{
 "url": "https://agenticweb.wiki/about/",
 "title": "About agenticweb.wiki & Belgravia Labs · agenticweb.wiki",
 "description": "agenticweb.wiki is built and maintained by Belgravia Labs; how the records are made and how to send a correction.",
 "markdown_url": "https://agenticweb.wiki/about/index.md",
 "markdown": "# About\n\nagenticweb.wiki is an open reference map and conformance engine for the agentic web's standards layer, built and maintained by Belgravia Labs under CC BY 4.0 (data) and MIT (schemas & probe rules). It tracks 132 standards across 9 lifecycle steps, 52 glossary terms, and 325 verified instances, with primary-source citations and executable probe rules.\n\n## What agenticweb.wiki covers\n\nagenticweb.wiki is a reference for the standards that let software agents use the web: how an agent finds what a site offers, proves who it is, learns what it may do, reads, acts, coordinates with other agents, pays, shows a person the result, and is held to account. Each standard has an article written from its primary specification, with a numbered reference for every claim, an honest status line in the issuer's own words, and a record of what has actually been observed in the wild. Where a category has no standard yet, the article says so.\n\n## Machine-native endpoints (MCP, API & OKF)\n\nAlongside the articles, the site serves a live [domain readiness checker](/check/) across 37 agent-facing specifications and discovery paths, side-by-side [protocol comparisons](/compare/), a cited [daily digest](/digest/), and a stateless [Model Context Protocol server](/connect/) (https://agenticweb.wiki/mcp) and [Open Knowledge Format](/okf/index.md) index so agents can query the map directly. Every page is served three ways at one address: HTML, a Markdown twin (<page>/index.md or Accept: text/markdown), and structured JSON (<page>/index.json or [bulk exports](/data/)).\n\n## Protocol observatory & compliance charter\n\nagenticweb.wiki operates as an open protocol and standards observatory — analogous to CanIUse, Qualys SSL Labs, and W3Techs — never a content scraper:\n\n- RFC 9309 /robots.txt gatekeeper first: every probe fetches /robots.txt before any other path. If User-agent: agenticweb-probe is disallowed globally, the probe stops with zero further requests; if specific content paths (such as /llms.txt or /okf/index.md) are disallowed in /robots.txt, those paths are skipped and recorded as disallowed_by_robots_txt.\n\n- RFC 8615 fixed front-door URIs only: probes check only a fixed list of 37 well-known capability and policy probe rules (/.well-known/*, /robots.txt, /llms.txt, /AGENTS.md, /auth.md, /okf/index.md, and root transport headers). We never spider internal pages, articles, or product catalogs.\n\n- In-memory validate-and-discard: response bodies are parsed in RAM solely to verify structural conformance and compute readability ratios, then immediately discarded. Zero third-party page or manifest bodies are stored on disk or redistributed (aligned with EDPB Guidelines 03/2026 v1.0 consultation draft).\n\n- Transparent cryptographic identity (RFC 9421): our probe identifies itself as agenticweb-probe/1 (+https://agenticweb.wiki/about/) and publishes its Ed25519 verification key directory at [/.well-known/http-message-signatures-directory](/.well-known/http-message-signatures-directory).\n\n## Who makes it & editorial methodology\n\nWho makes it: agenticweb.wiki is built and maintained by the Belgravia Labs Standards & Protocol Observatory ([Belgravia Labs](https://belgravialabs.com)). The open dataset, JSON schemas, probe rules, and issue tracker are hosted on GitHub at [Belgravia-Labs/agenticweb-data](https://github.com/Belgravia-Labs/agenticweb-data). Contact: [info@belgravialabs.com](mailto:info@belgravialabs.com) · [Terms of use & licensing](/terms-of-use/).\n\nHow the records are produced is set out in full on the [methodology page](/methodology/): each record is drafted from primary sources under a fixed brief, every evidence label is assigned per source, external URLs are link-checked on a recurring schedule, and an adversarial review re-checks a sample before publish.\n\n## Corrections & submissions\n\nCorrections and listing requests: use the [submit page](/submit/) or email [info@belgravialabs.com](mailto:info@belgravialabs.com). Automated updates appear on [/changes/](/changes/) and every record's history is on the [changelog](/changelog/) with a date.\n\n[Markdown](/about/index.md) · [JSON](/about/index.json) · [Methodology](/methodology/) · [Data & API](/data/)\n\n## Frequently asked questions\n\n- **Who builds and maintains agenticweb.wiki?**: agenticweb.wiki is built and maintained by Belgravia Labs. It tracks 132 agentic-web standards across 9 lifecycle steps, 52 glossary terms, and 325 verified instances under CC BY 4.0 (dataset) and MIT (code and MCP server).\n- **How are standards and instances verified on agenticweb.wiki?**: Every protocol and term article is drafted from primary specifications with numbered citations, explicit evidence labels (VERIFIED, REPORTED, or THIN), and executable HTTP probe rules where applicable. Origin instances are verified by live /check/ conformance scans against published manifests.\n- **How can an AI agent query agenticweb.wiki programmatically?**: Agents can connect to the stateless Streamable HTTP MCP server at https://agenticweb.wiki/mcp (11 read and live-probe tools, no authentication required), fetch Markdown twins at <page>/index.md or via Accept: text/markdown, read the Open Knowledge Format bundle at https://agenticweb.wiki/okf/index.md, or download bulk JSON/NDJSON/CSV exports under https://agenticweb.wiki/data/.\n"
}