Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.

Install scanned agent skills from the Future Skills marketplace.

Danish statue models scanned by Geoffrey Marchal

Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.

DocumentVision is a node.js library for processing and understanding scanned documents

Agent runtime for faapi — LLM-driven ReAct loop over scanned agent / tool registries

DocumentVision is a node.js library for processing and understanding scanned documents

React Native Android module to interface with Zebra's DataWedge using Android Intents to control the barcode scanner and retrieve scanned data

This is a repository for the how-to-use documentation used in the Look Scanned project, built with [VitePress](https://vitepress.dev/).

OCR stdlib adapter for glove-working-environment. Turns a scanned PDF or a photo of a document into text inside the agent's virtual filesystem as env:ocr — bundled Tesseract WASM plus bundled English training data, so it works with no host wiring and no n

Enhanced read for pi – office docs (docx/pdf/pptx/xlsx etc.) via anydoc, header-only, OCR for scanned pages (Firecrawl or local rapidocr, in the order you configure).

Frame-start scanned, frozen InputSnapshot Resource (logical keyboard key and physical code held/press/release edges + mouse.position/movementDelta + mouse.button(0|1|2)) + browser PointerLock backend for forgeax-engine.

Node PDF is a set of tools that takes in PDF files and converts them to usable formats for data processing. The library supports both extracting text from searchable pdf files as well as performing OCR on pdfs which are just scanned images of text

Fill existing PDF forms — including scanned and flattened ones — from n8n data, using a layout you set up once at justfill.app

MCP server that searches the Internet Archive, the Library of Congress and data.bnf.fr at once, inside scanned text and across catalogues. No API key required.

Reads QR and Data Matrix codes from noisy DPM photos and returns the scanned text

A thin wrapper on top of Fastify — decorator-based routing, JWT auth, HMAC signature, JSON Schema validation, DB connection pooling, auto-scanned controllers.

A JavaScript library to apply image filtering effects. It can be used to enhance scanned documents images or photos.

Easily extract text from digital PDF files with coordinate and font size included, and optionally group text by lines or render scanned pdf to canvas/png.

A WASM build of scanners-and-such for handling advanced barcode scanner features and decoding scanned data.