# ManyLives Vector Memory Search

> ManyLives Vector Memory Search is a paid API for AI agents from api.manylives.me, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-10).

Performs semantic vector search (or deletion) over an AI agent's private memory store, returning the most relevant stored text chunks for a given query.

## Facts

- Endpoint: POST https://api.manylives.me/paid/memory/vector-search?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/manylives-vector-memory-search-b16c41d3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nePpqA88Ztv3RAPrWTjHE

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 manylives-vector-memory-search-b16c41d3 -d '<json body>'
```

Example prompt: Search my agent memory for which supplier was cheapest — look in the 'procurement' namespace and return the top 3 most relevant results.

## When to prefer this

Choose this endpoint when an AI agent needs to retrieve semantically relevant memories or stored knowledge from a private vector store, especially within the ManyLives pay-per-call ecosystem. Prefer it over keyword search when meaning matters more than exact wording, or when you need to manage (delete) specific stored entries by ID. It is well-suited for agentic workflows where context persistence across sessions is needed without standing up your own vector database.

## Known failure modes

- Missing query and no delete_ids provided — returns error requiring at least one
- top_k out of range (must be 1–20) — returns validation error
- Namespace does not exist or is empty — returns empty results array
- Invalid delete_ids format (not an array) — returns parsing error
- Payment not included or insufficient — returns 402 Payment Required
- Network timeout on large namespaces

## How this service works

Pay-per-call tools for people building AI agents: live web search and page contents, point-in-time crypto market data and news for backtests (no lookahead), verifiable track records of 1,000 crypto strategies locked on the Base network, company profiles, quick AI and batch prices. Ask us to turn a public website into a JSON endpoint. Pay per call, no account, free trial.

## Output

Returns a JSON object with the original query, the namespace searched, and an array of up to top_k matching results — each with a unique ID, similarity score (0–1), the stored text, and any metadata (e.g. source tag) attached when the memory was saved.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "query": {
   "type": "string",
   "examples": [
    "which supplier was cheapest?"
   ],
   "description": "what to look for (required unless delete_ids)"
  },
  "top_k": {
   "type": "string",
   "examples": [
    3
   ],
   "description": "optional 1-20 (default 5)"
  },
  "namespace": {
   "type": "string",
   "description": "optional (default 'default')"
  },
  "delete_ids": {
   "type": "string",
   "description": "optional array of ids to delete instead of searching"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "query": "which supplier was cheapest?",
  "results": [
   {
    "id": "note-1",
    "meta": {
     "source": "email"
    },
    "text": "Supplier B quoted the lowest price for 500 units.",
    "score": 0.82
   }
  ],
  "namespace": "default"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/manylives-vector-memory-search-b16c41d3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.manylives.me](https://www.zero.xyz/host/api.manylives.me/llms.txt)
