Anyray bronze

anyray.ai

“Self-hosted AI gateway that cuts LLM-inference spend with real-time call optimization, spend visibility and governance, and full prompt/response privacy. Exposes an OpenAI-compatible API in front of OpenAI, Anthropic, Vertex AI, Bedrock, and Azure, and runs entirely in the customer's own environment.

a2a https://docs.anyray.ai/developers/api-reference talk to it https://anyray.ai/.well-known/agent-card.json its card

🇺🇸 US · Amazon.com, Inc. Checked 5d ago pushNotifications, stateTransitionHistory, streaming

we checked this the operator says this

Community rating 0 0 up · 0 down — sign in to vote

Verified by agenttru.st

Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.

Certificate: Issued by Amazon domain-validated
Valid until 21 Dec 2026.

Control of the hostname was checked; nothing about who operates it.
DANE / TLSA: Not verified (TLSA query returned RCodeNameError)
Discovery: Well-known document
First seen: 29 Aug 2026

View verification details

Assurance: bronze Bronze — agent card fetched over HTTPS with a valid certificate
Protocols: A2A verified by handshake or card fetch, not merely advertised
Hosted in: 🇺🇸 US · Amazon.com, Inc. (AS16509)
Last checked: 5d ago

What this agent says it can do

Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of anyray.ai controls every word below.

Optimized chat completions

Proxy an OpenAI-compatible chat-completions request to the configured provider, applying real-time optimization (prompt and context compression, tool pruning, semantic cache) before forwarding. Supports streaming responses.

llmopenai-compatiblegatewaycost-optimization

Examples it gives

POST /v1/chat/completions with an OpenAI-format body to any routed provider model.

Embeddings

Proxy an OpenAI-compatible embeddings request to the configured provider through the gateway.

llmopenai-compatibleembeddings

Examples it gives

POST /v1/embeddings with an OpenAI-format body.

Spend attribution and governance

Every request is attributed (user, team, model, provider, tokens, cost, latency, decision) into a content-free spend store for per-user and per-team governance.

observabilitycostgovernance

Examples it gives

Inspect attributed spend per user and team in the self-hosted console.

Technical agent card

Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.

Provider: Anyray — what this agent says about itself; other agents claiming the same provider are not thereby related
Protocol: a2a
Version: 1.0.0
Auth schemes: apiKey
Card completeness: a2a.proto v1.0 requires eight top-level fields. This card omits:
supportedInterfaces

Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.

View all card details

Capabilities: pushNotifications stateTransitionHistory streaming
Agent card: https://anyray.ai/.well-known/agent-card.json

Operate this agent and would rather not be listed? Request removal.