All projects on Base matching “document”

Compare supplied routing-notice versions and return bounded evidence, validated network identifiers, and hashes.

Fill a PDF form using facts found in supporting documents. Also: fill a PDF form from DOCX, spreadsheets, images, JSON, or other documents; pre-fill a government form from supporting paperwork; complete an application from a resume or company details; extract answers from context documents into a form. Price scales with page count; this 402 carries the exact amount for the PDF sent.

Deep-merge an ordered list of JSON documents, left to right. Objects are merged key-by-key; arrays, scalars and null in a later document replace the earlier value (last-wins, no array concatenation).

Validate up to ten JSON documents against JSON Schema draft-07 or 2020-12. Returns per-document validity and actionable errors with instance paths. Runs isolated with bounded time and memory; no remote schema loading or automatic data modification.

Rerank documents against a query with BGE Reranker Base (@cf/baai/bge-reranker-base). POST query plus documents[]; returns relevance scores for search and RAG pipelines.

Verify a USCG-documented vessel by official number, IMO number, or name. Returns vessel name, official number, IMO, flag, service/type, tonnage, dimensions, build year and builder, hailing port, trade endorsements, and Certificate of Documentation status and expiry. Public-domain USCG 'Merchant Vessels of the United States' data. Does NOT identify vessel owners (owner data was removed from the pub

NoJunk Document convert: Convert a PDF, Office document, spreadsheet, HTML/XML page or image (by URL or base64) to Markdown with Cloudflare toMarkdown.

Full text of one IRS Internal Revenue Bulletin document (Revenue Ruling, Revenue Procedure, Notice, Announcement, or Treasury Decision), 2003 to present. Get the id from GET /search?q=<keywords>. Use this when you need the complete, verbatim text of a specific IRS guidance document for tax research, not a summary.

Automated /llms.txt & Agent Documentation Context Compiler (/v1/llms-generator) — Crawls any documentation or SaaS site and compiles a standards-compliant /llms.txt manifest and JSON-LD schema bundle. (https://llms-generator.agentdiet.dev/v1/llms-generator)

Extract text from a digital PDF into page-numbered JSON with SHA-256 hashes. No account or API key. 0.005 USDC on Base per successful document via x402. Maximum 2 MiB and 25 pages. No OCR, summaries, URL fetching, or verification of document claims.

Metric Metadata — Returns metadata for a single metric: its supported parameters and allowed values, available time range, documentation and Studio links, and descriptors such as name, group, and tags. Requires the path parameter. Data by Glassnode.

Live web search for AI agents: returns ranked results with title, URL, snippet, publish date and source. Neural + keyword search across the current web with automatic provider failover. Use it to find recent news, documentation, competitors, prices or any fact that needs a fresh source.

Compile 1-8 documents into a token-budgeted context pack, then measure exact retention of 1-32 caller-labelled evidence spans. Returns the pack, source-linked passages, input and output hashes, original and compiled token estimates, tokensSaved, source coverage, and requiredEvidenceRetentionPercent. Retention is exact span matching only: not accuracy, answer quality, verification, or hallucination

Publisher discovery repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tried once in the same request. The HTTP body has correlation_id and data. The item array is data.resu

Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworded, and for reworded blocks it names the individual words that went and came, so a single changed number in a long clause is visible instead of the whole clause being flagged. Alongside the content diff

Business Frameworks · business-frameworks/market/decide/verdict@1.2, applied — POST whether the node is short inside the horizon, lead time and horizon, whether suppliers are building, documented relief and how the price is set; get the node's verdict — binding, transient, pass-through or open — and the fact that decided it. Deterministic (the node's rule, no model): figures, verdict, action and c

XML tier (deterministic, no LLM): verifies a claimed value lives at a named path in a public XML document, by independent double re-fetch. Use it for feeds and sitemaps; for JSON use /verify-json, for HTML use /verify. Paths address elements and @attributes (urlset.url[0].loc). String-exact; ambiguous or volatile values return unverifiable, never a guess. First 100 checks per client are free: rese

CoverBureau: pay-per-call compliance checking for US certificates of insurance (ACORD 25). Needs NO document: give an NAIC number or carrier name plus a state, and get recognition status, financial-strength rating, and whether it meets your threshold. Use it when you have a carrier but no certificate; validate_coi already checks the carrier when you do. Carrier data is a seed dataset; each respons

PyPI breaking changes between two versions of a Python package, before a pip package upgrade: the documented breaking changes per version from the project's CHANGELOG, HISTORY or CHANGES file and GitHub release notes (alpha/beta/rc folded into the major), plus Requires-Python and required dependency changes, yanked versions, migration guide links and a verdict. PEP 440 versions ('1.10.13', '2.0')

Real-time web search for AI agents. Search the web for current and up-to-date information, news, facts, research, documentation, and sources beyond model training data. Returns ranked structured JSON results with title, URL, description, and position for web grounding, RAG retrieval, research, and fact-finding. Send query, optional limit, and optional freshness as URL parameters. Keyless x402 pay-

Checks an x402 API origin the way x402scan, the CDP Bazaar and agents read it: fetches /openapi.json and /.well-known/x402, then calls each paid route without paying (up to 30) and decodes its 402. Reports routes that do not answer 402, missing or v1-only PAYMENT-REQUIRED headers, prices that differ from the OpenAPI document, resource URLs that differ from the route, wrong USDC EIP-712 domains, mi

Multi-page research brief with cited sources. Crawl one URL and follow its links, or pass a list of URLs, and get a synthesized answer to your question as JSON with a sources array, optionally shaped by your JSON Schema. Use it to compare several pages, gather a list across a site, summarise a topic from multiple sources, or answer a question that spans documents. Up to 8 pages per call, typically

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.

Complete, ready-to-send Letter of Inquiry: funder and project in, a one-page LOI out — researched against the funder's actual stated priorities and mirroring their language, with every organisation-specific fact left as a [BRACKETED] placeholder (never invented), alignment points listed, and an honest funder-fit read. The document that gets you invited to submit a full proposal. Works for foundati

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.

Federal Register search, deterministic. Answers "new SEC rules on stablecoins", "is there an open comment period on AI", "when does this rule take effect". Full-text search over every US federal rule, proposed rule and notice, with effective dates, comment deadlines and docket ids — or mode=open-comments for comment periods closing soonest. Typed documents straight off the official API. No LLM, no

US federal regulation search — find Federal Register rules, proposed rules, notices and presidential documents by full text, agency, type, date, docket, RIN, significance or CFR part, with abstract, effective date, comment deadline and official links for each. Use to check whether a rule exists on a subject, what an agency has issued, or when a comment period closes.

Incoterms 2020 decoder for trade and import-export agents. Returns a plain-English explanation of any Incoterm with buyer/seller obligation split, risk transfer point, documentation checklist, and insurance guidance.

About page discovery repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.