Web & Data

Sentiment analysis on text. Returns positive/negative/neutral with confidence...

Fetch raw content from a URL. Returns body, headers, status code. For hitting...

Intelligent document summarization for any text document (reports, articles, emails, legal docs, code). Returns an executive summary, key points, keywords, sentiment, document type classification, and action items. Structured JSON output by

Precision JSON extraction engine. Feed messy raw text, HTML, or unformatted data plus your target JSON Schema, and get back a single valid JSON object that strictly conforms to it. Ideal for agent pipelines that need structured data from un

Inspect a Python package’s latest release, Python compatibility, declared dependencies, license metadata and PyPI-reported advisories. No code execution.

Find up to five publications with DOI identifiers, authors, publication years and citation counts. Returns metadata, not abstracts or full text.

Resolve a CVE into its published description, status, CVSS metrics, weakness identifiers and vendor/reference links. This does not scan a system or prove safety.

Resolve a two-letter country code into its World Bank name, region, capital, income group and lending classification for data enrichment.

Resolve a DOI into normalized publication metadata, citation text, identifiers and source links. Abstracts and full paper text are excluded.

Find up to five npm packages with versions, descriptions, registry ranking scores and source links for package discovery.

One verify-loop lane: confidence-labeled findings on any topic. The flagship teaser — full sweeps at $0.50-5 ship when this crosses BUILD.

Look up a current RxNorm, ICD-10-CM, or LOINC display from an exact code. Use when an agent already has a code and must not invent the preferred term.

URL Metadata Extract: URL title, description, Open Graph image and canonical metadata Executed deterministically by the AmanChain node against live consensus state (real blocks, pools, balances) — paid per call via x402, settled in USDC on Base. Input: JSON body {"serviceId":"aman-url-meta","request":" "}. No account, no API key.

Link map: fetches one public HTML page server-side and returns up to 100 normalized, deduplicated http/https links with internal/external classification and counts, the final URL, a timestamp and a tamper-evident receipt. Single GET query parameter (url). One page only; no recursive crawling. Check crawl permission first with GET /api/v1/robots-check.

Minute-resolution price path from pool creation (t0): peak multiple, minutes to peak, terminal multiple, drawdown from peak, and buy fraction. Reconstructed from swap logs on our own chain node. Observation, not a forecast.

Call when you need the text of one public http(s) page. Required query url. SSRF-gated. Not a search engine and not a GitHub clone.

Fetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links. No model call, deterministic.

Search Users

Compare two text blocks and return a structured diff (unified, HTML, or JSON).

60 minutes of the browser dashboard for humans: live whale positioning, signals and an AI brief that refreshes on its own

Markets where a squeeze can build: stretched funding plus high open interest plus whales positioned against the crowd, scored 0-100 with the reasoning shown

Returns repo, total_neighbors, and the neighbor list for one repository. Returns 404 if the repository is unknown.

Detect the technologies a website uses (CMS, frameworks, analytics, CDN, web server, ecommerce, tag managers ...) from its HTML, headers, cookies, meta tags and script URLs, matched against 7,600+ open webappanalyzer fingerprints. Returns name, categories, version where visible, confidence and evidence, plus a by-category summary. Params: url (required), min_confidence (0 to 100, default 50).

Get a Person. Returns the comprehensive Person payload including display name, slug, headshot, curated bio, the Person's company-role history (most recent first), known third-party profile links, and an optional knowledge-graph cross-reference