Find recently updated ClinicalTrials.gov study identifiers, titles and registry status…
Find recently updated ClinicalTrials.gov study identifiers, titles and registry status for a condition, with the registry processing date. No medical conclusion.
Find recently updated ClinicalTrials.gov study identifiers, titles and registry status for a condition, with the registry processing date. No medical conclusion.
Repair bounded near-JSON into valid deterministic JSON and optionally validate a safe JSON Schema subset.
OpenAI-compatible chat completions gateway — standard /v1/chat/completions path and request shape, model chosen in the body: any gpt-* chat model (not Claude/embeddings)…
OpenAI-compatible chat completions gateway (alias of /v1/chat/completions for api/v1-style base URLs) — standard request shape, model chosen in the body: any gpt-* chat…
OpenAI-compatible text embeddings API (alias of /v1/embeddings for api/v1-style base URLs) — input as a string or batch of up to 128 strings, model text-embedding-3-smal…
Turn event fields into a valid RFC 5545 .ics calendar file — handles timed and all-day events, escaping, line folding, and a deterministic UID for idempotent re-import —…
Call OpenAI's gpt-4.1-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completion…
Call OpenAI's gpt-5.4-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completion…
Call OpenAI's gpt-5-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions…
Call OpenAI's gpt-4o-mini via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions…
Split text into overlapping chunks for RAG ingestion — by characters or words, with configurable chunk size and overlap. Deterministic (same input → same chunks), return…
Extract structured data from any unstructured text into your own JSON Schema — structured-data / information extraction, text-to-JSON, LLM data enrichment. You supply th…
Conform messy or inconsistent JSON to a target schema using Claude Haiku — renames keys, coerces types (string→number, "true"→boolean, etc.), and fills missing fields wi…
Turn unstructured text into structured JSON matching a caller-supplied schema using Claude Haiku — the agent declares the fields and types it wants, and gets back popula…
Single-call LLM grounding bundle — top 10 and bottom 5 composite-ranked assets, all signals triggered today, 30-day factor breadth across 8 classes, plus a ready-to-drop…
Latest material definitive agreement 8-K events as structured JSON — Latest 8-K filings classified as material definitive agreement (Item 1.01) across covered companies,…
Convert any webpage URL into clean, ad-free Markdown text optimized for LLM context windows. Paid in USDC on Base.
Sunrise, sunset, solar noon, day length, and moon phase for a given latitude/longitude/date, computed via the suncalc library (standard solar/lunar position algorithms)…
Base64 decoder API. Decodes a base64 string back to UTF-8 text instantly and correctly, avoiding the padding and charset errors LLMs make when decoding base64 by hand.
Base64 encoder API. Encodes UTF-8 text to base64 instantly and correctly — skip burning agent tokens hand-computing base64, which LLMs frequently get wrong on padding an…
Computes the next N run times for a standard 5-field cron expression, avoiding the mental cron-schedule simulation an LLM often gets subtly wrong.
Safe arithmetic expression evaluator. Parses and evaluates expressions with +, -, *, /, ^, and parentheses using a bounded-recursion parser (no eval/Function), avoiding…
FIRE (Financial Independence, Retire Early) calculator. Projects year-by-year net worth growth to determine how many years until your portfolio can sustainably fund reti…
Secure password generator API. Generates a cryptographically random password — true randomness an LLM cannot produce on its own. Accepts optional length (8-128), per-cha…