Web & Data

Search real-time breaking news, market events, and press releases via the Brave News index. Returns fresh articles, publishers, and timestamps. Provide ?q=topic.

Lookup WHOIS records and domain availability in JSON format. Provide the domain name via ?domain=example.com to query registrar, status, and expiration dates.

Execute live global web searches via the independent Brave Search index. Returns top ranked web pages, snippets, and page URLs. Provide ?q=your+query.

Searches a locally harvested metadata-only index of public scientific assets from free/open APIs. Returns curated pointers, licenses, provenance, freshness hashes, and source metadata without downloading or reselling the underlying open datasets, model weights, papers, or repositories.

Searches a governed corpus of 1,131 scientific hypothesis proposals across five rigor tiers (benchmark, established_method, active_research, exploratory, speculative). Every record is IDEA-tier and unvalidated — this is a discovery layer over proposals, not results. Quarantined records (not_physical, metaphysical) are excluded at the source. Returns full honesty fields (execution_status, validation_status, promotion_eligible, lifecycle_state, governor_reason) with every result.

Batch Base pre-trade risk, token safety, rugpull and honeypot verdicts for up to 5 EVM contracts before a buyer agent signs or routes a swap. Returns PROCEED/CAUTION/REJECT actions, safety scores, warnings, evidence, aggregate counts, and an optional 0.50 USDC bundled-risk-pack tier. Search keywords: rug check, honeypot check, token risk, swap preflight, rug pull, scam token, and is this token safe.

Rank search results for a task and flag duplicate, stale and spam-like results

Returns clean, normalized datasets of AI model benchmarks, pricing, leaderboard scores, and Ethereum EIPs, parsed from sources that are costly to scrape.

Grok-backed deep coding and architecture work for harder problems. Larger context, stronger reasoning.

Find a DAO's Snapshot space by name: returns matching spaces, biggest first, with their id (to use with dao-proposals), whether Snapshot has verified them, followers, number of proposals and how many votes are open now. E.g. q=uniswap, aave, arbitrum, ens.

Read one file from a public GitHub repository at any branch, tag or commit, as text trimmed to a budget you set, with optional line numbers and a start line for long files. Pass ?owner=honojs&repo=hono&path=src/hono.ts&max_chars=20000. List files first with /repo/tree. Binary files are refused (not charged).

Check whether a source supports, contradicts, or gives insufficient information about a claim - a typed verdict with a real probability, not generated text. Try GET /verify/sample.

Extract hard constraints, soft preferences, exclusions, budgets and deadlines from a human request

Compare 2 to 5 public product pages and select the cheapest offer separately per currency

Keyword and entity extraction API — topics, named entities and key phrases from any text; NLP enrichment. Deterministic on-chain execution by the AmanChain node — live consensus state, real blocks, pools and balances. Pay per call via x402 (USDC on Base), no account, no API key. POST JSON {"serviceId":"aman-keywords","request":" "}.

Premium AI toolkit — text, code, and analysis.

Web search API — live web search engine results for any query with titles, URLs and snippets; real-time SERP for web search, news search and docs search, agent-ready. Deterministic on-chain execution by the AmanChain node — live consensus state, real blocks, pools and balances. Pay per call via x402 (USDC on Base), no account, no API key. POST JSON {"serviceId":"aman-web-search","request":" "}.

Every hyperlink on a page as absolute URLs with anchor text, flagged internal or external. Capped at 300.

The pages a site publishes, from its sitemap, located via robots.txt then the conventional path, with last-modified dates.

A written read of the market right now by Claude Opus, grounded in this snapshot: funding, open interest and whale positioning. Educational, not advice

Per-target pricing change events -- whether the latest scraped snapshot differs from the previous one, with fetch times and content hashes for both. No outbound network on purchase; read from the local feed database populated by the scraper on a 6-hour cadence.

Stock ticker and company search API. Find US equity symbols by company name or ticker for trading, research, and autonomous-agent workflows.

Uncensored one-turn chat (abliterated LLM): direct, specific answers to any prompt.

Website screenshot: give a URL, get a 1280x800 JPEG of the page rendered in a real browser, with its title, final URL and SHA-256.