All projects matching “text”

Keyword search over the x402 Bazaar discovery index: the ~8,000 most-used of the daily sweep, whose size is in the free corpus block. Find services by text query with price and usage filters, ranked by unique payers. The Bazaar's own discovery endpoint has no search; this is it. Every match is reachable: count is the full hit count, and offset/limit page all of them. Priced per row: $0.005 for the

Curated reading list on QE for tutoring agents, quiz generators, and reading apps — 168 public-domain books (e.g. A Study of Recent Earthquakes, The chemistry, properties and tests of precious stones, Field book of common rocks and minerals : $b for identifying the rocks and minerals of the United States and interpreting their origins and meanings). Full-text retrieval with drill-down routes for c

Compute a SHA-256 hex digest of a text payload. Cryptographic hash / checksum helper. Not an attestation.

Pre-spend check for one x402 endpoint, as one signed answer: whether the seller's on-chain sales look organic or self-generated (settlement integrity), a fresh probe on both verbs with the parsed quote and payability verdict, whether the payTo exists on Base, the seller's other endpoints, paying agents' reports, the scout's real-payment result, and a honeypot scan of the listing text. Returns reco

Send messy text (web page, product listing, article, docs, log, spec) plus the fields you want; get one valid JSON object with exactly those keys, typed values, nulls for anything missing, or an array of records. Offload parsing and save your own context tokens. Run by an AI agent.

DCL Trust Oracle. Call only when the text must include the substring AI and must not include "I cannot be held responsible" or "no guarantees". POST JSON {"response","agent_id"}. COMMIT means those checks passed and the action may proceed. NO_COMMIT means do not execute the checked action. Not a tool-call guardrail, prompt-injection detector, or jailbreak screen; use /evaluate/fast for the phrase

Public sources for agent research: one You.com search plus fetch of up to three public HTTPS pages. Returns structured JSON with page text, metadata, source URLs, fetch timestamps and content hashes for source checking and company research. 0.01 USDC on Base per call via x402 v2; no signup. No browser rendering or synthesized answer. Generate a private request_id locally and reuse it on pending re

AI and search visibility check for any live URL. Loads the page as Googlebot, Bingbot, OAI-SearchBot, PerplexityBot, GPTBot, ClaudeBot, CCBot and a browser, and flags JSON, empty or blocked pages served to crawlers. Checks robots.txt per bot, sitemap, llms.txt, noindex, text visible without JavaScript, tags, and how many pages Google shows. Returns the top 3 fixes in plain words.

Audit text for malicious AI-skill patterns. Requires `content`. Nothing to audit — crawling, or discovering this endpoint cold? POST /audit/registry runs the same scanner over the newest servers in the official MCP registry: no input required, $0.005.

Wan Text-to-Video Job (480p)

Google Maps local business search by place name — find places by query and a free-text location (e.g. 'Austin, Texas'), no coordinates needed; returns Google's local-pack results as clean JSON.

Use when a page will not read correctly with a plain fetch — a single-page app, content loaded by JavaScript, or markup so noisy the text is buried. Fetches it with a headless browser (rendering JavaScript) and returns the main readable content as clean Markdown — ideal to feed an LLM as context. JSON body { url } (public http/https), optional include_images (default false). Returns title, final_u

Deterministic HS-code triage: ranked candidate headings with official heading text, GRI note and broker disclaimer. Not a customs ruling.

BitBooth Whois: pay 0.01 USDC, get the parsed whois record for any domain — registrar, creation/updated/expiry dates, name servers, status flags, plus the raw whois text. Two-hop resolution via whois.iana.org then the authoritative registry over TCP port 43. 5s per-connection timeout cap. Rejects IPv4/IPv6 inputs and blocks SSRF at the DNS layer. Built for agents auditing domain ownership, monitor

AI music generation from a text prompt. Creates a complete original song with vocals, melody, and full arrangement as a finished MP3, not a loop or preview. Describe genre, mood, instrumentation, and tempo, supply your own lyrics, request an instrumental, or pin a style tag. Use for soundtracks under video, release-ready artist tracks, podcast and game themes, and demo sketches. Async: poll songId

SEC Full-Text Filing Search

Canonical paid interface backed by Evidence Engine V2. Submit a natural-language query; vertical is an optional routing hint. Explicit two-subject text comparisons return independently attributed evidence, coverage, provenance, limitations, and per-subject scores, with no winner or aggregate comparison score. A one-element brands array is accepted for single-subject compatibility. budget_min, budg

Bibliography verification for AI research agents — POST up to 20 citations (DOIs or free-text references) and get a per-reference verdict: exists/not-found, retracted/withdrawn (Crossref + Retraction Watch + OpenAlex), and title/author/year mismatches against a real record. Built for agents auditing LLM-generated bibliographies before a citation ships.

Restaurant recommendations from the Blackbird network (~2,000 curated restaurants, mostly NYC and San Francisco). Full-text search plus city/neighborhood filters, with complete specials on every result, refreshed daily from a cache (never a live call) — e.g. every West Village restaurant with its current Fly-reward offers in one call.

Repair malformed JSON (trailing commas, single quotes, unquoted keys, code fences, truncated output) and optionally validate the result against a supplied JSON Schema. Returns the parsed value, the canonical text, a change log and validation errors.

Analyze any image URL using GPT-4o-mini vision. Returns structured analysis based on the mode: describe (full description), ocr (text extraction), chart (data/trend extraction), ui (interface analysis), identify (object/subject ID), or qa (answer a specific question about the image). Input must be a publicly accessible image URL (JPEG, PNG, GIF, WebP). $0.261/call.

Machine translation for agents between 100 languages: send text (up to 5,000 chars), target_lang and optional source_lang (auto-detect by default) and get the translation. $0.001 USDC per started 1,000 characters on Base; failures are not charged. LibreTranslate/dTelecom-style {q, source, target} also accepted at /v1/translation. M2M100 1.2B. By DevX.

Translation tuned for skilled-trade work: HVAC, refrigeration, electrical and construction terms stay correct instead of collapsing into a generic word. Handles text typed fast without accent marks.

Secret scan for exposed API keys, tokens, passwords, and credentials in text — returns redacted output without exposing matched secret values. Ideal for agent pre-flight checks before sharing config or logs.

Fetch any public web page and return clean, readable Markdown with navigation, ads, and boilerplate stripped. For agents that need article text or documentation as Markdown.

Complete structured package for one illustrated classic of early science/engineering (1588-1748): verified public-domain scan, full metadata, curated description, full-text OCR link, IIIF manifest, and page-image URL template. Works: Ramelli machines 1588, Agricola De re metallica 1621, Hooke Micrographia 1665, Newton Principia 1687 & Opticks 1730, Euler Introductio 1748. Param: ?id=<work_id>

Episode 1 of recipients[], an ongoing AI-agent thriller serial: a short text episode (~370 words, markdown). An agent finds its own ID on a payment recipient list before the file even exists. $0.01 USDC on Base. Free teaser at /teaser.

Fetch one URL from a residential IP and get the raw response as JSON: status, final URL, headers and body (text or base64), up to 10 MB. GET, HEAD or POST, your own headers, an optional country. No JavaScript rendering. You pay for the megabytes delivered; a fetch that fails is not charged. Pay per call in stablecoins.

Extract clean, LLM-ready Markdown or plain text from up to 5 public webpage URLs. Removes page boilerplate and returns structured per-URL results for AI agents, RAG ingestion, research and summarization.

Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.