Free, no key.
-
PDF Text Extractor
MCP serversText from PDF links, OCR for scanned pages. One flat row per URL, never null. Billed on success.
-
PDF Text Extractor (Ctrio Lab)
MCP serversExtract text, Markdown and metadata from PDF URLs or uploads via Apify, per document or per page.
-
PDF Text Extractor for AI Agents
MCP serversx402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.
-
PDF Text Extractor (Apify Actor)
MCP serversExtract text, tables and RAG chunks from public PDF URLs; pay-per-event via your Apify account.
-
trafilatura
AI repositoriesPython & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
git clone https://github.com/adbar/trafilatura.git -
Read printed words from receipts, forms and book pages, then export them as JSON, CSV or Excel.
-
MinerU-HTML
AI repositoriesMinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.
git clone https://github.com/opendatalab/MinerU-HTML.git -
PDF to Markdown and PDF to text from PDF URLs, page by page, with OCR for scanned pages
-
oxidizePdf
AI repositoriesPure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.
git clone https://github.com/bzsanti/oxidizePdf.git -
cjkfold
AI repositoriesFold look-alike CJK glyphs (Kangxi radicals, CJK radical supplements) so text extracted from PDFs matches again.
git clone https://github.com/cdcailf/cjkfold.git -
office_oxide
AI repositoriesThe fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.
git clone https://github.com/yfedoseev/office_oxide.git -
all2md
MCP serversConvert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.
git clone https://github.com/thomas-villani/all2md.git -
OCR.Space
Public APIsOCR text extraction from images and PDFs with a free tier
-
df0
AI repositoriesDF-0: Data processing Framework with Zero-overhead. Local-first C++20 data-processing infrastructure for deterministic, auditable, on-premise workflows. Supports 100+ formats, OCR, local AI, and opt-in cloud AI pipelines
git clone https://github.com/df0-io/df0.git -
mcp-file-processor
MCP serversText extraction, keyword extraction, language detection, and chunking for RAG
@intelagent/mcp-file-processor@0.1.1 -
mcp-file-processor
MCP serversText extraction, keyword extraction, language detection, and chunking for RAG
@opafex/mcp-file-processor@0.1.1 -
ocrspace-mcp
MCP serversRun OCR.space: text extraction from image URLs via GET or POST.
ocrspace-mcp@1.0.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.