Cynix Dev

Indexes the live OpenRouter model catalog into RAG-ready records with pricing, context, and capability flags. Detects new models and price changes between runs. Keyless, no proxy.

Monitor web pages for content changes. Diffs each run against the previous snapshot and emits structured change records with added/removed lines — ideal for price, job, docs, and competitor monitoring.

Map a therapeutic area, compound, or gene in one pull — pulling from the official US government and open biomedical APIs: FDA drug labels (openFDA), ClinicalTrials.gov studies, and MedlinePlus / NCBI Gene summaries.

Paste recipe URLs, get back just the recipe: ingredients, numbered steps, times, yield, nutrition, and rating as clean typed records. No ads, no popups, no 2,000-word childhood story before the ingredient list.

Search and extract SEC EDGAR filings: full-text search across all filings or company filing histories by CIK. Clean typed records with direct document URLs. No API key required.

Track recent SEC filings for any public company using the official, free EDGAR API. Filter by form type (Form D, insider Form 4, 13D, S-1, etc.) and a look-back window. Resolves tickers to CIKs automatically. No API key required.

Enrich a CPE/keyword across threat feeds in one run: NVD CVEs, CIRCL recent CVEs, and URLhaus malware.

Search Singapore's official ACRA business registry by company name or exact UEN. Get entity name, UEN, status (Registered/Deregistered), type, issue date and registered address as typed JSON rows. Covers 2.1M entities. No API key.

Extract job listings from MyCareersFuture.sg, Singapore's official government-backed jobs portal. Title, company (with UEN), salary range, location, category, skills, vacancies and posted date as typed JSON rows. No API key.

Scrape PropertyGuru Singapore property listings by location. Price, district, bedrooms, bathrooms, size (sqft), tenure and property type as clean JSON. Sale and rental modes. Playwright-based with residential proxy support.

Extract products, prices, variants, and inventory from ANY Shopify store via the public JSON API. No API key, no login.

Fetch Steam app details (price, genres, rating, description) and review summaries via the public Steamworks API. No API key.

Fetch newsletter posts (title, body, author, date) from any Substack publication via the public archive API. No API key.

Mine Trustpilot product reviews by name: title, star rating, body. Playwright + residential proxy. G2/Capterra are separate actors sharing the same output schema for easy union.

Search USPTO and global patents through Google Patents' free public index. Pull structured patent records by keyword, assignee, or inventor — title, abstract snippet, dates, inventors, assignee, and PDF link. No API key needed.

Scrape Vinted marketplace listings by search query. Obtains a session cookie from the homepage, then queries Vinted's keyless JSON catalog API and extracts title, price, brand, size, image, seller, and URL. Ideal for resale research, price monitoring, and inventory sourcing.

Crawl any website and turn its pages into clean, chunked, metadata-rich Markdown records ready for RAG pipelines, vector stores, and custom GPTs.

Crawl seed websites and extract contact details — emails, phone numbers, and social profiles (Instagram, X, LinkedIn, Facebook). Performs a light same-host crawl up to a per-domain page budget. Ideal for lead enrichment and outreach list building.

Extract structured knowledge from Wikidata — the free, open knowledge base. Search by term or fetch exact entities (Q-IDs) and get clean labels, descriptions, aliases, and a flattened claims map with human-readable property names. No API key required.

Search Wikipedia, fetch article summaries (extracts) or random articles across languages. Keyless, for RAG and reference data.

Query 14,000+ World Bank indicators across 200+ countries: GDP, inflation, trade, health, education, environment, governance, energy, and more.

Scrape X/Twitter tweets by tweet URL or username. Renders with Playwright through a residential proxy and extracts tweet text, permalink, and timestamp. Optional auth cookies for full timelines. Useful for social listening, trend tracking, and research.

FDA Drug Database Extractor: Orange Book (patents/exclusivity), NDC Directory, openFDA (adverse events, recalls, labeling), Drugs@FDA (approvals) — unified into one actor with typed records.

Upcoming, previous, and specific rocket launches from The Space Devs' Launch Library 2 API. Status, NET, rocket, provider, pad, location, mission, and orbit as typed records. No API key.