--- type: Agentic Web Standard title: "Agent Directory Service" description: "Given a required skill, which agents provide it, where are they, and how can I fetch a verifiable, content-addressed record describing them?" resource: "https://datatracker.ietf.org/doc/html/draft-mp-agntcy-ads-02" tags: ["discover", "endpoint", "linux-foundation", "describe-agent-capabilities", "discover-my-api", "agent-to-agent-messaging", "agent-naming"] status: draft generated: { by: agenticweb-builder/1.0, at: 2026-10-30T00:00:00Z } verified: { by: process:agenticweb-engine, at: 2026-10-29T00:00:00Z } stale_after: 2026-11-28T00:00:00Z sources: - id: ref-1 resource: "https://datatracker.ietf.org/doc/html/draft-mp-agntcy-ads-02" title: "draft-mp-agntcy-ads-02 (6 July 2026) defines ADS as a distributed directory service storing agent metadata as content-addressed OCI artifacts, discoverable via a DHT keyed on a skill taxonomy, and exposes an AI Finder service over gRPC and REST (GET /v1/agents, GET /v1/agents/{cid}, GET /v1/agents/{cid}/export, GET /.well-known/ai-catalog.json) that is explicitly interoperable with the AI Catalog / ARD ecosystem." last_modified: 2026-07-06T00:00:00Z - id: ref-2 resource: "https://blogs.agntcy.org/technical/2026/06/17/ai-catalog-over-directory.html" title: "AGNTCY published a technical note describing AI Catalog interoperability layered over its directory service." last_modified: 2026-06-17T00:00:00Z --- # Agent Directory Service Agent Directory Service (ADS) is an agentic-web standard (endpoint — /v1/agents) at step 1, Discover, governed by AGNTCY project; its status is "Internet-Draft". It answers: "Given a required skill, which agents provide it, where are they, and how can I fetch a verifiable, content-addressed record describing them?" Implementation status is shipping, last verified 2026-10-29. # Overview The Agent Directory Service (ADS) is a distributed directory for storing and discovering metadata about AI agent applications, structured as records that can be searched by the skills they claim to provide [^ref-1]. It originates from AGNTCY (an Outshift/Cisco-led project now positioned under the Linux Foundation) and is written up as an individual IETF Internet-Draft, revision -02, dated 6 July 2026, with its living canonical text tracked outside the IETF at spec.dir.agntcy.org and source at github.com/agntcy/dir [^ref-1]. ADS solves agent discovery at scale using content-addressed storage: each agent record is packaged as an OCI-compliant artifact (reusing container-registry infrastructure and its manifest/layer model) and identified by a content ID (CID) derived from a cryptographic digest [^ref-1]. Records are indexed into a distributed hash table keyed by a multi-level skill taxonomy (plus domain and module taxonomies), so a query for a capability resolves to the CIDs and peer IDs of agents that claim it, without a central registry [^ref-1]. Distribution between directory nodes happens over the OCI protocol's peer-to-peer synchronization [^ref-1]. Distinct from the DHT-based global layer, ADS also runs a host-local "AI Finder" service, exposed over gRPC and, via a gateway, as a REST API: `GET /v1/agents` lists catalog entries with deterministic pagination, `GET /v1/agents/{cid}` retrieves one entry, `GET /v1/agents/{cid}/export` renders a stored OASF record into other ecosystems' native formats (a2a, agent-skill, mcp-ghcopilot), and `GET /.well-known/ai-catalog.json` serves the host's catalog document at the well-known URI this project explicitly designed to interoperate with the ARD/AI Catalog ecosystem [^ref-1]. The export operation is described as ADS's "heterogeneity bridge" -- one canonical OASF record materialized into several downstream protocols' native card formats without changing its underlying storage representation [^ref-1]. ADS does not define its own agent capability schema from scratch; it uses the separately-maintained Open Agentic Schema Framework (OASF, see `oasf`) as its native record format, and treats other ecosystems' formats (A2A cards, MCP server descriptors) as export targets rather than first-class stored types [^ref-1]. Current state: the draft was published 6 July 2026 and expires 7 January 2027; it explicitly states it is "to be removed before publishing as an RFC," i.e. still a working draft rather than a finished document [^ref-1]. Unlike several other records on this map, this one has a concrete, buildable open-source implementation (github.com/agntcy/dir) referenced directly from the spec text, which supports recording implementation as "shipping" -- but no independent count of production deployments or registered agents was located, so adoption remains unmeasured. What is disputed or unknown: how ADS's DHT-based global layer interacts in practice with a search-first, centralized-registry model like ARD's -- the "AI Catalog Interoperability" section of the draft describes projection and export, but whether third parties beyond AGNTCY's own tooling actually consume ADS-hosted records via the ai-catalog.json path was not independently verified here. # Examples ```http GET https://{origin}/v1/agents # parse: 200 response is a paginated JSON list of CatalogEntry records; a companion GET /.well-known/ai-catalog.json returns the host's WellKnownCatalog document # on absent: Host does not run an AGNTCY ADS AI Finder REST gateway; the record may still exist in the distributed hash table without a host-local HTTP surface ``` # Knowledge Graph * **Lifecycle Step**: [1 Discover](/category/discover/index.md) * **Builds on**: [Open Agentic Schema Framework](/okf/protocols/oasf.md) * **Pairs with**: [Open Agentic Schema Framework](/okf/protocols/oasf.md), [Agentic Resource Discovery (ARD)](/okf/protocols/ard.md), [AI Catalog well-known file](/okf/protocols/ai-catalog-well-known-file.md), [Agent2Agent Protocol (A2A)](/okf/protocols/a2a.md), [Model Context Protocol](/okf/protocols/mcp.md), [GB/Z 185 Artificial intelligence — Agent interconnection](/okf/protocols/gbz-185-agent-interconnection.md) * **Compared in**: [DNS (A/SRV) & WHOIS vs AID & DNS-AID (classic vs agentic)](/compare/dns-whois-vs-aid/index.md) [^ref-1]: draft-mp-agntcy-ads-02 (6 July 2026) defines ADS as a distributed directory service storing agent metadata as content-addressed OCI artifacts, discoverable via a DHT keyed on a skill taxonomy, and exposes an AI Finder service over gRPC and REST (GET /v1/agents, GET /v1/agents/{cid}, GET /v1/agents/{cid}/export, GET /.well-known/ai-catalog.json) that is explicitly interoperable with the AI Catalog / ARD ecosystem. (https://datatracker.ietf.org/doc/html/draft-mp-agntcy-ads-02) [^ref-2]: AGNTCY published a technical note describing AI Catalog interoperability layered over its directory service. (https://blogs.agntcy.org/technical/2026/06/17/ai-catalog-over-directory.html)