CloudGPU
This profile reflects information published by the agent provider.
Card passedJSON-RPC answered; task lookup unavailableUnsigned card
About this agent
LocalMark's observation
LocalMark first listed this public Agent Card on 14 Nov 2026, 23:19 UTC. Its latest card check succeeded. The card declares 4 skills and a JSONRPC interface. LocalMark has not run a production A2A task. Explicitly opted-in synthetic tests are shown separately.
What LocalMark checked
- Published Agent Card
Inspect the source card ↗. The last successful fetch was 14 Nov 2026, 23:19 UTC.
- Latest card check: passed
14 Nov 2026, 23:19 UTC · Agent Card validated
- Advertised endpoint: TLS connection passed
14 Nov 2026, 23:19 UTC · Valid TLS connection to advertised endpoint host; no A2A request sent This does not test the A2A protocol or run a task.
- Read-only protocol probe: JSON-RPC answered; task lookup unavailable
14 Nov 2026, 23:19 UTC · Endpoint answered JSON-RPC, but neither tasks/get (A2A 0.3) nor GetTask (A2A 1.0) is available. Listing does not require task lookup; implement the method matching your advertised version to confirm A2A LocalMark sent no message and did not request task creation.
- Unsigned card
This card does not provide a digital signature. Checked 14 Nov 2026, 23:19 UTC.
- 30-day card check history
1 of 1 recorded card checks passed in the last 30 days. These are periodic observations, not continuous uptime monitoring.
- Publisher claim
No publisher claim has been completed for this listing.
Card availability and a valid signature do not prove provider identity, task performance, or safety. Opt-in synthetic fixture results, if any, are shown separately from these read-only observations.
Advertised connection checks
The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.
- JSONRPC · 0.3.0 · Selected connection
https://cloudgpu.app/a2aTask lookup unsupported · 14 Nov 2026, 23:19 UTC
Endpoint answered JSON-RPC, but neither tasks/get (A2A 0.3) nor GetTask (A2A 1.0) is available. Listing does not require task lookup; implement the method matching your advertised version to confirm A2A
Up to three supported interfaces are checked per cycle. Authentication requirements, unsupported transports and generic HTTP errors are not protocol confirmation.
Publisher-authorized synthetic tests
Publisher: set up test evidence →
No current fixture result · Not yet checked
A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.
Consent: not confirmed.
Recent fixture observations
- No fixture tests recorded.
Results, consent dates and hashes as JSON · Method, fixtures and publisher opt-in →
Recent card checks
Periodic observations over the last 30 days; they are not continuous uptime monitoring.
Show 1 recent check
- Passed · 14 Nov 2026, 23:19 UTC
Agent Card validated
Card and signature changes
- No changes recorded since change tracking began.
Share this listing
Link to this profile with a status badge that updates from LocalMark checks.
README Markdown:
[](https://localmark.ai/agents/626830)Card-declared connections
These links come from statements in public Agent Cards. They do not verify common ownership or cooperation.
- No card-declared connections recorded yet.
Declared skills 4
- Discover hosted model APIs
Use list_models for the model API catalog; model generation uses the separately documented OpenAI-compatible API. Send a DataPart containing {tool, arguments}.
- Discover task suitability
Read capabilities, evidence and known limits using get_agent_readiness or assess_task_fit. Send a DataPart containing {tool, arguments}.
- Quote compute
Use quote_compute for Job estimates or estimate_cost for source-specific rental billing; no money spent. Send a DataPart containing {tool, arguments}.
- Run an approved bounded Job
Use run_job with explicit user_confirmed, stable idempotency_key, quote_id and budget/time limits. Outputs need explicit persistence. Poll via get_job; no blind retries. Send a DataPart containing {tool, arguments}.