# AgentRXI Vector Memory

> AgentRXI Vector Memory is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-15).

Private long-term semantic vector memory for AI agents: upsert texts with metadata (auto-embedded, multilingual), then search by meaning or delete by ID, keyed to the paying wallet.

## Facts

- Endpoint: GET https://agentrxi.com/v1/vectors?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-vector-memory-c67e01f2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DgNzhEgcCsNIXXA7lGsw0

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 agentrxi-vector-memory-c67e01f2
```

Example prompt: Save these 3 notes to my long-term agent memory — upsert them: 'User prefers dark mode | source: preferences', 'User is vegetarian | source: dietary', 'User lives in Berlin | source: profile' — then later I want to search by meaning with a query like 'what are the user's food restrictions' and get the top 2 results.

## When to prefer this

Choose this endpoint when an AI agent needs persistent, wallet-scoped semantic memory that survives across sessions and conversations. Ideal for agents that need to remember user preferences, facts, or documents and retrieve them by meaning rather than exact keyword. The multilingual embedding support makes it suitable for cross-language memory. Prefer over in-context storage when data volume exceeds context window limits, or when memory must persist indefinitely between separate agent invocations.

## Known failure modes

- Missing required 'action' parameter defaults to query — may confuse callers expecting upsert behavior
- Exceeding 100 items per upsert batch returns an error
- Invalid or non-existent IDs on delete return empty confirmation rather than error
- Payment failure (x402) blocks all operations
- Malformed items string (not pipe-separated JSON objects) causes parse error
- top_k not specified may return fewer results than expected

## How this service works

Private long-term vector memory for an agent: upsert up to 100 texts with metadata (we embed them, multilingual), then search by meaning. Keyed to the paying wallet. from $0.004 per upsert batch (by size), $0.003 per query or delete. Also callable as GET with the same fields as query parameters.

## Output

For queries: a ranked list of semantically similar stored texts with their metadata and similarity scores (up to top_k results). For upserts: confirmation of stored vector IDs. For deletes: confirmation of removed entries. All results are scoped to the authenticated paying wallet.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "ids": {
       "type": "string",
       "description": "For delete"
      },
      "items": {
       "type": "string",
       "description": "[{id, text, metadata}]; separate items with |"
      },
      "query": {
       "type": "string"
      },
      "top_k": {
       "type": "integer"
      },
      "action": {
       "type": "string",
       "description": "upsert, query (default), delete"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrxi-vector-memory-c67e01f2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)