# Vektorwerk Co-occurrence Recommender

> Vektorwerk Co-occurrence Recommender is a paid API for AI agents from vektor.halowerk.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Calculates item co-occurrence and similarity from submitted interaction events to return recommendations, without storing any user profiles.

## Facts

- Endpoint: POST https://vektor.halowerk.com/recommend
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vektorwerk-co-occurrence-recommender-e0d55397
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Cc3mDqblGPAxzXxROAIWT

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 vektorwerk-co-occurrence-recommender-e0d55397 -d '<json body>'
```

Example prompt: Using the interaction events I'm sending you — where user-1 viewed item-a, item-b, and item-c, and user-2 viewed item-a and item-d — give me the top 5 items most similar to item-a based on co-occurrence, without storing any user profiles.

## When to prefer this

Choose this endpoint when you need stateless, privacy-preserving item recommendations computed entirely from a single request's interaction events — ideal when you cannot or do not want to store user profiles server-side. Prefer it for collaborative-filtering-style co-occurrence recommendations (not content-based or embedding-based similarity). It is well-suited for e-commerce, content platforms, or any domain where GDPR/privacy constraints prohibit persistent user data. If you need embedding-based semantic similarity rather than behavioral co-occurrence, consider the sibling embedding endpoints on the same host.

## Known failure modes

- interactions array is empty or missing — minItems:1 required
- item_id not found in the submitted interactions — returns empty or low-confidence recommendations
- interactions array exceeds 2000 events — request rejected
- limit out of range (must be 1–50) — validation error
- item_id or user_id strings exceed 120 characters — schema validation failure
- weight values outside 0–100 range — rejected
- malformed JSON body — 400 error

## How this service works

Calculates item co-occurrence and item similarity from the submitted events only. No user profile is stored.

## Output

Returns a ranked list of recommended item IDs (up to the requested limit, max 50) scored by co-occurrence and similarity computed purely from the submitted interaction events. No data is persisted between calls.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "limit": {
   "type": "integer",
   "default": 5,
   "maximum": 50,
   "minimum": 1
  },
  "item_id": {
   "type": "string",
   "example": "item-a",
   "maxLength": 120,
   "minLength": 1
  },
  "interactions": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "user_id",
     "item_id"
    ],
    "properties": {
     "weight": {
      "type": "number",
      "default": 1,
      "maximum": 100,
      "minimum": 0
     },
     "item_id": {
      "type": "string",
      "example": "item-a",
      "maxLength": 120,
      "minLength": 1
     },
     "user_id": {
      "type": "string",
      "example": "user-1",
      "maxLength": 120,
      "minLength": 1
     }
    },
    "additionalProperties": false
   },
   "maxItems": 2000,
   "minItems": 1
  },
  "user_history": {
   "type": "array",
   "items": {
    "type": "string",
    "maxLength": 120,
    "minLength": 1
   },
   "example": [
    "item-a"
   ],
   "maxItems": 100
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vektorwerk-co-occurrence-recommender-e0d55397/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from vektor.halowerk.com](https://www.zero.xyz/host/vektor.halowerk.com/llms.txt)