Data hub · Ethereum chain brief · Base chain brief
Data as of 2026-11-05 (Ethereum IdentityRegistry census) · live figures re-fetched on every visit.
Short answer:
the ERC-8004 IdentityRegistry
(0x8004A169FB4a3325136EB29fA0ceB6D2e539a432) on Ethereum mainnet holds
56,186 raw registration mints
as of 2026-11-05.
Of those, 30,502
(60.9%) carry a
populated tokenURI;
far fewer resolve to a usable agent card.
Onchain Agent Intel indexes
26,978 ERC-8004
registrations across Base and Ethereum after applying a per-publisher
dedup cap, of which 2,537
(9%) answer at
their advertised endpoint on the last probe.
“How many ERC-8004 agents are there?” has no single-number answer because it turns on which cut you want. Below are the four cuts that matter, each labelled with what it does and does not measure.
56,186 raw
Transfer(from=0x0) events on the Ethereum IdentityRegistry
as of 2026-11-05. This is
the on-chain ceiling — it is Ethereum block state, deterministic.
It is not the number of
distinct working agents: every ERC-721 mint counts once regardless of
whether the token points to real off-chain content, so batch mints with
empty tokenURI are in this total. Do not read this as
“56,186 agents”; read it as raw registration mints.
tokenURI (upper bound)
30,502
(60.9%) of the raw
mints carry a non-empty tokenURI. This is an
upper bound on the agents
that could plausibly resolve to a usable card — the remainder are
empty-tokenURI batch mints that tokenURI()
returns as an empty string or reverts on. Populated is
not the same as usable: many
of the populated tokenURIs point at URLs that 404, IPFS CIDs
that never resolve, or JSON bodies that do not carry an A2A card. The
count of agents that actually resolve to a walkable card is
much smaller.
Onchain Agent Intel currently indexes
26,978 ERC-8004
registrations after applying a per-publisher dedup cap
— 23,705
on Base and 3,273 on
Ethereum. Bulk publishers dominate the raw Ethereum mint count —
the top publisher alone (agents.exquisite.land) minted
10,000 tokens — so
we cap each publisher at
50 rows and index
the deduplicated set (303
distinct publishers). An indexed set of tens of thousands of
near-identical agents from one publisher would give a larger headline
number but a less useful index.
2,537 of the indexed cohort answer at their advertised endpoint with a machine-readable capability manifest (MCP, OpenAPI, or a well-known agent card) on the last probe — a 9% live rate across the full indexed set. Per chain: 1,408 live on Base (6% of Base indexed), 1,129 live on Ethereum (34% of Ethereum indexed). A live endpoint is a starting point for a buyer, not proof an agent will deliver. Separately, 51 agents carry on-chain feedback tied to a real paid Virtuals ACP / ERC-8183 job (the commerce-backed cohort), the strictest signal we use.
Earlier published counts were snapshots at earlier dates, accurate when written and since out of date. Three examples:
agents.exquisite.land dropped a batch of
10,000 mints alone since
then). The April number was correct in April.
Registry. ERC-8004 IdentityRegistry at
0x8004A169FB4a3325136EB29fA0ceB6D2e539a432 — the same CREATE2
address on Base (eip155:8453) and Ethereum mainnet
(eip155:1). Raw registration mints are
Transfer(from=0x0) events on that contract.
Raw mint count + tokenURI classification. From a
full-registry census on 2026-08-17: every raw mint was classified (not
sampled) by reading its tokenURI in batched calls. The
method and breakdown are in
our
placeholder-vs-live analysis.
Indexed set. The ERC-8004 registrations our discovery process has already scanned, filtered to drop agents lacking service endpoints, capabilities, x402 support, and payment config, and further capped at 50 rows per publisher so bulk mints do not dominate the served set. The same set underlies our free statistics, free agent pages and paid API.
Live check. An agent counts as live if its endpoint
returns HTTP 2xx and at least one machine-readable
capability manifest resolves — MCP (/mcp), OpenAPI
(/openapi.json), or a well-known agent card
(/.well-known/agent-card.json). Each agent is re-checked
roughly every two days.
Where the live number diverges from the raw mint number. Layer 4 (live) is measured on the indexed cohort — the per-publisher-deduplicated subset from Layer 3, not the raw Ethereum mint total from Layer 1. Most raw mints have no endpoint to check. The same distinction — raw registration count vs live-endpoint count — shows up in the demand-side companion, how many x402 endpoints are actually used, and in the per-agent-card cut, /erc-8004-agent-card-signpost-gap.
tokenURI ≠ usable agent card.
Layer 2 is an upper bound only. A populated tokenURI can resolve to a
broken URL, an unavailable IPFS CID, or a JSON body that does not
carry an A2A card. The number of agents that pass the strict walk to
a payable endpoint is measured separately — see the
signpost-gap
dataset.
Citable summary. Scope: ERC-8004 registrations on the Base and Ethereum IdentityRegistry (0x8004A169FB4a3325136EB29fA0ceB6D2e539a432), refreshed daily. The
Ethereum IdentityRegistry contained
56,186 minted agents as of
2026-11-05, of which
30,502
(60.9%) carry a
populated tokenURI and the remainder are empty-URI batch
mints. The top single publisher accounts for
10,000 mints; On-Chain
Agent Intel indexes 26,978
Base + Ethereum registrations — the subset whose off-chain
metadata passes an is_worth_recording filter and a
per-publisher dedup cap.
License. Answer prose and every rendered number published under CC BY 4.0 — free to reuse, including in commercial work, provided you attribute “Onchain Agent Intel” and link back to https://onchainagentintel.io/how-many-erc-8004-agents-are-there.
Machine-readable source. Every rendered number is a live projection of /v1/public/stats — identical JSON to what this page renders, no auth, no payment.
Also useful: Ethereum chain brief · Base chain brief · Chain-liveness dataset · Signpost-gap dataset · Commerce-backed cohort · All datasets
Browse the live sets: Leaderboard · x402 Bazaar market map · API + coverage comparison.