Fetch and parse robots.txt (+ llms.txt if present) into structured JSON, including which AI crawlers are blocked.
Extract a public HTTP(S) page into JSON: title, description, JSON-LD, Open Graph, headings, links, and AI-readiness signals. No JavaScript; 12-second timeout; 3 MB cap.…
Scores prompt-injection / jailbreak risk for LLM inputs. Agent builders use this to sanitize user inputs before hitting their LLM.
Automatically select a suitable open-weight model from Kimi K3, Qwen3.6-35B-A3B, and GLM-5.2, then generate a chat completion. The exact price is calculated from the sel…
Where Ether stands. Its price and global 24h volume, with that volume's 30 day z score (CoinGecko); its distance from the 200 day average; Lido's stETH APR; the CFTC's C…
US oil and gas stocks. EIA weekly commercial crude stocks and Lower 48 gas storage against the same week in the prior five years, with the week's change, the levels that…
AI-generated descriptions of places found by web or place search. Use it to learn what a place is before recommending it. Pass the location ids, repeated as ids=a&ids=b.…
News search over Brave's independent index. Returns recent articles with title, URL, source, and age. Use it for current events, where web search can surface older pages…
Summarize text: send any text, get a short summary written by Claude, with a word limit you choose.
Pay-per-read pieces by independent publishers. Find one by question first: POST https://tenjin.sh/api/search is free and returns payable candidates or an honest MISS. Th…
Chat completion from an open AI model (Llama 3.3 70B by default; Llama 3.1 8B for speed), no account or API key: send messages (or a prompt), get the model's reply. Up t…
437 models, no account, no API key, pay per call in USDC - OpenAI-compatible chat completions and AI inference gateway (Claude, GPT, Gemini, Llama, Mistral and more in o…
Fact-check verdict written by Claude Haiku 5.5 (Anthropic) from real web sources: supported/contradicted/mixed/unverifiable, each source with its stance (supports/contra…
Base token safety check: Claude Haiku 5.5 (Anthropic) writes a rug pull / honeypot verdict (SAFE/CAUTION/RISKY/DANGER) from on-chain data, a tagline, a short explanation…
Validate caller-supplied JSON against Forest bounded JSON Schema subset v1 before an agent trusts or forwards structured output. Returns deterministic machine-readable v…
Prediction markets and odds, live from Hyperliquid ($0.005): every open HIP-4 market as a plain question with each option's probability, 24h change and USDC volume, most…
Read one web page as clean Markdown (or plain text) for an LLM: the main content without menus, cookie banners and footers, plus title, description, author, published da…
Privacy-first OpenAI-compatible vision: a local vision-language model on dedicated hardware understands your images - they never reach OpenAI/Anthropic or any third-part…
Catalog snapshot: every site in the 402registry catalog of sites verified visible to AI crawlers, as one JSON file rendered at purchase, every record dated. Basic fields…
Birth time resolver: Local birth time + place -> exact UT, historical UTC offset, Delta T, Local Mean Time, true solar time.
Planetary positions: Tropical (or sidereal) longitudes, latitudes, speeds and retrograde flags of Sun..Pluto, nodes, Lilith.
Match local features between a pattern image and a larger image: detects ORB or SIFT keypoints in both, matches them with a brute-force matcher and Lowe's ratio test (Op…
AI text summarization and analysis (Qwen3-4B, local). Send any text in the 'texto' field (you may start it with an instruction, e.g. 'Summarize in 3 bullets: ...') and g…
Repair broken JSON, typical of LLM output: strips ```json fences, comments and surrounding text, trailing commas, single quotes, unquoted keys, Python True/None and uncl…
