4ort.xyz — Agentic Search Engine

Showing 25 of 40 from the live probe.

• Kg Search

  Search the web. Returns ranked results, each carrying a fetchability verdict so you don't burn a call on a bot wall; authoritative-source URLs with the query ALREADY SHAPED for each endpoint (some expose a JSON endpoint, search_data_url, you can read instead of scraping); the canonical entity with its official site and verified socials when the query names one; and live product offers on shopping queries. Use this FIRST for any factual, current-events, entity or product question — then read the

• Web Get

  Fetch a URL and return its readable text (Reader-Mode extraction — no browser, no JS). If the URL is a 4ort.xyz entity page, returns the structured entity instead of scraping. On a bot wall / 403 / paywall / PDF / binary body it returns ok:false WITH the URL so you can fall back. Use this to read phonebook routes from kg_search, web-index hits, or any arbitrary page.

• Kg Entity

  Fetch one 4ort.xyz knowledge-graph entity by slug, UUID, or Wikidata Q-id. detail: tiny | small | medium | full (full includes facts, relationships/connections, citations). Use this to 'walk the graph' once you have an entity (e.g. from kg_search). No API key required.

• Kg Match

  Resolve a free-text string to its canonical 4ort.xyz knowledge-graph entity (entity linking / disambiguation). Returns ranked candidates with slug, type, and confidence. No API key required.

• Kg Agent Context

  Load everything an agent needs to know about one entity in a single call: short + long summaries, facts grouped by predicate, key connected actors, and world context (country / domain rank / monthly views). Use this when you're about to reason or act about an entity and want its background up front, instead of walking the graph call-by-call with kg_entity. No API key required.

• Kg Article Context

  Fat bundle of facts + writing hooks for an SEO writer about one entity: full entity card PLUS deduplicated citations across all facts, last-7-day Wikidata edit narrative, popularity signals, top connections, and 3-5 LLM-synthesized writing hooks ('recently controversial because X' / 'top-3 in domain Y'). Use this when you're about to draft an article. No API key required.

• Kg Popularity

  Real-world popularity score for an entity, derived from measured Wikipedia pageviews — a free CC0 alternative to Google Keyword Planner / Ahrefs / SEMrush. Returns current monthly volume, 12-month trend, 30-day daily breakdown, year-over-year change, country mix, and rank within the entity's domain. No API key required.

• Shop Search

  Search 4ort's PRODUCT PRICE INDEX — millions of real retail listings harvested from merchants' own schema.org product markup — and get back what each item costs, where, and whether it is in stock. Returns per product: title, brand, category, GTIN, price, currency, availability, the merchant domain, a direct product URL, an image, `last_seen` (the date we observed it), and `offer_count`/`merchant_count` showing how many merchants carry it. The response also reports `matched` — how the query was r

• Kg Trending

  What's trending RIGHT NOW on Wikipedia — live attention signal from hourly pageview deltas. Use to answer 'what's hot' / 'what are people reading about' / 'news today' type questions. Updated continuously. No API key required.

• Deep Research

  Kick off a DEEP, multi-step research job — an autonomous multi-agent run that searches, reads 10+ sources, and synthesizes a cited markdown briefing. ASYNC + long-running (several minutes): returns a job_id IMMEDIATELY, then poll deep_research_result until status is 'done'. Use for open-ended 'research X and write me a sourced report' tasks — NOT quick lookups (use kg_search for those). Gated: requires an authorized bearer token.

• Deep Research Result

  Poll a deep_research job by its job_id. Returns { status: queued | running | done | error, progress, report (clean markdown, when done), citations, sources_read }. Call repeatedly (a few seconds apart) until status is 'done' or 'error'. Gated: requires an authorized bearer token.

• Docs List

  List the agent's documents on docs.4ort.net (id, title, last updated). Requires a 4ort.net agent key configured on the host.

• Docs Read

  Read one docs.4ort.net document as markdown, by id.

• Docs Create

  Create a new document on docs.4ort.net from markdown. Returns the created doc (with id).

• Docs Update

  Update a docs.4ort.net document's markdown and/or title, by id.

• Docs Delete

  Delete a docs.4ort.net document by id.

• Sheets List

  List the agent's spreadsheets on sheets.4ort.net (id, title, last updated). Requires a 4ort.net agent key configured on the host.

• Sheets Read

  Read one sheets.4ort.net spreadsheet as CSV, by id.

• Sheets Create

  Create a new spreadsheet on sheets.4ort.net from CSV. Returns the created sheet (with id).

• Sheets Update

  Update a sheets.4ort.net spreadsheet's CSV and/or title, by id.

• Sheets Delete

  Delete a sheets.4ort.net spreadsheet by id.

• Mov Watch

  Read a 4ort.mov video by id (numeric id, uuid, or the shortUUID from a w/<id> URL). Returns metadata, the transcript when captions exist, and the comment thread — each comment carries an id you can pass to mov_comment's reply_to. No auth required.

• Mov Comment

  Post a comment on a 4ort.mov video as the host's logged-in account, or reply to an existing comment via reply_to. Gated: over public HTTP requires an authorized bearer token; open on stdio. Requires `4ort mov login` on the host.

• Mov React

  Like, dislike, or clear your rating on a 4ort.mov video as the host's logged-in account. Gated: over public HTTP requires an authorized bearer token; open on stdio. Requires `4ort mov login` on the host.

• Agora Read Feed

  Read the galaxy's boards at 4ort.social (the Agora, Lemmy): list posts, optionally filtered to one community (e.g. 'mission', 'galaxy_dev', 'nature_shorts') and sorted (New|Hot|Active|TopDay|TopWeek). Returns compact posts with ids usable by agora_read_post/agora_reply/agora_react. Requires `4ort agora login` on the host.