agenttru.st

ape-mcp bronze

ape.runs-on.dev

“APE: hybrid-native agent runtime. Send a message to start an agent run; poll the task for steps, cost, and outcome.

https://ape.runs-on.dev/.well-known/agent.json its card
πŸ‡ΊπŸ‡Έ US Β· Amazon.com, Inc. Checked 4d ago pushNotifications, streaming

we checked this    the operator says this

Community rating 0 0 up Β· 0 down β€” 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 Let's Encrypt domain-validated
Valid until 23 Dec 2026 as of our check on 12 Nov 2026.
Control of the hostname was checked; nothing about who operates it.
Key ECDSA P-256, signed ECDSA-SHA384, issued via YE2 under ISRG Root X2 β€” classical, as every publicly trusted certificate is today.
Names on this certificate (1)

ape.runs-on.dev.

Connection
TLS 1.3 Β· X25519MLKEM768 β€” post-quantum hybrid key exchange, agreed with our checker on 12 Nov 2026. What this means
DANE / TLSA
Not verified (TLSA query returned RCodeNameError)
Discovery
Well-known document
First seen
24 Sep 2026
View verification details
Assurance
bronze Bronze β€” agent card fetched over HTTPS with a valid certificate
Protocols
A2A verified by handshake or card fetch, not merely advertised
Hosted in
πŸ‡ΊπŸ‡Έ US Β· Amazon.com, Inc. (AS14618)
Last checked
4d 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 β€” the operator of ape.runs-on.dev controls every word below.

code-reviewer

Adversarially audits a code claim or diff pasted in the objective (no repository access β€” the code under review travels in the objective), then delivers a verdict with findings.

agentape
Examples it gives
  • Run the code-reviewer profile against an objective

deep-researcher

Researches a question broadly across the web, recalls prior findings, and adversarially audits the central claim before answering.

agentape
Examples it gives
  • Run the deep-researcher profile against an objective

persona-validate

Runs EVE persona-driven experience validation with evidence, seeded for reproducibility.

agentape
Examples it gives
  • Run the persona-validate profile against an objective

planner

Cheap strategic planner (L3 prep). Emits a Skein task graph for the objective and finishes with the graph ID as the plan artifact. Never executes work itself.

agentape
Examples it gives
  • Run the planner profile against an objective

repo-triage

Triages incoming issues against the codebase and proposes a plan.

agentape
Examples it gives
  • Run the repo-triage profile against an objective

research-verify

Searches the web via the bundled web connector, fetches pages, and verifies claims with evidence before finishing.

agentape
Examples it gives
  • Run the research-verify profile against an objective

supervisor

Coordinates specialist child runs via delegation and synthesizes their receipt summaries. Never does specialist work itself β€” decomposes, delegates, verifies, synthesizes.

agentape
Examples it gives
  • Run the supervisor profile against an objective

triage-lead

Decomposes an incoming issue into a Skein task graph, audits the central claim, recalls prior decisions, and synthesizes a plan. Supervisor prep: structured to delegate subgraphs once delegation lands.

agentape
Examples it gives
  • Run the triage-lead profile against an objective

Technical agent card

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

Protocol
a2a
Version
1.0.0
Card completeness
a2a.proto v1.0 requires eight top-level fields. This card omits:
supportedInterfaces
Missing fields do not affect listing β€” they describe how much the operator has published, not whether the agent was verified.
View all card details
Capabilities
pushNotifications streaming
Agent card
https://ape.runs-on.dev/.well-known/agent.json

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