InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. html-to-markdown

    AI repositories

    Turn messy, real-world HTML into clean Markdown, from every major language.

    Indexed GitHub, xberg-io 887 ★MITUpdated 2 days ago

    git clone https://github.com/xberg-io/html-to-markdown.git
  2. xberg

    AI repositories

    The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.

    Indexed GitHub, xberg-io 9,590 ★MITUpdated yesterday

    git clone https://github.com/xberg-io/xberg.git
  3. Extract text from images using OCR. Tesseract-powered. x402 micropayment.

    Stale Official MCP Registry, io.github.Br0ski777 Updated 6 months ago 1 note

  4. pdf_oxide

    AI repositories

    The 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.

    Stale GitHub, yfedoseev 1,184 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/yfedoseev/pdf_oxide.git
  5. Extract local PDF text with page-level paragraphs and English/German OCR fallback.

    Stale Official MCP Registry, io.github.Prashant2204 Updated 13 days ago 1 note

    pdf-text-extractor-mcp@0.1.1
  6. PDF Text Extractor

    MCP servers

    Extract text, pages and metadata from PDFs in bulk, with OCR for scanned files.

    Stale Official MCP Registry, io.github.fernandoguiraud16-coder Updated 41 days ago 1 note

  7. Read the text of any public PDF, page by page, plus page count and metadata. Free, no key.

    Stale Official MCP Registry, com.faceabot Updated 26 days ago 1 note

  8. PDF Text Extractor

    MCP servers

    Text from PDF links, OCR for scanned pages. One flat row per URL, never null. Billed on success.

    Stale Official MCP Registry, io.github.sumitrmardy Updated 25 days ago 1 note

  9. Extract text, Markdown and metadata from PDF URLs or uploads via Apify, per document or per page.

    Stale Official MCP Registry, com.ctriolab Updated 6 days ago 1 note

  10. x402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.

    Stale Official MCP Registry, io.github.industrial-platform-ai Updated 47 days ago 1 note

  11. Extract text, tables and RAG chunks from public PDF URLs; pay-per-event via your Apify account.

    Stale Official MCP Registry, io.github.truhojunbot-tech Updated 39 days ago 1 note

  12. trafilatura

    AI repositories

    Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

    Indexed GitHub, adbar 7,128 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/adbar/trafilatura.git
  13. Read printed words from receipts, forms and book pages, then export them as JSON, CSV or Excel.

    Stale Official MCP Registry, io.github.bepolabs Updated 4 days ago 1 note

  14. MinerU-HTML

    AI repositories

    MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

    Stale GitHub, opendatalab 299 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/opendatalab/MinerU-HTML.git
  15. PDF to Markdown and PDF to text from PDF URLs, page by page, with OCR for scanned pages

    Stale Official MCP Registry, io.github.kriton-dev Updated 14 days ago 1 note

  16. oxidizePdf

    AI repositories

    Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.

    Indexed GitHub, bzsanti 193 ★MITUpdated 3 days ago

    git clone https://github.com/bzsanti/oxidizePdf.git
  17. cjkfold

    AI repositories

    Fold look-alike CJK glyphs (Kangxi radicals, CJK radical supplements) so text extracted from PDFs matches again.

    Stale GitHub, cdcailf 164 ★MITUpdated 32 days ago

    git clone https://github.com/cdcailf/cjkfold.git
  18. office_oxide

    AI repositories

    The 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.

    Stale GitHub, yfedoseev 163 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/yfedoseev/office_oxide.git
  19. all2md

    MCP servers

    Convert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.

    Indexed GitHub, thomas-villani 35 ★MITUpdated today

    git clone https://github.com/thomas-villani/all2md.git
  20. OCR.Space

    Public APIs

    OCR text extraction from images and PDFs with a free tier

    Indexed public-apis (GitHub list)

  21. df0

    AI repositories

    DF-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

    Indexed GitHub, df0-io 119 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/df0-io/df0.git
  22. mcp-file-processor

    MCP servers

    Text extraction, keyword extraction, language detection, and chunking for RAG

    Stale Official MCP Registry, io.github.IntelagentStudios Updated 8 months ago 1 note

    @intelagent/mcp-file-processor@0.1.1
  23. mcp-file-processor

    MCP servers

    Text extraction, keyword extraction, language detection, and chunking for RAG

    Stale Official MCP Registry, io.github.Opafex Updated 23 days ago 1 note

    @opafex/mcp-file-processor@0.1.1
  24. ocrspace-mcp

    MCP servers

    Run OCR.space: text extraction from image URLs via GET or POST.

    Stale Official MCP Registry, io.github.mrfentmen Updated 30 days ago 1 note

    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.