The agent economy, live on Base
Integrity intelligence for the agent economy.
Autonomous agents now pay, rate, and vouch for each other on-chain. Verifeth continuously verifies that agents are what they claim to be, and that their reputation is real. First, only, and most advanced agentic fraud detection technology.
Every machine-to-machine market grows a native fraud layer within two years. The tools built for human fraud go blind the moment the actor is a machine.
Existing analytics trace fund flows; merchant tools watch human checkout. Neither sees agent-versus-agent behaviour at the application layer, where the manipulation actually happens. That blind spot is what we monitor, from the registry's first block onward.
The manipulations we detect
A detection engine per manipulation, running on first-party telemetry. Five are live on the real dataset today; five more are on the roadmap as the data deepens.
Reputation wash trading
Reciprocal A↔B transfers and closed cycles that inflate volume and standing.
Sybil identity farms
One owner minting thousands of agents behind a single shared metadata URI.
Fake volume
Floods of near-zero-value dust transfers staged to simulate real usage.
Fabricated reputation
Reputation manufactured by a single actor: one agent, a handful of voucher addresses.
Collusive vouching
A closed set of addresses generating the entirety of an agent's feedback.
On the roadmap
Collusion rings, Predatory probing, Identity whitewashing, Coordinated sybil funding, Feedback / review manipulation.
Score any agent before you clear it.
The Verifeth risk API turns first-party behavioural telemetry into a single pre-settlement verdict. Payment facilitators, marketplaces, and underwriters call it in-line: pass an agent, get a risk score, the integrity breakdown, and the evidence.
- clear / flag / block, one decision in real time
- Identity and reputation integrity in the same response
- Every verdict links to the on-chain evidence behind it
// score an agent before you clear its settlement POST https://api.verifeth.com/v1/score { "agent": "0x4efb…565a", "network": "eip155:8453" }
{
"agent": "0x4efb…565a",
"risk": 84, // 0 clear · 100 block
"verdict": "block",
"integrity": {
"identity": "sybil_cluster",
"reputation": "fabricated"
},
"flags": ["SYBIL_CLUSTER", "VOUCH_CONCENTRATION"],
"evidence": "verifeth.com/catalog/…"
} The moat is the dataset.
First-party behavioural telemetry, collected since ERC-8004's first block. Nobody else has it. More data sharpens detection; sharper detection earns more integrations; more integrations deepen the data. Whoever holds this record when agent fraud goes mainstream is the only party that can price it.
- 15,129
- Distinct owners
- 1,066,433
- Settlements tracked
- 1,183,383
- On-chain events ingested
- 1
- Abuse patterns published
What the record already shows
Abuse pattern catalogof registered agents are clones. 14,349 of 59,296 belong to identity farms.
of all on-chain reputation was fabricated by a single agent, sourced from 13 addresses.
dust transfers from 296 wallets, staged to simulate genuine activity.
Sybil Identity Farms
Roughly a quarter of registered agents on Base's ERC-8004 registry belong to identity farms: single owners minting thousands of agents that share one metadata URI. Raw volume does not distinguish a farm from a legitimate platform; metadata diversity does. Our corroborated detector flags 44 such farms as of block 48,425,370, the last indexed registry block before 10 July 2026 (00:00 UTC).
Trace where value moves. Blind to whether the agent moving it is real.
Built for human checkout: session, device, typing cadence. There is no human here.
Application-layer, agent-versus-agent behaviour. The integrity of the actor itself.
Build on the integrity layer.
Early access to the risk API and the private signature feed is opening to facilitators, marketplaces, and underwriters. Tell us what you're clearing.