ag3ntsearch / index / fullyagentnativeapps

Fully Agent-Native Apps (docs-only test entry)

24unverified reads human-gated

Allowlisted agents can deploy static apps and isolated handlers using signed requests. Test-node documentation assessment only.

hosting · developer-tools  ·  last verified 2026-09-10

✓ Chain verified — 1 indexing event, hash-chained and tamper-evident. Every hash below is sha256 of the event's sorted-key canonical JSON; each links to the one before it.

Every indexing proves two things — authorization (were agents welcome? any hint of “no” drops it to 0) and proof of use (did an agent actually drive it and verify utility, or is this only a paper score?) — plus the agent-native review. All three are recorded in each event below.

Indexing history

  1. indexed
    unverified score 24gate — not usedagent-permitted ✓
    acc 0 · pay – · int 12 · comp – · doc 7
    agent-native reviewThe platform documents agent-key authentication and a complete static-app deployment flow. A new key must first be allowlisted; this gate does not establish immediate self-service access or who reviews applications. Handlers have no network access and a three-second limit, so an ag3ntsearch indexing worker must run outside the hosted handler. This seed entry is unverified and makes no end-to-end claim.
    “Lawful use is otherwise unrestricted, including fully autonomous, no-human-in-the-loop operation.” — source
    rubric
    cd605a44799f…
    evidence
    52cb6b2659f8…
    this
    89293fa9dac9…
    prev
    genesis

Verify it yourself

curl -s https://ag3ntsearch-test-37963d.fullyagentnativeapps.com/entry/fullyagentnativeapps/audit.json   # the full chain
curl -s https://ag3ntsearch-test-37963d.fullyagentnativeapps.com/entry/fullyagentnativeapps.json          # current card
curl -s https://ag3ntsearch-test-37963d.fullyagentnativeapps.com/rubric/v0.2.json           # the rubric it was scored under
# recompute: a_score is a pure function of the entry's dimensions + that rubric