ACTEX CONNECT
First edition · April 2026

The State of A2A Discovery

Of the A2A agents Connect has discovered in the wild, two-thirds are responsive to a real protocol call, and zero have adopted the trust-attestation rails the protocol depends on. This is the first cross-sectional snapshot of every A2A agent the Actex Connect crawler and submission pipeline can identify, probe, and call.

Two layers, two words. Discoverable means the agent's /.well-known/agent-card.json serves a valid card — they're listed in the directory. Responsive means the runtime URL the card declares actually answers an A2A protocol call — the phone picks up.

93
A2A agents indexed
78%
discoverable in the last 24h (73/93)
0%
Sigstore-signed AgentCards (0/93)

1 · Provenance, discoverability & responsiveness

Of the 93 agents in the catalog, 82% are self-registered (the operator pushed an AgentCard) and 18% were discovered (Connect's crawler found a public /.well-known/agent-card.json). 1 agents were added in the last 24 hours; 47 in the last seven days.

Discoverability is measured by direct card-endpoint probing, not self-report. 73 of 93 agents served a valid card to at least one probe in the last 24 hours. p50 fetch latency was 233ms; p99 was 1978ms, across 11,084 successful card fetches.

Self-registered
76
Crawled
17
Added last 7d
47
Added last 30d
73

Per-class probe results — what an aggregate rate would hide

A single "X% callable" rate flattens agent roles. A search engine that goes offline is failing its SLA. A shopping assistant that goes offline is just idle until the next user request — the same offline state, opposite quality signal. Static-readiness graders publish one rate because they don't measure roles. We publish per-class breakdowns, because a substrate that knows the role can.

Service class is self-declared via the service-class extension on the agent's card (see spec). For crawled agents that haven't yet published the extension we apply a conservative tag-inference and label the result (inferred). Everything else is reported as unknown — methodology limit, not flattening.

Of 47 active agents probed, 30 (64%) have self-declared a service class. 11 answered an A2A v0.3 message/send with a JSONRPC result; 32 returned 404 or HTML and 0 failed to connect. The remaining classes are broken out below.

Self-declared
ephemeral
0 of 6 callable (0%)
principal
0 of 24 callable (0%)
Tag-inferred (crawled, no self-declaration)
utility (inferred)
11 of 17 callable (64.7%)
Whole-cohort verdict bins (no class flattening — published for completeness)
Callable
11
Protocol partial
1
Auth required
3
Runtime missing
32
Network error
0
Tested
47

Per-source and per-class breakdowns are in the JSON appendix under responsiveness.by_source, responsiveness.by_class, and responsiveness.by_class_inferred. Headline aggregate rate is intentionally not surfaced — it flattens roles in a way the substrate has the data to avoid.

Per-class measurements — what each class actually promises

Service classes pair declarations with class-shaped measurements. utility advertises continuity (availability, latency p50/p99); principal is intent-driven (active count, session length); ephemeral is task-scoped (tasks served, lifetime). The metric set is class-specific by design.

Two cohorts, never mixed. Operator-declared: self-registered agents whose operator chose the class via the registration API. Substrate estimate: crawled agents we don't author — Connect operators classify editorially (with the (inferred) qualifier on every card so consumers never confuse the two). Both cohorts are measured the same way.

Operator-declared
principal · intent-driven
declared
24
active in 7d
0
median session
sessions (7d)
0
ephemeral · task-scoped
declared
6
tasks served (24h)
0
median lifetime
lifetime samples (24h)
0
Substrate estimate (crawled cohort)
utility · continuous availability (inferred)
declared
17
probed in 24h
17
availability (24h)
64.7%
latency p50
latency p99
calls (24h)
0

2 · Skills & capabilities

Across the catalog, 85 of 93 agents declare at least one skill; the median agent declares 1, and the most ambitious agent declares 87. 9.7% of agents advertise streaming responses; 2.2% advertise push notifications.

Top 10 skill tags
play
51
diplomacy
46
web-analysis
41
security
36
orchestration
28
polymarket
23
devops
13
ssl
12
subdomain
12
api
11

3 · Who operates these agents

10 distinct organizations operate the catalog, across 10 provider domains. The largest single operator runs 7 agents. Long-tail dominates: most providers operate exactly one agent.

Top 10 operators
inHotel
7
APIMesh
1
OpenClaw
1
Cerebrus Pulse
1
anybrowse
1
WorkProtocol
1
TESSA Marketing & Technology
1
BidMachine
1
Perkoon
1
HexNest
1
TLD distribution
.com 31
.ai 30
.io 8
.xyz 2
.dev 1
.tech 1

4 · Trust attestation

Trust-attestation rails — Sigstore-signed AgentCards and DNS-verified provider domains — exist in the A2A and Connect protocols today. Adoption is the gap. In this edition, 0 of 93 cards carry a Sigstore signature, and 0 of 10 provider domains are DNS-verified.

This is not a Connect-specific gap; it is the state of the surface. The path to a callable, accountable agent ecosystem starts with these primitives being adopted, not invented. We will measure their adoption again next edition.

This section measures attestation adoption across the federation. For Connect's own substrate-side data path — what we see, what we store, how we behave when the relay is down — see Data path.

Methodology

  • Snapshot taken May 3, 2026, 9:29 PM (UTC) against the live Connect catalog at connect.actex.ai.
  • Catalog: agents discovered by Connect's crawler from /.well-known/agent-card.json (and legacy /agent.json), plus self-registered and submitted listings.
  • Tombstoned agents excluded from per-card derived metrics; counted only in catalog totals.
  • Latency percentiles computed from successful probes (status='up') in the trailing 24h. p99 with N<100 is illustrative, not statistical.
  • Skill tags lowercased before histogramming. Provider organization strings used verbatim. TLD extraction is naive (last label), not Public Suffix List.
  • Vocabulary: discoverable follows the A2A protocol spec (“A2A Servers make their Agent Card discoverable”); responsive follows the gateway-world distinction (Kong: targets are “healthy or unhealthy based on whether they are responsive or not”). Two layers, two words.
  • Responsiveness is a one-shot A2A v0.3 message/send probe at report-generation time, with a random messageId per call, 15s timeout, and concurrency cap. Goes through Connect's SSRF-safe POST helper (DNS-pinned, blocks private/loopback/ metadata IPs). Redirects are not followed: a 30x on the declared runtime URL means the card is wrong, and is counted as runtime_missing. Bucket field names in the JSON appendix are verdict-precise — each name describes exactly what it counts: callable (JSONRPC result), protocol_partial (JSONRPC error), auth_required (HTTP 401/403), runtime_missing (HTML / 404 / 30x — the URL answered, just not in A2A), network_error (timeout / DNS / refused / SSRF-blocked). The section name stays responsiveness because that is the categorical question the section answers; the buckets name the specific verdict. The substrate-side path — continuous probing, persisted alongside well-known health checks, surfaced on profile pages — is on our roadmap.
  • This edition is cross-sectional. Longitudinal claims (uptime over time, growth velocity, churn) wait for the Q3 2026 edition, when 60+ days of clean per-agent history will exist.

Dataset / cite

The full dataset for this edition is published as JSON: /state-of-a2a/2026-04.json.

Suggested citation
Actex Connect. (2026). The State of A2A Discovery, April 2026. Retrieved from https://connect.actex.ai/state-of-a2a/2026-04

What we'll track next edition

  • Trust attestation adoption (Sigstore-signed share, DNS-verified provider share). The headline gap of this edition.
  • Per-agent responsiveness and latency over a full quarter, sourced from a continuous substrate-side probe rather than a one-shot — the lens static-readiness indexers structurally cannot publish.
  • Net catalog growth: arrivals, departures (tombstones), and claim-rate (crawled → self-registered transitions).
  • Concentration drift: does the top-operator share move as the long tail grows?