All projects matching “engineering”

Check Base ERC-20 decimals and total supply at a recorded block, and up to three claims against cited evidence. Returns supported, contradicted, or unknown. Official project coverage currently includes Base USDC only. No safety verdict, liquidity, or holder analysis. One brief costs 0.25 USDC; retain your private Idempotency-Key for recovery.

Extract main webpage content as clean Markdown or structured JSON from a URL, with deterministic source hash, plain text, metadata and links. SSRF-safe with strict redirect and document-size limits.

Web search for AI agents returning up to 10 ranked results with title, URL, snippet and date for research, source discovery and RAG.

Stateful pre-payment firewall for autonomous agents. Enforce caller-supplied amount/network budgets, detect repeated intents, seller pay-to/network drift and large price jumps. Never signs or sends the downstream payment.

Web search that returns structured SERP results as JSON. Runs on a dedicated SearXNG instance aggregating multiple engines, so there is no per-engine API key, quota or HTML scraping to manage. Each result carries title, URL, snippet, the source engine and a published date where available. Choose general web, news, or image results, up to 10 per call. Use it to ground an answer in current web sourc

Autonomous agent execution (multi-step reasoning + tools). Engines: cheap agents/oss-20b or premium agents/gpt-6-sol; stream=true streams SSE step events. Ceiling = engine base + max_steps x step + code_exec calls ($0.002 each, max 3 per task) (charged_ceiling_usd).

Track a website's AI search visibility every week for 4 weeks. $19 USDC on Base per call. Runs the 16-engine report now, then each Monday until 4 successful runs. Returns a private tracking_url with a trend chart and competitor shifts, plus emails. Settles only if the first run succeeds (12+ of 16 engines). Don't use this for a single snapshot; use /api/v1/report.

Publication proofing — IQR outlier flags + Explicit missing-value fill: IQR outlier flags + Explicit missing-value fill for supplied publication proofing records (checked_pages, flagged_pages). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200

Real-time BTC/ETH market pulse — price, CVD, OI, whale flow, gear ratios, session P&L and win/loss counts from live trading engine

Apify is the largest and most trusted marketplace of tools for web scraping, crawling, data extraction, and automation. Use these tools, called Actors, to extract structured data from social media, e-commerce sites, search engines, maps, travel sites, or any other website. Turn the open web into a real-time data source for your research, lead generation, and monitoring.

Live market-state data for one crypto pair: BUY/SELL/HOLD state + confidence from a multi-timeframe engine. Machine-readable, ECDSA-signed. Input data for AI finance agents (USDC pay-per-call). Free preview: GET /signals/preview Bad input (unknown pair) returns 400; upstream outage returns 503; you are never charged for an error.

Canonical paid interface backed by Evidence Engine V2. Submit a natural-language query; vertical is an optional routing hint. Explicit two-subject text comparisons return independently attributed evidence, coverage, provenance, limitations, and per-subject scores, with no winner or aggregate comparison score. A one-element brands array is accepted for single-subject compatibility. budget_min, budg

Agent guardrail decision engine. Call once before every agent action; returns a single decision — proceed, slow down (with a reason and wait time), or stop — based on cost budget, chain depth, step cap and retry budget, and request volume pressure. Policy thresholds are configured separately via /policy; this endpoint only reports the decision for a single action.

Population-level empirical profile of what separated eventual 5x stocks at the moment of purchase: measurable entry valuation/size/quality specs, twin-engine return decomposition (multiple expansion vs. earnings growth), 5x->25x graduation base rates, drawdown/kill-zone path characteristics, and sector-regime sensitivity. Synthesized and fully cited from Bessembinder, Yartseva, Mayer, Alta Fox, LS

US safety recalls for a VIN, deterministic. Answers "does this car have open recalls", "is this used car safe to buy", "what NHTSA campaigns cover this vehicle". Decodes the VIN via NHTSA vPIC (year, make, model, body, engine) then lists every NHTSA recall campaign for that vehicle: component, summary, remedy, park-outside and do-not-drive flags. No LLM, no key, public domain.

AGMM guide library: one long-form article per request, from a UK AI consultancy for business owners. Covers what AI costs, GDPR, automation, tools and readiness for businesses turning over 1m to 50m pounds, with sources and a last-reviewed date on every page. One GET returns the full page as HTML, or as Markdown with index.md. Costs one US cent in USDC on Base. People, search engines and AI answer

Real-time at-risk DeFi borrowers across Aave V3, Morpho, Comet, Euler V2, Fluid, Moonwell, Spark on 11 EVM chains. Returns health factor, collateral, debt, and protocol. Updated every 5 minutes from the liquita liquidation engine.

RAVN — execute a previously quoted swap. Returns a signable transaction, typed data to sign, or a Bitcoin deposit address depending on the route; RAVN never custodies funds. Same 0% fee, non-custodial engine the RAVN app itself runs on.

Returns a 0–100 generative-engine visibility score and estimated LLM mention rate for a URL. Cost $0.01 per call. Not HTTP uptime, TLS, or a credit.

Decode a 17-character VIN: ISO 3779 structural validation (check digit), WMI manufacturer lookup, model year, and NHTSA vPIC pattern decode (make, model, trim, body, engine, plant). Public-domain NHTSA data.

Healthcare text de-identification engine (demo endpoint — SYNTHETIC/TEST DATA ONLY, never send real PHI; nothing is stored). Strips names, DOBs, member/claim IDs, phones, emails, addresses, SSNs; dates become a derived interval timeline (service-to-denial days, days-ago) so denial and timely-filing math survives de-identification. Returns scrubbed text + token map for local re-identification. Prod

Research cards from KARP, SoulDriver's multi-model research engine: GPT, Gemini, Grok and Claude debate a topic over many rounds and publish a conclusion. Each card gives the conclusion, key insight, warnings, dated figures, consensus status, open questions, research date and staleness. See what is covered first with the free POST /v1/coverage; verify time-sensitive points with POST /v1/check. Cat

How to make money with AI — one tailored business-in-a-box. Give a goal, budget and interests; get a specific business to start now: the exact real-time PulseNetwork API engine to build it on, suggested pricing, unit economics, monetization paths, and a fork-and-ship starter kit. Turns 'find me a way to earn / passive income / start a business' into a concrete plan. For agents tasked with making m

Energy and climate compliance regulation scan across a curated 14-regulation database, with jurisdiction, urgency, and effective-date signals, including California SB 253 and SB 261 status. The scan step pairs with Viridis GHG inventory, sustainability disclosure, and clean-energy tax-credit engines.

General current-operation routing for permit/exemption/duty-of-care and Digital Waste Tracking review using the same deterministic engine as the MCP tool. Payment verification precedes deterministic execution. Not Environment Agency approval or legal advice.

Query a World ID-verified human expert agent. Each expert is a real person's domain knowledge extracted via voice interview and served by the ADIN engine. Discover experts at /api/bazaar.

Publish a practitioner-grade IoT, embedded firmware, MQTT/CoAP, or Edge AI engineering article on IoTSoftwareDeveloper.com with TechArticle JSON-LD schema & Ed25519 receipt ($1.00 USDC).

Company hiring-intent radar for sales agents: one call turns a company domain into buying signals from its public job board (Greenhouse, Lever, Ashby, Workable, Recruitee, SmartRecruiters): intent_score 0-100, hiring_status, open roles, roles posted in the last 30 days, hiring by function (sales, engineering, data/AI...), technologies the company is hiring for (cloud, data/AI, databases, observabi

OX212 risk check: the engine's behavioural risk reading of the trades you send (no AI).

Detect the structure of a book manuscript before typesetting it: the chapter list our engine will use (numbered / unnumbered), words and scene breaks per chapter, paragraph count, characters the book font cannot print, and the warnings a full build would raise. Same parser as /v1/typeset, so what you see here is exactly how the book will be divided.