Web & Data

Unverified public-channel chatter for one topic (?topic=), posted in the last 48 hours. Returns every raw message with its platform, source URL and timestamp, plus a grey_ref you can recompute as sha256(url + NUL + ts + NUL + text), and an LLM trend summary with an echo-chamber concentration index. NOT official fact and NOT a forecast; the summary is not offline-reproducible - only the per-item grey_ref is. Nothing posted in the window -> 422 no_charge, not billed.

For site owners auditing AI readability: returns the clean markdown an LLM extracts from your page after nav, ads, and scripts are stripped. See what survives for AEO, GEO and AI search; respects robots.txt

Curated compilations of Telegram channels: ready-made lists by theme for discovery and research.

Facebook Ad Library search by keyword — every live and recent ad matching a search term across all advertisers on Facebook, Instagram, Messenger and Threads. Returns the full ad creative (headline, body copy, CTA button + destination link, image and video URLs), the advertiser, run dates and days-running, and platform mix. Commercial and political ads, no Meta API or login. Competitor ad intelligence, ad spy, and creative research for AI agents.

Keyless attested web scrape: ?url= → { title, markdown, word_count }. $0.02 Base USDC (agent scrape band).

Skim Signal: AI/tech news — high-signal Hacker News stories, fresh arXiv AI papers, and official vendor announcements as structured items (title, excerpt, source, link). Refreshed on a 10-minute cycle; poll as often as you like.

Search granted US patents from the USPTO Open Data Portal by keyword: invention title, assignee company, inventor name, patent number, or technology area. Returns patent number, title, grant date, filing date, assignee, inventors, USPC classification and a provenance URL per match. For prior art checks, freedom to operate research, competitor IP monitoring, and patent portfolio lookup.

Debarment and exclusion screening, not just sanctions: 291,000+ parties on 11 authorities in one call. SAM.gov federal exclusions, HHS OIG healthcare exclusions, World Bank debarment, Federal Reserve enforcement, OFAC SDN and Consolidated, EU, UK, UN, Trade.gov CSL, FBI Wanted. Provable negative: NO_MATCH only when the complete candidate set on all 11 lists was examined, otherwise INCOMPLETE_SCREEN. sha256 receipt. KYB, vendor onboarding, AML, KYC.

Current wall-clock time for any IANA timezone, resolved live by timeapi.io (IANA tz database, includes DST rules). Query: ?tz=Europe/Paris (or America/New_York, Asia/Tokyo...). Returns ISO datetime, date, time, day_of_week and dst_active flag. Served with a 60s cache.

Schema-driven extraction: fill YOUR JSON schema from any URL. Hybrid LLM + deterministic canonicalization. 0.02/call.

Screen a name against the five official sanctions lists (EU, US OFAC SDN, UN, UK FCDO, French asset freezes) from a snapshot refreshed daily, with per-list dates. Query: name=NAME (optional threshold=0.6-1.0, lists=eu,ofac,un,uk,fr). Returns scored matches with entity type and programs, and a verdict: match, possible_match or no_match.

Returns computed results and answers to queries processed through a computational knowledge engine.

Returns a list of nearby locations based on geographic search parameters.

Retrieves photos associated with a specific location.

Provides simplified computational answers and mathematical results for queries.

[3-LEG+CHATTER] A full three-leg regional bundle with per-leg proof, PLUS the unverified public-channel chatter for a topic from the last 48h - two separate top-level keys, never merged. The unverified half is stored apart with an update-forbidding trigger and is not part of any official hash, so the authoritative half stays offline-recomputable. Nothing posted in the window -> 422 no_charge, not billed (check GET /shadow/catalog first, free).

Identifies and detects personally identifiable information within provided data or text.

获取任意位置的天气

Normalized income statements. Invalid or unsupported tickers return upstream 400/404; check /api/company/facts/tickers or endpoint-specific /tickers lists before batching.

Extracted item-level text from a specific filing (e.g., 10-K Item 1A Risk Factors).

Recent articles. With ticker: company news. Without: market news.

Dataset metadata for this Japanese (JP) corporate-number API — how many corporations are loaded and which prefectures are covered.

Get investment funds with raised amount, dates, and manager context.

Turn messy text — or any URL's page content — into structured JSON matching the shape you ask for, so an agent can consume a web page as data instead of prose