PDF Text Intake Auditor

Ranked MBA & EMBA Deadline Finder

trovevault/ranked-mba-emba-deadline-finder

Finds current MBA and EMBA application deadlines from official business school pages. Filter by region, country, and program type for applicant and admissions consulting workflows.

Dutch Energy Contract PDF Extractor

alkausari_mujahid/dutch-energy-contract-pdf-extractor

Extracts structured data from Dutch energy contract PDFs (direct PDF or Dropbox file/folder links): customer & address details, contract term, electricity/gas tariffs, totals, cashback. Supports Energiedirect.nl, Budget Energie, NLE, Essent, Huismerk Energie. Text PDFs only, no OCR.

Given a domain, finds sitemap.xml / sitemap_index.xml (also via robots.txt), recursively expands sitemap indexes, returns one row per discovered URL with lastmod / changefreq / priority. SEO audits, crawl-target prep, content cataloging. $0.0001/URL + $0.01 site fee.

SEC EDGAR Filings — 8-K Items Decoded

alaudinburki/sec-edgar-filings

Pull SEC filings for any US-listed company and get the meaning, not just the form code: 8-K items decoded into plain language, material events flagged (bankruptcy, exec change, acquisition, restatement), newest first. Free official SEC data, no key.

SDS/MSDS PDF Parser — 16 Sections & Changes

invincible_nova/sds-msds-pdf-parser

Convert English or German SDS/MSDS PDFs into 16-section JSON with page evidence, identifiers, warnings, OCR fallback, and optional revision comparison.

SEC EDGAR 8-K Material Events Scraper

jungle_synthesizer/sec-edgar-8k-material-events-scraper

Turn every 8-K into a structured record: reported Item numbers with SEC's own labels, narrative text per Item, and full exhibit text (EX-99 press releases, EX-10/EX-2 agreements). Boolean flags for cyber incidents, restatements, bankruptcy and more. Full historical backfill, not a live feed.

PDF to Markdown for LLMs and RAG (no file retention)

hushvert/pdf-to-markdown

Convert PDF to clean Markdown for LLM context windows, RAG ingestion, and agent pipelines. Keeps multi-column pages in true reading order. Privacy-first: inputs deleted the moment the conversion finishes, outputs within about an hour. Scanned PDFs fail loudly (no OCR); failed runs are never charged.

SEC 13F Holdings Scraper

parseforge/sec-13f-holdings-scraper

Scrape institutional investment holdings from SEC 13F filings by CIK or fund name. Returns each holding with issuer, CUSIP, shares, value, and put/call flags.

Google Gemini SynthID Text Watermark Tool

rainminer/google-gemini-watermark-checker

Paste text or upload PDF and DOCX to check whether writing is AI generated. Looks for Google SynthID-Text signals when the sample is long enough and returns isAiGenerated, confidence, likely source, and limitations as JSON. For editors, reviewers, and trust-and-safety teams. No Google login.

Document to JSON Extractor (Arabic and English)

omargnagy/document-to-json-extractor

PDF, DOCX, image or plain text in, structured JSON out, with the page and paragraph anchor for every value so a person can verify it. Arabic and English: Hijri dates, Arabic-Indic digits, right to left order and Arabic clause numbering all handled. Pass a JSON Schema to get exactly your fields.

Match ecommerce catalog items to safety documents, flag missing GPSR information, and screen products against official U.S. recall data.