One to ten exact public HTTP(S) index/resource pages on default ports. Omission uses the GNU license index. No crawl, login or document bodies. Duplicate input pages are fetched once.

Type:string[]

Min. items:1

Max. items:10

Default:

[
  "https://www.gnu.org/licenses/"
]

Maximum candidate rows

maxCandidates

Optional

Retain at most this many distinct document-link targets across the page list; a lower event budget reduces the limit. Queries stay distinct.

Type:integer

Minimum:1

Maximum:200

Default:100

Maximum metadata checks

verifyMaxCandidates

Optional

Zero leaves all candidates as hints. A positive value performs up to 20 HEAD-only checks, with no GET fallback or document body reads. Requires verificationHosts.

Type:integer

Minimum:0

Maximum:20

Default:0

Explicit verification hosts

verificationHosts

Optional

Exact lowercase hostnames selected from pageUrls, for example www.gnu.org. Empty blocks all verification. No implicit subdomains or external-host checks. Verification redirects must remain on the candidate host.

Type:string[]

Max. items:10

Default:

[]

Elite Document Ocr Lite

thepattyroller/elite-document-ocr-lite

Basic document text extraction and processing. Extract text from documents, analyze document structure, and extract structured data from invoices and receipts. Perfect for document automation workflows.

Logan Kiser

Document Intelligence Extractor

incomeenginelabs/document-intelligence-extractor

Extract structured intelligence from document text for AI, RAG and automation workflows. Detect document type, dates, money, emails, phone numbers, URLs, headings, named-entity candidates, statistics and possible PII. Returns machine-readable JSON.

James Holzer

Ai Document Qa

vivid_astronaut/ai-document-qa

BRAINIALL Team

PDF & Document to Markdown - PDF, DOCX & HTML for LLMs

entranced_gelato/ai-document-reader

Turn any PDF, DOCX, TXT, or HTML document into clean, LLM-ready text + Markdown with metadata (title, pages, word count) and an optional AI summary. The document counterpart to a web reader — built for RAG ingestion, document Q&A, and AI agents (LangChain, LlamaIndex). Fast, structured, single-call.

AIDevs

Ai Legal Document Analyzer

vivid_astronaut/ai-legal-document-analyzer

BRAINIALL Team

PWA Install Readiness and Manifest Asset Gate

kingii98/pwa-install-readiness-and-manifest-asset-gate

Reads the manifest link from the HTML head of each origin, reads the web app manifest, then verifies every declared icon, screenshot and shortcut icon with one HEAD and one ranged GET. It reports the true pixel size read from the file header against the d

kingii98

Federal Register Scraper

parseforge/federal-register-regulatory-notices-rules-scraper

Scrapes Federal Register documents by keyword, agency, date range, document type, or significance. Returns each document as a flat row with full text and metadata.

ParseForge

Scribd Document Search Scraper

solidcode/scribd-scraper

[💰 $3.5 / 1K] Search Scribd by keyword and export structured metadata for every matching document — title, author, type, page count, ratings, views, language, categories, and direct reader and download links. One tidy row per document, many keywords per run.