Web & Data

Looks up normalized package metadata from the Python Package Index, version, dependencies, license, homepage, and yank/deprecation status, trimmed down from the much larger raw index response. For agents auditing or generating requirements files before running pip install.

Pull a structured summary for any known topic — short description, lead paragraph, thumbnail, and source URL — from a continuously updated, community-maintained knowledge base. Accepts titles with spaces or underscores. Built for research agents and chatbots that need quick, grounded background on a person, place, or concept.

Video-to-audio extraction: pulls the audio track out of any public video or audio URL (up to 25MB) and returns it as an MP3, encoded on request rather than pulled from a pre-made library. Source files are deleted the moment processing finishes. Use it to prep clips for transcription, strip audio from screen recordings, or normalize mixed formats before a media pipeline.

Breaks down any text into character, word, and sentence counts, estimated LLM token count, and reading time, computed instantly with nothing stored. Useful for context-budget checks before an API call, content-length validation, and editorial word-count requirements.

Text statistics API: characters, words, sentences, average sentence length, Flesch reading-ease score, estimated reading time, and estimated LLM token count for any text — instant, computed locally, nothing stored. For context-budget checks, readability gates, and content QA in agent pipelines.

Fetch manga details by MyAnimeList id: title, type, chapter count and community score. Backed by the keyless Jikan v4 API (MyAnimeList). Pass a MAL manga id like 1 for Monster.

Pulls the current day's featured astronomy image along with its title and full explanatory caption, as structured JSON. Built for content agents, daily digest bots, and education tools that want a rotating supply of space imagery with context attached rather than a static image library. Cached 6 hours.

Audio-to-text conversion: submit any public audio file URL (mp3, wav, m4a, ogg, up to 25MB) and get back a full text transcript, with the source language automatically detected across roughly 99 languages. Audio is processed in an isolated sandbox and deleted immediately afterward. Built for turning meeting recordings, interviews, and voice memos into searchable text.

Speech-to-text API: audio URL in, transcript out — a neural speech-recognition engine on our own hardware, ~99 languages, mp3/wav/m4a/ogg up to 25MB. For voicemail, podcast, meeting, and voice-agent pipelines. Audio deleted after processing.

PDF to text API: fetches any public PDF URL and returns its full plain text, fast, with layout preserved. For scanned PDFs needing OCR see /pdf-to-markdown. 25MB / ~100 page cap. Nothing stored.

Decision procedure for agents merging search results from multiple paid and free sources (mpp catalog, x402 endpoints, web APIs) into one canonical result set. Covers field mapping across heterogeneous schemas, dedupe key selection, source priority and trust weighting, freshness ranking, cost-aware truncation, and evidence logging per result. Prevents duplicate spending on overlapping queries and stops agents from comparing raw JSON from different vendors as if it were one schema.

GlianaAI - pay-per-call AI: LLM chat (OpenAI-compatible), image, video, music, speech - 80+ models, no signup, USDC. This resource: claude-fable-5 (Text Generation). https://ai.glianalabs.com

Look up a UK postcode from Postcodes.io, no key. Returns the latitude, longitude, district, region, and administrative areas. For AI agents validating and enriching UK addresses.

Tech news front page API: the current top 30 ranked tech stories — title, outbound URL, points, comment count, and timestamps — as normalized JSON. For trend detection, topic monitoring, and content-pipeline agents. Refreshed every few minutes.

Formats any phone number into its E.164 canonical form plus national and international display formats, detecting the country and line type, mobile vs landline where determinable, from messy human input. For CRM cleanup, signup forms, and dialing systems that need one consistent format instead of guessing at punctuation.

Look up a country by name or its 2- or 3-letter ISO code and get capital, currencies, official languages, calling code, region, land area, bordering countries, and flag emoji in one normalized object. Handy for onboarding forms, compliance checks, and shipping-rule engines that key off ISO codes rather than free-text country names.

Returns current position data for traders on a prediction market platform.

Returns event data for prediction market contracts on Polymarket.

Bulk Export

PDF text extraction API: give it any public PDF URL and get clean layout-preserving text back in one call. Handles digital PDFs up to 25MB. Use it as a PDF parser, PDF-to-text converter, or document ingestion step for RAG and analysis agents. Files are processed in a temp sandbox and deleted immediately.

Extracts clean, layout-preserving text from any public PDF URL up to 25MB in a single call, no local PDF library or OCR pipeline required. Built for feeding PDF content into research agents, document QA, and RAG ingestion pipelines that need plain text rather than a binary file.

Fetches a public file URL, up to 50MB, and returns its SHA-256, SHA-512, SHA-1, or MD5 digest so you can confirm a download matches its published checksum before trusting it. A supply-chain safety step for agents pulling packages, models, or binaries from the open web.

HTML to Markdown API: pass a public URL (or raw HTML) and get clean readable markdown back — title, byline, article body with navigation/ads/boilerplate stripped. We honor robots.txt AND Content-Signal (aipref) declarations: a site that disallows agent access returns an unpaid 403, you are never charged. Use for research agents, summarization pipelines, and RAG ingestion.

Retrieve the complete text of any King James Version Bible chapter, verse-by-verse and as one continuous passage, served entirely from local data.