# Kette Wallet Behaviour Classifier

> Kette Wallet Behaviour Classifier is a paid API for AI agents from kette.halowerk.com, paid per call via x402, $0.006/call, status unknown (last checked 2026-09-15).

Classifies an Ethereum-compatible wallet address into one or more behaviour classes (e.g. bot, DeFi trader, human retail) based on on-chain activity patterns including swap share, interval regularity, hour-of-day spread, counterparty count, and contract code.

## Facts

- Endpoint: POST https://kette.halowerk.com/wallet/classify
- Price: $0.006/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/kette-wallet-behaviour-classifier-059d813b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cVtqjEzvFkbCgXCNksI5T

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability kette-wallet-behaviour-classifier-059d813b -d '<json body>'
```

Example prompt: Classify the on-chain behaviour of wallet 0x3fC91A3afd70395Cd496C647d5a6CC9D4B2b7FAD — tell me which behaviour classes it belongs to, its automation likelihood, and what on-chain evidence supports each class.

## When to prefer this

Choose this endpoint when you need evidence-based, multi-class behavioural profiling of a wallet address rather than a simple label. It is preferred over heuristic blacklist checks when you need to understand automation likelihood with quantified features (interval regularity, hour-of-day spread), when a wallet may belong to multiple behaviour classes simultaneously, or when you need auditable evidence for each classification rather than a black-box score.

## Known failure modes

- Address not found or has no on-chain history — no classes returned
- Unsupported chain or address format — validation error
- Insufficient on-chain activity to derive any class — empty classification with explanation
- Network or RPC timeout when fetching chain data — 5xx error
- Malformed wallet address input — 4xx bad request error

## How this service works

Derives behaviour classes from on-chain activity: share of swaps, regularity of intervals, hour-of-day spread, counterparty count and contract code. Several classes at once are allowed and usually more accurate than one. Every class carries its evidence; without evidence no class is set. automation_likelihood comes from measurable traits - interval regularity and how evenly activity spreads over the day - listed in features_used, never from a hunch. Limits: this classifies BEHAVIOUR, not people.

## Output

Returns one or more behaviour classes (e.g. automated, DeFi swapper, retail human) each accompanied by supporting on-chain evidence. Also includes a numeric automation_likelihood score derived from measurable features such as interval regularity and hour-of-day spread, along with a features_used list explaining exactly which signals drove the classification. No class is assigned without evidence.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "chains": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 4,
   "description": "Chains to query. Default: ethereum, base, arbitrum, optimism."
  },
  "wallet": {
   "type": "string",
   "description": "Wallet address, 0x followed by 40 hex characters."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/kette-wallet-behaviour-classifier-059d813b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from kette.halowerk.com](https://www.zero.xyz/host/kette.halowerk.com/llms.txt)