Skip to content
AgenID / The agent ecosystem

The Agent Ecosystem

AgenID is designed to work across the platforms where AI agents live. Your agent can change platforms. Its identity shouldn’t have to.

An agenid:<ULID> identifies the agent and the party accountable for it — never the model, framework, or host underneath. That is what makes this list possible: nothing in the protocol references any vendor on it.

WHAT A LISTING MEANS

Three statuses. Only one of them is currently issued.

Compatible25 entries

Identity can be carried through this platform today using its existing, documented API surface. No AgenID-specific code is required from the platform, and none is claimed to exist.

Verified Integration0 entries

AgenID has executed the integration end to end and published the result. Not asserted for any entry yet.

Official Partner0 entries

A partnership is on record with the platform. Not asserted for any entry yet.

Every entry below is Compatible and nothing more. No platform on this page ships AgenID code, and no adapter package exists for any of them. A listing is a technical statement about how an identity travels through a platform’s existing, documented API surface — it is not an endorsement, a partnership, or a relationship of any kind. All product names and marks belong to their respective owners.

ONE IDENTITY, MANY PLATFORMS

The platforms change. The identity doesn’t.

IDENTITY PERSISTENCE
manifest_digest sha-256:9f2c…a41d · unchanged at every hop
agenid:01J8Z3K3F2QZ9X6V7R4T8N2W5Y
VOICE
Retell · custom-LLM webhook
MODELS
OpenAI · model call
INFRASTRUCTURE
Cloudflare · edge verify

The identifier and the signed manifest_digest are the same bytes at every hop — the operator’s manifest names the agent and who is accountable for it, never the vendor underneath. Each hop can re-verify the Ed25519 signature offline before it acts, without calling AgenID and without trusting the platform it received the identity from. Stages are illustrative of the layers in the registry below, not a record of an executed hand-off.

COMPATIBILITY MATRIX

25 platforms across 5 layers.

Every platform in the registry.

25 of 25 platforms

Bland AI

Voice

Outbound and inbound AI phone calls

CompatibleCall request metadata + webhook

Identity is attached to the call request's metadata object and returned on the completion webhook, where it is resolved and re-verified out-of-band.

ElevenLabs

Voice

Voice synthesis and conversational agents

CompatibleAgent client data + tool-call metadata

Identity is carried as client/dynamic variables on the conversational-agent session and echoed into tool calls, where the operator's tool endpoint re-verifies the signed manifest proof.

Retell

Voice

Conversational voice AI platform

CompatibleCustom LLM webhook + post-call webhook

The agenid:<ULID> travels in the custom-LLM request/response payload and the post-call webhook body; verification runs in the operator's own webhook handler with @agenid/core. Retell ships no AgenID-specific code.

Synthflow

Voice

No-code voice assistant builder

CompatibleCustom action headers + webhook payload

Compatible through the generic pattern only: the identifier is passed as a custom-action header or payload field. No platform-specific brief has been written or tested.

Platform site ↗reviewed 2026-09-13

Vapi

Voice

Developer voice agent platform

CompatibleAssistant metadata + server-message webhook

The identifier rides in assistant metadata and every server message; the operator's server verifies the ManifestProof before acting on a call event.

Anthropic

Models

Claude model family and Agent SDK

CompatibleModel-agnostic — identity sits above the model call

Same construction as any other model provider: the manifest names the operator and the agent, never the underlying model. Changing provider does not change the identity or invalidate an existing proof.

Platform site ↗reviewed 2026-09-13

Google Gemini

Models

Gemini model family

CompatibleModel-agnostic — identity sits above the model call

Listed for completeness of the model layer. No Gemini-specific surface is required or used by the protocol.

Platform site ↗reviewed 2026-09-13

Meta Llama

Models

Open-weight model family

CompatibleModel-agnostic — identity sits above the model call

Self-hosted inference is fully compatible; the protocol has no hosted-API dependency of any kind.

Platform site ↗reviewed 2026-09-13

Mistral AI

Models

Open-weight and hosted models

CompatibleModel-agnostic — identity sits above the model call

Including self-hosted open-weight deployments: identity is a property of the operator and the agent, not of where inference runs.

Platform site ↗reviewed 2026-09-13

OpenAI

Models

GPT model family and Agents SDK

CompatibleModel-agnostic — identity sits above the model call

AgenID never references a model provider. An agent keeps one agenid:<ULID> across a switch of model vendor; the identifier is carried by the operator's own request context, not by the model API.

Platform site ↗reviewed 2026-09-13

xAI Grok

Models

Grok models and Grok bot surfaces

CompatibleBot profile disclosure + resolver link

The documented pattern publishes the agenid:<ULID> in the bot's own profile/disclosure surface so a reader can resolve and verify it independently. Nothing is enforced by the platform.

AWS

Infrastructure

Cloud compute and hosting

CompatibleHosting for operator key documents and agent runtimes

Runtime-neutral. Relevant only as a place an operator hosts the agent, its key document, or its own verification endpoint.

Platform site ↗reviewed 2026-09-13

Cloudflare

Infrastructure

Edge compute, Workers, and DNS

CompatibleWell-known key hosting + edge verification

Two roles: DNS TXT records satisfy the L2 domain-control evidence type, and /.well-known/agenid/keys.json can be served from Workers or Pages as the domain path of two-path key discovery.

Platform site ↗reviewed 2026-09-13

Google Cloud

Infrastructure

Cloud compute and hosting

CompatibleHosting for operator key documents and agent runtimes

Runtime-neutral, same as any other host.

Platform site ↗reviewed 2026-09-13

Microsoft Azure

Infrastructure

Cloud compute and hosting

CompatibleHosting for operator key documents and agent runtimes

Runtime-neutral, same as any other host. Route 'is this agent verified' checks through @agenid/core in the operator's own service.

Platform site ↗reviewed 2026-09-13

Vercel

Infrastructure

Edge/serverless application hosting

CompatibleHosting for resolvers, key documents, and badge embeds

The AgenID reference resolver itself runs here, which makes it a tested host for the read path — not a protocol dependency.

Platform site ↗reviewed 2026-09-13

AutoGen

Frameworks

Multi-agent conversation framework

CompatibleAgent metadata passed between participants

Compatible through the generic pattern only. No framework-specific brief has been written or tested.

Platform site ↗reviewed 2026-09-13

CrewAI

Frameworks

Multi-agent orchestration

CompatibleAgent metadata passed between crew members

Compatible through the generic pattern: each crew member carries its own agenid:<ULID> in agent metadata so inter-agent calls can be verified. No framework-specific brief has been written or tested.

Platform site ↗reviewed 2026-09-13

LangChain

Frameworks

Agent orchestration and LangGraph

CompatibleCallback/config metadata threaded through the graph

The identifier is carried in the run configuration and surfaced on tool boundaries, so a downstream tool can resolve and verify the calling agent before it executes.

Model Context Protocol

Frameworks

Open tool/context protocol for agents

CompatibleServer metadata + @agenid/mcp-server tools

@agenid/mcp-server exposes resolution and verification as MCP tools, so any MCP-capable client can check an agent's identity. The package builds and tests in CI; it has not been published to npm (the @agenid scope is unclaimed).

OpenAI Agents SDK

Frameworks

Agent runtime and handoffs

CompatibleRun context + handoff metadata

Compatible through the generic pattern: identity persists across handoffs because it lives in the operator's run context, not in the SDK's session state. Not yet tested end to end.

Platform site ↗reviewed 2026-09-13

OpenClaw

Frameworks

Local agent gateway

CompatibleGateway-level identity header + verification hook

The documented pattern attaches the identifier at the gateway so every downstream agent call carries it. Pattern only — no adapter package exists.

Auth0

Enterprise Identity

Customer identity and access management

CompatibleComplementary — end-user identity, not agent identity

Auth0 identifies the human on the other side of the conversation. AgenID identifies the agent on this side of it.

Platform site ↗reviewed 2026-09-13

Microsoft Entra ID

Enterprise Identity

Enterprise identity and access management

CompatibleComplementary — workforce identity, not agent identity

Entra answers 'which principal is calling'. AgenID answers 'which agent is this, who is accountable for it, and what has been independently verified'. The two compose; neither replaces the other.

Platform site ↗reviewed 2026-09-13

Okta

Enterprise Identity

Enterprise identity and access management

CompatibleComplementary — workforce identity, not agent identity

Same composition as any IAM provider: authorize the service principal with Okta, resolve and verify the agent's provenance with AgenID.

Platform site ↗reviewed 2026-09-13

Building on a platform that isn’t listed?

Absence from this list is not a compatibility claim in either direction. The pattern is the same everywhere: attach an agenid:<ULID> to the agent’s existing config, sign a manifest with @agenid/core, and resolve it at /a/<agenid>. The registry itself lives at packages/web/data/ecosystem/ in AgenID-protocol/agenid, one reviewable JSON file per platform, validated in CI — a new entry is a pull request, and raising an entry above Compatible requires evidence in the same change.