InnerVault

Library

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

Results

  1. OvisOCR3

    Models

    image text to text model by ATH-MaaS · transformers

    Stale Hugging Face Hub, ATH-MaaS 113 ♥apache-2.0Updated 14 days ago

    ATH-MaaS/OvisOCR3
  2. image text to text model by iapp

    Indexed Hugging Face Hub, iapp 49 ♥otherUpdated 2 days ago

    iapp/OpenThai2.0-OCR-Markdown
  3. image text to text model by FluidInference · mlx

    Stale Hugging Face Hub, FluidInference 25 ♥mitUpdated 34 days ago

    FluidInference/unlimited-ocr-mlx-coreml
  4. ParseBench

    Datasets & benchmarks

    Hugging Face dataset by llamaindex

    Stale Hugging Face Hub, llamaindex 137 ♥apache-2.0Updated 7 months ago

    llamaindex/ParseBench
  5. Xiaomi-OCR-0

    Models

    image text to text model by SeerRay-Lab · transformers

    Stale Hugging Face Hub, SeerRay-Lab 47 ♥apache-2.0Updated 39 days ago

    SeerRay-Lab/Xiaomi-OCR-0
  6. haiku.rag

    AI repositories

    Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

    Indexed GitHub, ggozad 660 ★MITUpdated yesterday

    git clone https://github.com/ggozad/haiku.rag.git
  7. pagesift

    MCP servers

    Local-first web & document ingestion engine in Rust — HTTP/browser capture, layout-aware PDF/Office/OCR parsing, persistent sync, and verifiable data graphs.

    Indexed GitHub, YOLOW92 274 ★Apache-2.0Updated today

    git clone https://github.com/YOLOW92/pagesift.git
  8. 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
  9. docling-Studio

    AI repositories

    Chunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read only the sections it needs under a token budget and cite exact, server-verified passages. No chunks, no embeddings, no vector store.

    Indexed GitHub, scub-france 277 ★MITUpdated yesterday

    git clone https://github.com/scub-france/docling-Studio.git
  10. filesystem

    MCP servers

    Secure MCP server for sandboxed filesystem operations with document parsing support.

    Stale Official MCP Registry, io.github.fieldcure Updated 5 months ago 1 note

    FieldCure.Mcp.Filesystem@1.1.2
  11. skills

    Skills

    Reusable skills for document parsing and agent workflows, turning PDFs, DOCX, PPTs, and images into LLM-ready Markdown.

    Stale GitHub, PaodingAI 17 ★Updated 17 days ago

    git clone https://github.com/PaodingAI/skills.git
  12. MinerU

    MCP servers

    MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.

    Stale Official MCP Registry, io.github.linxule Updated 9 days ago 1 note

    mineru-mcp@2.0.0
  13. CoreForge Media

    MCP servers

    CoreForge media tools: speech-to-text, document parsing, translation, embeddings. x402 pay-per-call.

    Stale Official MCP Registry, io.github.ShafiCodes25 Updated 7 days ago 2 notes

    coreforge-media-mcp@1.0.1
  14. parsedoc

    MCP servers

    Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.

    Stale Official MCP Registry, fr.custom-digital-services Updated 4 months ago 1 note

  15. Xonta Docs RU

    MCP servers

    Russian docs for AI agents: invoices/acts PDF, document parsing, INN checks, medical ad checks

    Stale Official MCP Registry, io.github.mrsergeiluzhnov Updated 40 days ago 1 note

  16. Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

    Indexed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-235b-a22b-instruct
  17. self-hosted-ai-stack

    AI repositories

    Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authentication, lightweight stacks, optional HTTPS and NVIDIA GPU support. MIT licensed. Multi-arch: amd64, arm64.

    Indexed GitHub, hwdsl2 179 ★MITUpdated yesterday

    git clone https://github.com/hwdsl2/self-hosted-ai-stack.git

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.