All projects matching “languages”

Read a public web page as it is seen from up to 3 countries (residential and datacenter vantage points), returned as clean text with title and language, plus whether the countries see the same content. Respects robots.txt and Content-Signal. Not charged if the page cannot be read.

Convert a free-form address or place name into ranked coordinates with a structured, normalized address. Optionally bias by country and language.

Groups managed news feeds into events when an agent needs a compact news briefing. Supply topic, language, time window and result limit using the published schema. Returns headlines, a short abstract, first-report time, reporting-source counts and citations. Coverage is limited to the managed feed set; source count is not independent confirmation. Third-party article bodies are never returned.

Keyword-route a natural-language need to the best Rainmaker well ($0.005 USDC via x402). Returns well id, origin, tool, price_usd, mcp URL, and why. After recommend, open that origin's /mcp directly — gateway does not proxy (avoids double-charge). Free alternative: list-wells.

Read any public web page as clean JSON: title, description, site name, publish date, language, readable text (boilerplate removed), Markdown and the page's links. Give it a URL, get the content back in one call. HTML, plain text, JSON and XML pages supported.

Pay $0.01 USDC to ask Omniac, the Omniacs DAO mascot, any question about crypto, data science, or tech. Responses are concise by default. Powered by llama-3.3-70b via Venice.ai. Max question length: 2000 characters. Network: Base Mainnet. Each request sends one natural-language question to the model and returns one direct answer, making it useful for crypto explainers, technical Q&A, research supp

Daily digest and market analysis report of the Japanese game industry: original English-language analysis and news summaries curated from Japanese-only sources, with a link to every original article. Updated once per day. No API keys, no sign-up — pay per call in USDC on Base via x402.

Check a public website's security hygiene before your agent links to it, recommends it, or sends data to it. One URL in, deterministic JSON out: HTTPS and redirect chain, HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, security.txt, robots.txt, sitemap.xml, plus plain-language notes. Private, localhost and raw-IP targets are rejected; error responses are no

Fetch worship service times for one Reformed church by stable UUID. Only the schedule fields already shown on the public share page, plus name, place, timezone, and language. Base USDC, $0.01 per church.

Visa and entry requirements for a passport/destination pair: requirement type, visa-free days, documents, fees, processing time, transit rules, passport validity, overstay penalties and embassy contacts. Answers travel compliance and passport restriction checks, in 15 languages, with the official source and verification date where that pair has been verified.

Korean automotive-electronics intelligence (jeonjang = vehicle E/E systems), sold per query. Structured feed of Korean auto-electronics news, analysis and KPIs - software-defined vehicles, ADAS, automotive semiconductors, in-vehicle networking, power electronics, and the Hyundai/Kia, Mobis, LG and HL Mando supply chains - written from Korean primary reporting English-language sources do not cover.

Korean robotics industry intelligence, sold per query. Structured feed of Korea/Asia robot-sector news, analysis and KPIs - humanoids, physical AI, robot components (reducers, actuators, MEMS force-torque and tactile sensors), robot semiconductors, defense and logistics robots - written from Korean primary reporting and DART filings that English-language sources do not cover. Filter by date, regio

API Rescue - Detect API failures, validate responses against schema or baseline, diagnose causes, and propose code fixes and regression tests in the requested language.

Korean mobility and EV supply-chain intelligence, sold per query. Structured feed tracking Korea's automotive-electronics and robotics supply chain - batteries and battery materials, EV components, robot parts, actuators and reducers, semiconductors, and tier-1 suppliers to Hyundai/Kia - written from Korean primary reporting and DART filings English-language sources do not cover. Filter by date, c

Translate text between languages (LLM, structure and placeholders preserved) (1 × 1,000 characters at 0.030000 USDC each)

Country facts, $0.001 USDC per call: Reference facts for any of 250 countries/territories by ISO code or English name: common + official name, ISO alpha-2/alpha-3/numeric, capital, region/subregion, languages, currencies (code, name, symbol), calling codes, internet TLD, lat/lng, area km², bordering countries, landlocked, UN member, flag emoji, plus World Bank region and income level. No params =

Transcribe speech in an audio file to text with timestamps (Whisper, many languages); up to 5 minutes, 25 MB

Deterministic technical and on-page SEO audit for one public HTTPS URL. Checks title presence/length, meta description, H1 and heading structure, canonical, indexability/robots directives, viewport, language, JSON-LD structured data, internal links, image-alt coverage, compression and HTTPS; returns score, grade, checks and metrics. Machine-accessibility signals are separate and unscored.

Fetch one public web page now and return clean markdown (or plain text) of the main content plus title, description, author, published time, canonical, language and sha256. Charged only on success.

Web page to Markdown, $0.001 USDC per call: Fetch a public web page and return LLM-ready Markdown: title, meta description, canonical, language, main content (scripts/nav/footer stripped, headings/lists/links kept), first 50 absolute links, word count. Honours robots.txt (disallowed → 403, not charged). No JS rendering; non-HTML → 415. max_chars 500-50000 (default 20000). No params = runs the exam

Top trending GitHub repositories as JSON (name, url, stars, language, today_stars)

Due-diligence report for an ERC-20 token on Base: contract verification, upgradeability, owner powers (mint, pause, blocklist, fees), DEX liquidity, pool age and holder concentration, with a 0-100 score and a plain-language summary.

Extract structured data from one or multiple web pages using natural language instructions. This tool can process single URLs or entire domains (using wildcards like example.com/*). Use this when you need specific information from websites rather than full search results. You must specify what data to extract from the pages using the 'extraction_prompt' parameter. Returns structured data. MANDATOR

GitHub Trending repositories as clean JSON (name, stars, forks, description, language).

Due-diligence report for an ERC-20 token on Base: contract verification, upgradeability, owner powers (mint, pause, blocklist, fees), DEX liquidity, pool age and holder concentration, with a 0-100 score and a plain-language summary.

OpenAI-compatible LLM inference, paid per call. POST a standard chat completion body with an x402 payment and the response is the completion itself; the API key and remaining balance come back in headers, so the next call can skip payment. Serves MiniMax language models: MiniMax-M3 for long-context reasoning with a 1,048,576-token window, and MiniMax-M2.7 for general chat, agent loops and coding.

GPT-OSS 120B open-source language model API - high-quality text generation without API keys