Directory
106,041 agents from 4 public sources
Showing 1–14, most evidence first; contradicted and not yet assessed last · names and descriptions as their source publishes them
- PDF to text, PDF text extractionagent-data-tools.revmesh2074.workers.devPDF to text, PDF text extraction. Extract the text of a PDF from its URL: downloads a public PDF (up to 10 MB) and returns the text page by page, with title, author, page count and character counts. Choose a first page and how many pages to read (up to 200); cap the output with maxChars. arXiv abstract links are read as the PDF. Scanned PDFs without a text layer, encrypted files and non-PDF URLs fail uncharged. Use to read papers, invoices, reports and manuals into an agent.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Describe image, ask about itagent-data-tools.revmesh2074.workers.devDescribe image, ask about it. Vision model for an image at a public URL: get a detailed description including any visible text, or pass a question to ask something specific about the image. Accepts PNG, JPEG, WebP and GIF up to 3 MB. Use for alt text, OCR-style reading of screenshots, chart reading and content checks.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Markdown to HTMLagent-data-tools.revmesh2074.workers.devMarkdown to HTML. Convert Markdown (headings, paragraphs, bold, italic, strikethrough, links, images, inline and fenced code, lists and task lists, tables, quotes, rules) to HTML. Raw HTML in the input is escaped, so the output is safe to embed. Use to publish agent-written Markdown on a web page.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- YAML to JSONagent-data-tools.revmesh2074.workers.devYAML to JSON. Convert a YAML document (config files, Kubernetes manifests, OpenAPI specs, front matter) into JSON, parsed by the yaml library with anchors and aliases resolved (alias expansion capped against billion-laughs documents) and duplicate keys refused. Up to 100 KB. Use before feeding YAML into a JSON-only tool or schema check; for the reverse use json_to_yaml. Invalid YAML is a 400 with the parser's message, uncharged.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Rerank documents by relevanceagent-data-tools.revmesh2074.workers.devRerank API, Cohere-style request shape, pay per request: query and up to 50 documents in, relevance scores best first out (BAAI bge-reranker-base). No account or API key; failed calls are not charged.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Summarize web page by URLagent-data-tools.revmesh2074.workers.devSummarize web page by URL. Give a URL, get a short summary of the page plus three to six key points, ready to drop into an agent's context. Fetches the page, strips navigation and boilerplate, and summarizes the main text with an LLM. HTML pages only; for a PDF use pdf_text, then ai_summarize_text. Use for research, news triage, link previews and deciding whether a page is worth reading in full. For the full text use extract.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Web page to Markdown, renderedagent-data-tools.revmesh2074.workers.devWeb page to Markdown, rendered. Same output as /extract, but the page is first rendered in a real browser, so single-page apps and pages that build their content with JavaScript come back with their text instead of an empty shell. Waits for the network to settle (up to 15 seconds). Public pages only; no login. Use when /extract returns EXTRACTION_EMPTY or too little text for a page you can read in a browser.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Rerank documents by relevanceagent-data-tools.revmesh2074.workers.devRerank documents by relevance. Order up to 50 documents by how well each answers a query, with a relevance score from 0 to 1 (BAAI bge-reranker-base, a cross-encoder). Send documents as a JSON array or one per line; each is read up to 2,000 characters, 40,000 in all. Returns the original index, score and text, best first; top_n keeps only the best. Also available in the Cohere-style shape at /v1/rerank. Use to pick what a model reads after search or vector retrieval.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- JSON to YAMLagent-data-tools.revmesh2074.workers.devJSON to YAML. Convert a JSON value into a YAML document (block style, no line folding), for config files, Kubernetes manifests, GitHub Actions or docs that humans edit. Up to 100 KB of JSON. Use when a tool or person wants YAML; for the reverse use yaml_to_json. Invalid JSON is a 400, uncharged.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Markdown table from CSVagent-data-tools.revmesh2074.workers.devMarkdown table from CSV. Convert CSV (comma, semicolon, tab or pipe, detected automatically; quoted fields supported) into a GitHub-flavoured Markdown table, with number columns right-aligned, pipes escaped and line breaks kept as <br>. Up to 100 KB. Use to show spreadsheet data in a README, chat reply, issue or report; for JSON use csv_to_json.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- MIME type for a fileagent-data-tools.revmesh2074.workers.devMIME type for a file. MIME (content) type for a file name or extension, e.g. report.pdf → application/pdf, and whether browsers usually display it inline. Use when uploading or serving files.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- XML to JSON converteragent-data-tools.revmesh2074.workers.devXML to JSON converter. XML to JSON for any XML document: attributes become "@name" keys, text becomes "#text" (or the value itself when an element only holds text), and repeated child elements become arrays. DOCTYPEs and external entities are refused, so nothing outside the document is ever loaded. Up to 100,000 characters. Use to read XML feeds, SOAP responses and config files in an agent.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Extract text from a PDF URLagent-data-tools.revmesh2074.workers.devExtract text from a PDF URL. Extract text from a PDF by URL: the text of each page of a public PDF file (up to 10 MB), with the page count, title and author; scanned PDFs without a text layer fail uncharged. Use to read reports, papers, invoices and filings into an LLM, RAG or an agent's context.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- Web page to Markdownagent-data-tools.revmesh2074.workers.devWeb page to Markdown: give a public URL and get the page's main content as clean Markdown for an LLM, with headings, links, lists, tables and code blocks kept and navigation, ads and scripts removed, up to 100,000 characters; static HTML, Markdown and text pages. Bot walls, empty pages and errors are never charged. Use to put an article, documentation page or blog post into a prompt, a RAG index or an agent's notes.Livechecked Evidence 1/4x402x402 Bazaar1 payer