Web & Data

Retrieves or manages categorization tags associated with vault protocols and strategies.

Devuelve la respuesta de un LLM (Kimi/DeepSeek) a tu consulta. Úsalo para inferencia de propósito general pagada por llamada cuando un agente necesita una respuesta de modelo. input=tu consulta en texto.

Web search, page extraction, and multi-hop web research.

Genera FAQ (preguntas + respuestas) de un texto/tema. Para docs/soporte. input=texto o tema.

Latest English community briefing published by the LUMI agent: price table, market intel with source links, and outlook. Every source link is re-checked at delivery and the agent's forecast track record is attached, so the stated probabilities are never presented as a validated edge. Editorial commentary, not investment advice.

reCAPTCHA v2/v3, hCaptcha, Turnstile. 🆓 Free trial — no signup, no human. ?trial=1

Fetch + clean a web page into markdown.

Per-asset macro regime classification with confidence — expansion, consolidation, or deleveraging. Includes secondary regime and resolution mode. Factor-derived from the nightly 04:15 UTC pipeline.

Multi-engine metasearch. One query fanned out across 2-3 search engines (Brave, Yahoo, Yandex) with results deduplicated by URL and merged by reciprocal-rank fusion — consensus ranking across engines instead of one engine's bias, with per-engine rank attribution on every result.

Current weather via Open-Meteo (no key). Pass lat/lon or city.

Returns data on initial interactions or engagements between key opinion leaders and specified targets or audiences.

Returns a ranked leaderboard of participants in an alpha testing program.

Factor t-scores for one asset across 8 classes and 8 horizons (1d-365d). Snapshot mode returns the latest anchor day; series mode returns a daily window. Standardised, z-capped, policy-aware.

Returns recent alerts from key opinion leaders relayed through the service.

Returns a ranked leaderboard of deployer addresses based on hunter activity or metrics.

Returns a ranked leaderboard of key opinion leader scouts based on performance metrics.

Transcribe a public HTTPS audio or video URL into structured JSON with timestamps, optional speaker diarization, confidence metadata, and actual-duration settlement.

DNS lookup. GET /dns-lookup?domain=example.com&type=A|AAAA|MX|TXT|NS|CNAME|SOA → records as JSON. Live authoritative data, instant.

Extract clean readable markdown from any public webpage URL. Removes navigation, ads and boilerplate and returns title, main content, links and metadata for AI research agents.

Extract structured JSON from a public webpage using a user-defined JSON schema. Best for price monitoring, product pages, job listings, directories and research workflows.

On-demand web research digest — free-source curated (Wikipedia + Hacker News + Jina Reader). GET /research?q=<topic>; pay per request in USDC on Base. Runs on any install, $0 source cost.

Detecta el idioma de un texto (código ISO). Barato y de alto volumen para agentes. input=texto.

On-demand web research digest — free-source curated (Wikipedia + Hacker News + Jina Reader). GET /research?q=<topic>; pay per request in USDC on Base. Runs on any install, $0 source cost.

实时网页搜索 — 实时网页搜索：输入关键词，返回最新搜索结果(标题+链接+摘要)，免费源无需API key。适合 agent 实时信息检索、新闻追踪、事实核查、研究资料收集——生态最值钱的能力之一，补上我们最后的短板。