All projects on Base matching “clean”

Web search API for AI agents: live Google search results (SERP) for any query as clean JSON, with ranked title, URL, snippet and date, plus the answer box. Search the web or search news only; filter by date (past hour to past year), keep to or leave out up to 5 sites. A fast Google search API / SERP API for grounding, RAG, research, fact checks and finding sources. Results via Serper.

Apple App Store product details (path variant) — full profile for a single app by product_id in the URL: rating, price, description, version history, screenshots & metadata as clean JSON.

Wikipedia article summary — plain-text and HTML extract, short description, thumbnail and Wikidata id for any title, in a clean normalized envelope with CC-BY-SA attribution.

Clean web content extraction — any URL to markdown + text + metadata

DNS TXT record lookup — a domain's TXT records as a clean JSON list: SPF, DKIM and DMARC policy strings plus site-verification and domain-ownership tokens, for email-authentication and domain-verification checks.

Transcribe text to Unicode braille (grade-1 / uncontracted English braille), with capital and number signs. Characters with no grade-1 representation are clean 400s.

Search plus page-to-markdown in one $0.01 call: ranked results from Wikipedia, Hacker News, GitHub and a web engine, with clean readable article text. Pass q= to search, or url= to extract any single page. Free /demo and /quickstart.

Hotel details & rates — one hotel's full profile by property token: address, phone, per-booking-site nightly & total rates, rooms, amenities & review breakdown as clean JSON.

A lightweight, verifiable web search proxy that accepts a natural-language query and returns ranked, cited results. It is designed for agent-to-agent and x402-metered traffic: one paid call yields one clean search response with title, URL, snippet, and a stable rank. Use it when your agent needs cheap, low-latency public web search without managing multiple upstream providers. Requests are validat

Audit a URL's HTTP security headers over a single body-free (HEAD) request. Grades Strict-Transport-Security, Content-Security-Policy, X-Frame-Options, X-Content-Type-Options, Referrer-Policy and Permissions-Policy, flags information-leak headers (Server, X-Powered-By), and returns the parsed values plus advisory warnings. Clean JSON for security and pentest automation.

Google Maps local business search by place name — find places by query and a free-text location (e.g. 'Austin, Texas'), no coordinates needed; returns Google's local-pack results as clean JSON.

South African SA benchmark bond yields (SARB closing yields on the R2030 and R209 South African government benchmark bonds, key reference points for the domestic yield curve.) Clean cited JSON with official source URL, effective date and freshness flag.

Use when a page will not read correctly with a plain fetch — a single-page app, content loaded by JavaScript, or markup so noisy the text is buried. Fetches it with a headless browser (rendering JavaScript) and returns the main readable content as clean Markdown — ideal to feed an LLM as context. JSON body { url } (public http/https), optional include_images (default false). Returns title, final_u

SWARM Read Page - Retrieve the content of a URL as clean, LLM-ready text (headings with #, lists with -; menus, scripts, styles and markup removed). Use when an agent needs to read a web page, article or docs page without paying model tokens for raw HTML: on 15 public pages we measured, the text was a median 97% smaller than the HTML (about 67,000 fewer tokens per page). Requires `url`; HTML or te

Fetch any public web page and return clean, readable Markdown with navigation, ads, and boilerplate stripped. For agents that need article text or documentation as Markdown.

Text to tiny, clean SVG code. Best for icons, logos, lettering and badges. Returns real shapes and editable text, each part its own layer. About 10 s.

Read one public web URL and convert its webpage content to clean Markdown or plain text. Removes HTML boilerplate and returns LLM-ready text for AI agents, RAG context, research and summaries. One URL per paid request.

Live grid carbon intensity, deterministic. Answers "how clean is the grid right now", "gCO2 per kWh in Germany", "cleanest hour to run a job today". Current intensity + forward curve (to 48h) + cleanest and dirtiest slots, from NESO (GB national + 14 DNO regions) and energy-charts/Fraunhofer ISE (DE FR NL BE AT ES IT NO). No LLM, no key. Pair with /api/energy/compute-window for full job scheduling

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

Global news article search by GDELT — normalized fulltext search across worldwide media (query syntax: phrases, OR, sourcecountry, theme, tone) returned as a clean snake_case envelope.

Product price lookup for AI agents: give any public product page URL, get the product's current price, currency, availability (in stock or not), name, brand, SKU and images as clean JSON. The page is rendered in a real browser, so JavaScript stores work, and the store's own schema.org product data is read first. For price checks, price monitoring and comparing stores before you buy.

Cross-venue perpetual funding rates (OKX, Kraken Futures, dYdX) for any major token. Per-venue annualized rates plus the cross-venue spread in percentage points — a ready-to-use funding arbitrage signal. Clean JSON for trading and research agents.

Top DeFi yield opportunities per chain from DefiLlama — TVL-filtered, outlier-cleaned (unsustainable meme-pool APYs removed), sorted by APY. Fields: project, symbol, apy_pct, apy_base_pct, tvl_usd, stable. Ideal for yield-hunting agents.

Parse an SMPTE timecode (HH:MM:SS:FF, or HH:MM:SS;FF for drop-frame) at a given frame rate into its components, total frame count and real-time seconds. Drop-frame is auto-detected from a ';' separator unless dropFrame is set. Out-of-range or non-existent drop-frame values are a clean 400.

Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.

Prompt-injection scanner for content your agent is about to read. Returns a risk score (0-1), a level (low/medium/high), findings and the cleaned text wrapped as untrusted data (hidden text, invisible characters, data-exfiltration links, instruction-override phrases in 13 languages). Deterministic. Content is scanned in memory and never stored. Not charged if it fails. Same service: POST /v1/read

SSL/TLS certificate check: expiry, issuer, SANs, chain validity, hostname match, negotiated protocol/cipher, and weak-algo warnings for a public HTTPS host. Clean JSON.

Japanese address normalization (住所正規化): standardize a JP address into clean prefecture / city / town / chome-banchi components. Fixes fullwidth/halfwidth digits, old-form kanji, and chome-banchi notation variants, and resolves the 7-digit postal code. Returns a 0-1 confidence score so agents can flag low-quality input. Use for address validation, cleansing, deduplication, and canonicalization befo

Google Patents search — find patents by technology, inventor or assignee with date, country, legal-status and classification filters; clean JSON with titles, snippets, dates, owners, PDFs and patent IDs.

Fetch any public URL and return its content as base64 with the content type and a ready-to-use data URI. Embed images, PDFs and files directly in LLM and API calls without downloading them yourself. Clean JSON.