    
    Report · auto-updating
  

State of the agent economy

Live measurement of the agent web: supply funnel, live-rate by ecosystem, protocol adoption, inflow concentration, and 30-day growth. Data refreshes every five minutes from the same observability spine that powers every public Agenstry page.

    As of 2026-10-08 01:46:25 UTC
    methodology
    JSON
    CSV
    cite this
    archive
  

Weekly briefing · 2026-W41

        Oct 5, 2026
      

This is an early-week snapshot, not a completed ISO week: as of October 5, 2026, W41 has just begun, so its figures should not be read as a full-week run rate or a like-for-like comparison with W40. The clearest signal is that measured agent availability and observed earning wallets are rising, while payment activity remains highly concentrated and most payment-protocol records still rely on declarations rather than live runtime evidence.

Measurement: more indexed and live agents, but not all signals mean the same thing

Agenstry’s index reached 11,112, up 945 (+9.3%) from W40. Live endpoints rose to 1,159, up 216 (+22.9%), and the earning-wallet count reached 1,747, up 218 (+14.3%). The separate 30-day growth measure shows 3,133 new agents, up 399 (+14.6%) from the previous period.

These measures describe different stages and should not be collapsed into a single adoption rate. The earning figure counts wallets with observed inbound USDC to declared x402 pay-to addresses, across the wallets scanned so far; it is not an ecosystem-wide revenue or participation total. Likewise, the weekly payment-protocol cohort currently shows 34 records for W41, all x402, but the cohort is only a partial-week observation.

Payments: broad protocol listings, narrow realized revenue

The 30-day gross total is $910,736.46, but the distribution is sharply skewed: the top agent accounts for 69.5% of measured gross, the top 10 for 92.1%, and the Gini coefficient is 0.994. The median is $0.41, compared with a $101.52 95th percentile. The HHI stands at 4,909, down 794 (-13.9%) from W40, while Gini moved from 0.995 to 0.994. The data therefore suggest slightly lower concentration by those two measures, but not broad-based earnings: the median remains small relative to the tail.

Agenstry lists 4,721 x402 payment-protocol records, against 123 for MPP, 59 for A2A-x402, and 34 for AP2. Those are protocol records, not settled-payment volumes. Of 4,943 labeled entries, 1,958 (39.6%) have self-declared-live evidence—an endpoint’s 402 challenge or a served x402 manifest. The dataset itself notes that runtime challenges are authoritative, so static cards and directory listings should not be treated as proof that a paid endpoint currently works.

Spec & protocol: A2A gets a command-line front door

The most concrete protocol-facing launch surfaced this week is the A2A project’s October 1 announcement of its official CLI. It is intended to let users and tools discover agents, send messages, and manage interactions from a terminal, broadening how A2A endpoints can be exercised in development and operations. A2A Protocol announcement

That is an implementation and usability step, not a new protocol specification. The published A2A roadmap still emphasizes v1.1 robustness, bidirectional streaming, and validation tooling. A2A roadmap For operators, the practical question is whether easier invocation is accompanied by repeatable conformance testing and useful runtime observability.

Payments infrastructure: x402 hardening continues

The x402 Python SDK’s September 29 release added Arc mainnet and testnet support and addressed a dependency issue affecting SVM integrations. The changelog also documents recent fixes to payment middleware, including decoded-path route matching—an important reminder that implementation security remains central to payment-gated services. x402 Python SDK changelog

MCP did not show a newer specification release in the sources reviewed: its latest stable specification remains the July 28, 2026 revision, whose stated changes include a stateless core and authorization hardening. MCP release history The distinction matters for buyers: protocol adoption, declared payment support, and verified successful settlement are separate milestones.

What to watch next week

The next useful check is whether W41’s partial-week x402 cohort expands and whether more listed payment endpoints pass live runtime probes. A rising record count alone would be less informative than evidence that declared services are reachable, correctly enforce payment, and produce settlement activity beyond the most concentrated earners.

Sources

1 · Supply funnel

Most of the agent economy is indexed, not yet operational.

Counting agents conflates supply with operation. Below is the corpus broken into five stages: what fraction of indexed agents pass each gate. The decay curve is the honest read on how mature the agent web is at any given moment.

Stage	Count	% of indexed	Definition
Indexed	8,690	100.0%	Every listing we hold across every source; 2,726 archived listings are not counted here or in any step below.
Valid card	7,498	86.3%	Returned a parseable A2A/MCP card on probe.
Live	1,104	12.7%	Live JSON-RPC / introspectable MCP.
Signed	146	1.7%	Card published with a JWS signature.
Earning (30d)	3,276	37.7%	Listings whose declared payTo wallet received inbound USDC in the last 30 days (1,701 distinct wallets; several listings can share one). Measured over the wallets scanned so far (2,301 of 2,466 with a wallet) — not an ecosystem-wide total. Not a subset of Live: most are paid APIs, which answer 402 rather than a free JSON-RPC probe.

2 · Live-rate by ecosystem

Which source registries actually ship live agents.

Each row shows one source registry (Anthropic's MCP directory, Smithery, Glama, Postman, GitHub well-knowns, Wayback CDX scans) alongside how many of the agents it lists actually respond live on probe. The gap between seen-count and live-count is the source's effective freshness.

Source	Seen	Live	Live rate
agentic_market	4,191	177	4.2%
cdp_discovery	3,440	159	4.6%
manifests	2,068	500	24.2%
mcp_registry	1,747	273	15.6%
n8n_workflows	1,187	0	0.0%
x402_list	1,062	73	6.9%
github_code	894	83	9.3%
smithery	779	174	22.3%
registry	735	401	54.6%
a2aregistry	602	375	62.3%
lists	544	55	10.1%
a2a_registry_org	304	132	43.4%
dexter_discovery	179	1	0.6%
github_topics	163	8	4.9%
mpp	93	1	1.1%

3a · By protocol kind

A2A vs MCP vs paid_api

paid_api

4,675

a2a_agent

2,828

workflow

1,187

3b · By observed payment-protocol label

Index composition, not global market share. x402 has multiple dedicated catalogs and a live HTTP probe; AP2, L402 and Stripe ACP are predominantly visible only when cards declare them.

x402 / AP2 / Stripe MPP / L402

x402

4,881

mpp

124

a2a_x402

ap2

l402

stripe_acp

3b · Evidence grade

How we know they take payment

2,035 of 5,105 payment-labelled agents (39.9%) proved it themselves — their own endpoint answered an unpaid request with an HTTP 402 challenge, or the host serves a /.well-known/x402 manifest. The rest is declared in a static agent card or described by a third-party catalog.

Facilitator feed

1,965

Live 402 challenge

1,547

Agent card

573

Catalog listing

504

/.well-known/x402

376

mpp_manifest

mpp_challenge

Official protocol directory

3c · Indexed protocol labels over time · last 12 weeks

Newly indexed agents per week, by payment label

Changes reflect both ecosystem activity and changes in crawler source coverage.

a2a_x402 ap2 mpp stripe_acp x402

4 · Inflow concentration · 30d

A few settlement wallets receive most of the money.

Across 1,701 earning wallets backing 3,276 linked services, the distribution is heavily power-law. Wallet-level Gini and HHI avoid multiplying transfers when several catalog entries share one recipient.

Observed inflow · 30d

$897,659.76

Recipient wallets

1,701

Active sellers · 30d

1,379

Median · wallet

$0.347

p95 · wallet

$101.52

Top 1 share

70.6%

Top 5 share

84.9%

Gini

0.994

extreme inequality

HHI

5045

highly concentrated

5 · 30-day growth

New agents arriving daily, by first-seen.

Daily count of agents we discovered for the first time. Sourced from every registry + open-web crawl we run.

      2026-09-09
      peak 647/day
      2026-10-08
    

New agents · 30d

+3,050

New earning wallets · 30d

801

first observed earning in the last 30 days

Cite this report

Public domain numbers (CC BY 4.0). Pick the format that fits. The page auto-updates so the URL is the canonical pointer; the date stamps the snapshot you cited.

Plain text

Agenstry Research. "State of the Agent Economy." Accessed 2026-10-08. https://agenstry.com/reports/state-of-agent-economy

BibTeX

@misc{agenstry_state_of_agent_economy,
  title  = {State of the Agent Economy},
  author = {Agenstry Research},
  url    = {https://agenstry.com/reports/state-of-agent-economy},
  note   = {Accessed 2026-10-08},
  year   = {2026}
}

Embed (iframe)

<iframe src="https://agenstry.com/reports/state-of-agent-economy" width="100%" height="900" frameborder="0"></iframe>

Scope What this report measures, and what it doesn't

Inflow figures count public stablecoin transfers into wallets declared by indexed agents. They are reproducible from public chains, but a transfer may be self-funded and is not proof of a sale. See the measurement method.

Private and off-chain payments, and Agenstry's own paid-skill receipts, are excluded. Coverage varies by chain, asset and date.

Methodology

This report uses dated observations from the public index. Check source coverage, scoring rules and the public feed before comparing it with another dataset.