Aggregated crypto news with sentiment: deduplicated headlines from many major crypto outlets (CoinDesk, Cointelegraph, Decrypt, Bitcoin Magazine, The Block, CryptoSlate), each scored bullish/bearish/neutral by a crypto-tuned lexicon, optionally filtered by coin or query. One call instead of polling a dozen feeds and running your own NLP.

Composite crypto market sentiment: the Fear & Greed index (value, classification, trend) blended with aggregated news-headline sentiment into one bullish/bearish/neutral score, optionally focused on a coin or query. Data by alternative.me (attributed) + curated RSS headlines.

Verify an EIP-191 personal_sign or EIP-712 typed-data signature and recover the signer address from public inputs (message + signature). Verification/recovery only — never signs.

Vulnerability intelligence for a single CVE id. Fuses NVD (CVSS base score and vector, CWE, patch links), CISA KEV known-exploited status, EPSS exploitation probability and OSV.dev affected and fixed versions into one cited JSON with a deterministic patch-priority score. Risk indicators, not advice.

Vulnerability scan for a software package by ecosystem, name and version, or by package-URL (purl). Queries OSV.dev for known advisories, collects their CVE ids and enriches them with NVD CVSS, CISA KEV and EPSS, then returns a prioritized list of advisories with exact fixed versions. Risk indicators, not advice.

Coverage density and deployment opportunity for a geography on a DePIN network. Give network (helium) and a geo string (city, state, country or an H3 cell). This is a keyed enrichment: without the Relay key configured it returns available false with a note; the keyless network, hotspot and wallet routes do not need it.

Profile of a DePIN hotspot or gateway from public data. Give network (helium) and an entity or asset key and get owner wallet, subnetworks (IOT, MOBILE), obfuscated location (city, state, country and H3 cell), elevation, gain, onboarding fee and computed flags for asserted location, multi-network and deployment completeness. Each value is cited to its source.

Network health and token-economics verdict for a DePIN network from public data. Give network (helium) and get coverage size (IOT and MOBILE node counts), token supply for HNT, IOT, MOBILE and DC read on-chain, the emission and halving context, and a coverage-scale indicator. Each value is cited to its source.

Reward economics and earnings trend for a DePIN entity or subnetwork. Give network (helium) with an entity key or a subnetwork (iot, mobile). This is a keyed enrichment: without the Relay key configured it returns available false with a note; the keyless network, hotspot and wallet routes do not need it.

Portfolio of a DePIN operator or investor wallet from public data. Give network (helium) and a Solana wallet pubkey and get the hotspot count, a breakdown by subnetwork, the geographic spread, token balances (HNT, IOT, MOBILE, DC) and computed signals for deployment diversification and concentration. Each value is cited.

Perpetual basis for an asset: the mark-versus-oracle premium on venues that publish a native mark price (Hyperliquid), in basis points, with a naive annualized carry proxy. Shows how far the perpetual trades from the underlying oracle — a froth and leverage-cost signal.

Perpetual-swap funding rates for an asset fused across decentralized venues (Hyperliquid, dYdX v4): each venue's current funding plus an open-interest weighted aggregate funding rate, annualized APR, the cross-venue spread and dispersion. One normalized call instead of polling each protocol and reconciling funding intervals yourself.

Open interest for a perpetual asset across decentralized venues (Hyperliquid, dYdX v4): per-venue open interest in coins and in USD notional (via each venue's mark or oracle price), the total aggregate USD open interest and each venue's share. One call, normalized across protocols.

Fusion positioning brief for a perpetual asset in ONE call: aggregate funding and APR, aggregate open interest, mark-vs-oracle basis, cross-venue funding spread, a funding-flip trend from Hyperliquid history, and a deterministic 0-100 squeeze/positioning score with a verdict and crowding direction. Saves several protocol calls plus the normalization and scoring.

GitHub repository health & intelligence for due-diligence / dependency choice: stars, forks, open issues, watchers, size, language, topics, license, archived/fork flags, and computed signals (days_since_push, age, issues_per_star, is_active). From the official GitHub REST API, normalized.

Hacker News engagement / dev-sentiment for a project or topic: story count, total & average points and comments, and the top stories (title/url/points/comments/date). From the keyless HN Algolia search API.

Package intelligence across npm / PyPI / crates: latest version, age, release cadence, deprecation/yank, license, and download stats (last day/week/month) with a rising/falling trend. Aggregates the official registry + downloads API + deps.dev.

Top GitHub repositories by language and/or topic (optionally newer than a date), ranked by stars/forks/recently-updated: name, full_name, stars, language, description, url, pushed_at. From the official GitHub Search API.

Adverse-event summary for a medical-device brand from the FDA MAUDE database. Returns counts of malfunctions, injuries and deaths by event type. Informational, not medical advice.

Recent DEX swap history + buy/sell flow for a token or pool on Base: per-swap trader/side/amount/price plus a summary (count, buy/sell volume, net flow, largest swaps), decoded by us from public Aerodrome/Uniswap-V3 Swap event logs.

Trending Base DEX pools ranked by recent swap volume and net buy/sell flow over a short window, computed by us from public Aerodrome/Uniswap-V3 Swap event logs.

Version-delta changelog for a library between two versions. Give an ecosystem, package name and from_version and to_version and get the GitHub release notes in that range, the registry versions between them, and surfaced breaking-change markers. Built for agents deciding whether an upgrade is safe.

Up-to-date, version-pinned documentation for a library or API, for coding agents. Give an ecosystem and a package name (optional version and topic) and get a compact doc slice: package identity (latest and requested version, license, repo, homepage and doc URLs, version list) plus the README or llms.txt section matching the topic, each with a provenance citation. Keyless PyPI, npm, crates and GitHub sources.

Working code snippets for a library, matched to a topic. Give an ecosystem, package name and a topic or symbol and get the fenced code blocks from the README or docs whose language, code or nearest heading matches, each with a source citation and an honest truncated flag. Ideal for grounding a coding agent in real usage examples.

Phishing/trust verdict for a website domain before an agent transacts with an unfamiliar merchant. Fuses registration age (RDAP), DNS/mail posture (SPF, DMARC, DNSSEC), TLS validity, Certificate Transparency history and a typosquat/homoglyph analysis into a composite trust score 0-100, a category (trusted / caution / untrusted / unknown), per-dimension flags and reasons. Trust indicators, not a guarantee.

Pure-compute typosquat and homoglyph check on a hostname: edit-distance to a curated brand list, look-alike character normalization, brand-in-subdomain lures, punycode/IDN, abused free-hosting suffixes and throwaway TLDs. Returns is_typosquat plus the nearest brand, edit distance and reasons. No network — instant, cheap.

Adverse-event summary for a drug from the FDA FAERS database by name. Returns the top reported reactions, the serious and death-flagged fractions and a demographic breakdown as aggregate counts. Informational, not medical advice.

Drug-interactions label section for a drug by name, with an optional check of whether the label mentions a second drug. A label-text heuristic, informational, not medical advice.

Key FDA structured-product-label sections for a drug by name: boxed warning, indications, dosing, contraindications, warnings, drug interactions and pregnancy. Informational, not medical advice.

Clinical safety profile for a drug by brand, generic or active-ingredient name or NDC. Fuses FDA identity and approval status, key label sections, an adverse-event summary and a deterministic severity indicator into one cited JSON. Informational, not medical advice.

Current FDA drug-shortage records for a generic drug name: status, therapeutic category, dosage form, company and dates. Informational, not medical advice.

Cited time-series for a single financial line-item from SEC EDGAR XBRL. Give a ticker or CIK plus a concept (a canonical name like revenue or netIncome, or a raw us-gaap tag) and get the normalized period values, each cited to its filing. Cheap granular pull.

Normalized company financials from SEC EDGAR XBRL filings. Give a ticker or CIK and get income statement, balance sheet and cash flow lines mapped to one clean schema, each value cited to its real XBRL tag and filing. Compact cited JSON instead of megabytes of raw XBRL.

Key financial ratios computed from SEC EDGAR XBRL: margins, liquidity, leverage and growth. Give a ticker or CIK and get ratios over recent periods, each computed number citing the source facts it was derived from, plus restatement flags and simple anomaly flags.

Check whether an accrediting agency is recognized by the US Department of Education. Give an accreditor name and get back a recognized flag plus the matched agency, its type (institutional or programmatic), Title IV gatekeeper status, active status and recognition year. The direct fake-accreditor test.

Screen a US college or university name against the federal DAPIP database: fuzzy name search returning ranked institution candidates, each with its DAPIP id, OPEID, IPEDS unit id, state and an accredited flag. Cheap first step before edu/verify.

Verify a US college or university is accredited and get a diploma-mill verdict. Give one of name, opeid, ipeds or domain plus an optional claimed_accreditor; get back an is_accredited flag, the recognized accreditors, a diploma_mill_flag with weighted signals, operating status, a confidence and cited sources. Deterministic, no LLM.

Employer labor-certification track record from public OFLC case-disclosure data: application counts by program, certified, denied and withdrawn rates, offered-wage range, top occupations and a flag for offered wages below the prevailing wage. Query by employer name or by SOC, state and fiscal year.

US electricity data from the EIA grid monitor and retail survey: generation mix by fuel type with percentage breakdown (latest hour), demand by region, and average retail price by state/sector (monthly).

US natural gas data from the EIA: Henry Hub spot price (daily) and weekly working gas in underground storage (Bcf, Lower 48 or region). Returns latest value, change vs the prior period (week-over-week for storage), and short history. Source: U.S. Energy Information Administration.

US petroleum prices and stocks from the EIA: retail gasoline and diesel by PADD region (weekly), WTI and Brent crude spot (daily), and weekly crude/gasoline/distillate inventories. Returns latest value, change vs prior period, short history, and a region-vs-US spread.

Renewable share of US electricity generation from the EIA grid monitor: solar, wind, hydro and geothermal as a percentage of the latest hourly generation total, by grid region. Source: U.S. Energy Information Administration.

Enrich a domain / company / email into one aggregated profile from public sources: registration (RDAP/WHOIS age, registrar, expiry, nameservers), DNS (A/AAAA/MX/NS, SPF, DMARC), TLS certificate (issuer, validity, expiry), homepage metadata (title, description, Open Graph, JSON-LD Organization, social links, role contacts) and a tech-stack detection. Each block is null-on-failure (partial, never 500). Business/domain data only — no personal data of individuals.

Validate and classify an email DOMAIN from public DNS: MX hosts + mail-provider, SPF and DMARC policy, plus disposable / free-webmail / role-account flags and a deliverability signal. No SMTP probing of individual mailboxes (privacy + ToS).

Resolve one legal entity across three public registries from a single identifier. Give exactly one of name, ticker, cik, lei, qid or isin and get back the reconciled set of ids (SEC CIK, GLEIF LEI, Wikidata QID, ISIN, ticker, EIN) plus legal name, jurisdiction and status, with per-id provenance and an optional GLEIF parent/child hierarchy.

Disambiguate a company by name: fuzzy legal-name search returning ranked candidates, each with the ids known for it (Wikidata QID, GLEIF LEI, SEC CIK, ticker), country and a match score. Cheaper first step before entity/resolve.

US facility EPA compliance and enforcement detail: current significant-violation status by statute, quarters in noncompliance, formal and informal actions, penalties, and inspection dates, for a company name, FRS registry id, or location.

US facility emissions profile: EPA Toxics Release Inventory toxic releases with trend plus the Greenhouse Gas Reporting Program CO2e profile by year, for a company name, FRS registry id, or location.

US facility environmental due-diligence: one cited JSON verdict fusing EPA compliance status, enforcement history, penalties, toxic releases and reported greenhouse gases, with a 0 to 100 environmental-risk score, for a company name, EPA FRS registry id, address, or coordinates.

Screen US EPA-regulated facilities: fuzzy name or location search returning ranked candidate facilities with their EPA FRS registry id and compliance status — the cheap first step before a full env facility verdict.