--- title: Google and Industry Partners Announce Agentic Resource... description: Google and industry partners including Microsoft, GitHub, Hugging Face, Cisco, NVIDIA, and Salesforce have announced the Agentic Resource Discovery (ARD)... canonical: https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents | daily.dev og:description: Google and industry partners including Microsoft, GitHub, Hugging Face, Cisco, NVIDIA, and Salesforce have announced the Agentic Resource Discovery (ARD)... og:url: https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx og:image: https://api.daily.dev/og/posts/KkVgDNSbX.png og:image:alt: Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents **[InfoQ](https://daily.dev/sources/infoq)** · 3 min read · 1 upvotes · 0 comments ## Summary Google and industry partners including Microsoft, GitHub, Hugging Face, Cisco, NVIDIA, and Salesforce have announced the Agentic Resource Discovery (ARD) Specification — an open standard for AI agents to publish, discover, and verify tools, APIs, and services across organizational boundaries. ARD introduces a discovery layer using machine-readable `ai-catalog.json` files and registries that aggregate catalogs, enabling agents to search by task intent rather than hardcoded integrations. It complements existing protocols like MCP and OpenAPI by addressing the earlier lifecycle stage of capability discovery. Trust and domain-based verification are built into the design. Early implementations include GitHub's Agent Finder in Copilot and Hugging Face's Discover Tool. The spec is open and available with reference implementations on GitHub. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the Agentic Resource Discovery (ARD) specification and how does it differ from MCP? ARD is an open standard for AI agents to publish, discover, and verify external tools, APIs, and services across organizational boundaries. Unlike the Model Context Protocol, which defines how an agent invokes a tool it already knows about, ARD addresses an earlier stage: how agents find those tools in the first place, using catalogs and registries rather than hardcoded integrations. _Engineers designing agent discovery layers can track ARD adoption and MCP interplay on daily.dev._ ### Which companies contributed to the Agentic Resource Discovery specification? Contributors include Google, Microsoft, GitHub, Hugging Face, Cisco, Databricks, GoDaddy, NVIDIA, Salesforce, ServiceNow, and Snowflake. Early implementations already exist, such as GitHub's Agent Finder in Copilot and Hugging Face's Discover Tool, both using ARD for runtime capability discovery. _Teams evaluating multi-vendor agent tooling can follow ARD adoption news on daily.dev._ ### How does the ai-catalog.json file work in the ARD specification? Organizations publish a machine-readable ai-catalog.json file within their domain describing available capabilities like tools, APIs, skills, and agent endpoints. Registries then aggregate these catalogs, letting agents search by task intent rather than relying on static endpoint lists, while domain-based ownership and verification mechanisms let agents confirm resource authenticity before connecting. _Developers building capability catalogs for agents can follow ARD implementation details on daily.dev._ ## Similar posts on daily.dev - [Announcing the Agentic Resource Discovery specification](https://daily.dev/posts/announcing-the-agentic-resource-discovery-specification-nlrmganhc) · Google Developers · 0 upvotes · 0 comments - [MCP was supposed to solve the agent tooling problem. It missed a step.](https://daily.dev/posts/mcp-was-supposed-to-solve-the-agent-tooling-problem-it-missed-a-step--ie52iqlyo) · The New Stack · 1 upvotes · 0 comments - [Agent finder for GitHub Copilot now available](https://daily.dev/posts/agent-finder-for-github-copilot-now-available-3vpyld8tc) · GitHub Changelog · 1 upvotes · 0 comments - [Microsoft Discovery: Advancing agentic R&D at scale](https://daily.dev/posts/microsoft-discovery-advancing-agentic-r-d-at-scale-p4wd9khzf) · Microsoft Azure · 4 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#architecture](https://daily.dev/tags/architecture), [#mcp](https://daily.dev/tags/mcp), [#openapi](https://daily.dev/tags/openapi) [View this post on daily.dev](https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents","url":"https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx"},"datePublished":"2026-07-14T13:43:42.539Z","dateModified":"2026-09-14T08:52:34.554Z","description":"Google and industry partners including Microsoft, GitHub, Hugging Face, Cisco, NVIDIA, and Salesforce have announced the Agentic Resource Discovery (ARD)...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4ad8d8dff5ff59728f5db265cad5feae?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4ad8d8dff5ff59728f5db265cad5feae?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoQ","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoQ","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/afc3bced3e1e4b188dd9127017a60e0c","url":"https://daily.dev/sources/infoq"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,architecture,mcp,openapi","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoQ","item":"https://daily.dev/sources/infoq"},{"@type":"ListItem","position":3,"name":"Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/google-and-industry-partners-announce-agentic-resource-discovery-specification-for-ai-agents-kkvgdnsbx#faq","mainEntity":[{"@type":"Question","name":"What is the Agentic Resource Discovery (ARD) specification and how does it differ from MCP?","acceptedAnswer":{"@type":"Answer","text":"ARD is an open standard for AI agents to publish, discover, and verify external tools, APIs, and services across organizational boundaries. Unlike the Model Context Protocol, which defines how an agent invokes a tool it already knows about, ARD addresses an earlier stage: how agents find those tools in the first place, using catalogs and registries rather than hardcoded integrations. Engineers designing agent discovery layers can track ARD adoption and MCP interplay on daily.dev."}},{"@type":"Question","name":"Which companies contributed to the Agentic Resource Discovery specification?","acceptedAnswer":{"@type":"Answer","text":"Contributors include Google, Microsoft, GitHub, Hugging Face, Cisco, Databricks, GoDaddy, NVIDIA, Salesforce, ServiceNow, and Snowflake. Early implementations already exist, such as GitHub's Agent Finder in Copilot and Hugging Face's Discover Tool, both using ARD for runtime capability discovery. Teams evaluating multi-vendor agent tooling can follow ARD adoption news on daily.dev."}},{"@type":"Question","name":"How does the ai-catalog.json file work in the ARD specification?","acceptedAnswer":{"@type":"Answer","text":"Organizations publish a machine-readable ai-catalog.json file within their domain describing available capabilities like tools, APIs, skills, and agent endpoints. Registries then aggregate these catalogs, letting agents search by task intent rather than relying on static endpoint lists, while domain-based ownership and verification mechanisms let agents confirm resource authenticity before connecting. Developers building capability catalogs for agents can follow ARD implementation details on daily.dev."}}]} ```