Web & Data

Capture a citable snapshot of a public web page: final URL after redirects, HTTP status, timestamp, security headers, extracted text, and SHA-256 hashes of both the raw response and the text. Deterministic and reproducible — no model involved, nothing generated. Use it to prove what a page said at a point in time, or to detect whether content actually changed.

Turn tabular text — pasted tables, statements, reports, CSV-ish fragments — into clean JSON rows with consistent column names. Handles ragged formatting that regex-based parsers break on. The cloud equivalent for table extraction bills around $15 per 1,000 pages.

Convert any public web page into clean, LLM-ready Markdown with the navigation, scripts and boilerplate stripped. Pay per call with no account, no subscription and no monthly minimum — useful for agents that need a handful of pages rather than a scraping plan. Obeys robots.txt and fetches logged-out public pages only.

Extract structured JSON from unstructured text against a JSON Schema you supply. Returns data conforming to your schema, or nulls where the text does not contain a field. Runs on dedicated local hardware — no per-token cloud billing. Typical alternative: $15-30 per 1,000 pages.

Fetch a public web page and return structured JSON matching a JSON Schema you supply. Combines retrieval and extraction in one paid call, so an agent does not need a separate scraping subscription. Obeys robots.txt and fetches logged-out public pages only.

Email validation — Syntax check + live MX/deliverability + disposable-domain flag.

DNS lookup — Resolve DNS records via DNS-over-HTTPS.

robots.txt / llms.txt — Fetch and parse a site's robots.txt and llms.txt.

Fetch Wayfair product details by SKU.

Search Yelp businesses by query and location.

Search Wayfair products.

View the roadmap

SYNTHORA sanctions-screen: sanctions screening with MATCH / CLEAR verdict over 4 official downloads (OFAC SDN primary and alias lists, UN, OpenSanctions). Multilingual, tested on Cyrillic transliterations.

Screen a person/company/vessel name against OFAC (SDN + Consolidated), UN, EU, UK, Canada, Australia, France, Switzerland, US export-control (BIS/State), and US SAM procurement/benefit exclusions. Deterministic typo-tolerant fuzzy matching with versioned list snapshots.

SYNTHORA fed-watch: US reference-rate funding pulse — SOFR/EFFR/TGCR/BGCR/OBFR with volumes, percentile dispersion and the SOFR-EFFR spread (the funding-stress signal before it hits the news). Cross-check of 5 independent official NY Fed series. The input for Fed/CPI prediction markets. Free official source, no key. $0.01 USDC x402 Base.

text-metrics: Returns character count, word count, and average word length for any given string.

Location-relevant mobility option finder for transit-aware trip planning. Returns a short list of provider matches and the next paid planning call to make.

Convert a web page (by URL) or raw HTML into clean, readable Markdown plus structured metadata (title, description, Open Graph tags, canonical URL, language). Strips scripts, styles and boilerplate tags; preserves headings, links, images, lists, code blocks and tables. Built for agents that need web content as LLM-ready text. POST a JSON body like: {"url":"https://example.com/article"}

Extracts URLs from a specified domain.

Dark web intelligence from Telegram: marketplace listings, forum chatter, access broker posts, credential shops, Tor site activity. Filters: severity, min_confidence, since, tag, sector, country, organization, limit, offset.

Harvests the curated feed set for one topic and language, groups the headlines into events and returns one entry per event. The source count is the product: ten outlets on one story is a different signal than one. Never returns third party article bodies, only headline, own abstract and link.

Provide a maintained scope, UTC as_of time, and optional paging and history-window controls. Receive JSON of new grants, field changes, deadline risks, and award changes from stored Grants.gov snapshots, with official evidence links.

Agent researches a topic (web) and returns a concise, structured, cited brief. ?topic=. Pay-per-call in USDC on Base.

Any web URL -> clean LLM-ready markdown (title + main content, boilerplate stripped). The retrieval/RAG primitive for agents.