Aspects: Aspects (with orb, exactness, applying/separating) for a moment, or for any longitudes you supply.
Panchang: Tithi, vara, nakshatra, yoga, karana with the exact time each ends, plus sunrise and sunset.
Western natal chart: Complete natal chart: planets in signs and houses, ascendant, MC, 11 house systems, aspects, summary.
Nakshatras: Sidereal nakshatra, pada and lord of every graha; janma nakshatra with gana, yoni, nadi, varna.
Fetch any public URL and return its content as base64 with the content type and a ready-to-use data URI. Embed images, PDFs and files directly in LLM and API calls witho…
Locate a pattern image inside a larger image even when it is scaled, rotated or viewed at an angle: ORB or SIFT feature matching plus cv2.findHomography with RANSAC. Ret…
Extract clean readable webpage text from a public URL, removing boilerplate for LLM-ready research or RAG ingestion.
Translate text to any language with local AI (Qwen3-4B), preserving formatting, names and numbers; detects the source language.
Structured data extraction with local AI: give a text and a list of field names, get a JSON object with those fields (null when absent).
Language detection with local AI: ISO 639-1 code, language name, confidence and any mixed languages.
Zero-shot text classification with local AI: pick the best label (or several) from your own list, with confidence and reason.
Loan or mortgage with French amortization (fixed installment): monthly payment, total paid, total interest, approximate APR (TAE) including fees, and a yearly or monthly…
Count the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100k for GPT-4/3.5) plus estimates for Claude, Llama and Gemini, with characters per token.…
Read a website's /llms.txt (the standard that tells LLMs what a site is about) as structured data: title, summary, sections with links and descriptions, and whether llms…
Parse a site's robots.txt: whether a user-agent may crawl a path, which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot...) are blocked, and declar…
Split long text into overlapping chunks for RAG and embeddings, by characters, words or estimated tokens, keeping sentences or paragraphs whole, with each chunk's positi…
Clinical trials on ClinicalTrials.gov by disease, drug or sponsor: title, NCT id, status, phase, conditions, interventions, sponsor, dates, enrollment and countries; rec…
Detect which email service a domain uses (Google Workspace, Microsoft 365, Zoho, Proton, OVH, IONOS...) from its MX and SPF records, plus corporate spam filters and othe…
Read a website's /llms.txt (the standard that tells LLMs what a site is about) as structured data: title, summary, sections with links and descriptions, and whether llms…
Count the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100k for GPT-4/3.5) plus estimates for Claude, Llama and Gemini, with characters per token.…
Redact personal data from text without AI: emails, phone numbers, IBANs, card numbers (Luhn-checked), Spanish DNI/NIE, IPs, crypto addresses and URLs, replaced by labels…
Live status of widely used cloud services and APIs (GitHub, Cloudflare, OpenAI, Anthropic, Discord, Vercel, npm, Twilio, DigitalOcean, Coinbase, Atlassian, Netlify, Supa…
Split long text into overlapping chunks for RAG and embeddings, by characters, words or estimated tokens, keeping sentences or paragraphs whole, with each chunk's positi…
Social media profiles of a company or project from its website (X/Twitter, LinkedIn, Instagram, Facebook, YouTube, TikTok, GitHub, Telegram, Discord...) plus its contact…
