# Mnemo Memory Recall

> Mnemo Memory Recall is a paid API for AI agents from memory.reversecaptcha.fun, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-29).

Retrieves stored user memories using hybrid vector + keyword search, filtered by kind and tags

## Facts

- Endpoint: POST https://memory.reversecaptcha.fun/v1/memory/recall?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mnemo-memory-recall-765a9cf3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-DPFGpC6YSpdAw6IRMuLM

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 mnemo-memory-recall-765a9cf3 -d '<json body>'
```

Example prompt: Recall up to 5 memories about my user's communication style and formatting preferences — search for 'response format code style' and filter to the preference and instruction kinds.

## When to prefer this

Use this endpoint when you need to retrieve previously stored user context, preferences, instructions, or decisions in a cross-agent portable way. Prefer this over session-local memory when the user has delegated their Mnemo memory to your agent and you need personalized, persistent context that follows the user across different AI agents. Ideal when you need hybrid semantic + keyword search over typed memory records.

## Known failure modes

- 401 Unauthorized if Bearer token is missing or expired — re-delegate to get a new token
- 402 Payment Required if x402 payment is not provided or insufficient
- Empty memories array if no stored memories match the query — not an error
- Malformed query_embedding array causes 400 Bad Request
- Rate limiting or quota exhaustion returns 429

## How this service works

Memory that belongs to the user and follows them across agents. The agent pays per call (x402); the user authorizes the agent once: POST /v1/memory/delegate/challenge {user, agent} returns text the user signs (EIP-191), then POST /v1/memory/delegate {..., signature} returns a bearer token. Send Authorization: Bearer mn_... on every memory call. Start a session with GET /v1/memory/profile, write with POST /v1/memory/remember, retrieve with POST /v1/memory/recall (hybrid vector + keyword). When the user contradicts a memory, POST /v1/memory/conflict supersedes it with history kept. Tier B stores client-side ciphertext the server cannot read. Export and forget are always free.

## Output

Returns a JSON array of memory records, each with an id, kind (fact/preference/instruction/decision/state), a relevance score (0-1), and the memory content string. Results are ranked by hybrid vector + keyword similarity to the query.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "k": {
   "type": "number"
  },
  "tags": {
   "type": "array",
   "items": {
    "type": "string"
   }
  },
  "kinds": {
   "type": "array",
   "items": {
    "enum": [
     "fact",
     "preference",
     "instruction",
     "decision",
     "state"
    ]
   }
  },
  "query": {
   "type": "string"
  },
  "query_index": {
   "type": "array",
   "items": {
    "type": "string"
   }
  },
  "query_embedding": {
   "type": "array",
   "items": {
    "type": "number"
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "memories": [
   {
    "id": "mem_...",
    "kind": "preference",
    "score": 0.82,
    "content": "Prefers short answers with code first"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mnemo-memory-recall-765a9cf3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from memory.reversecaptcha.fun](https://www.zero.xyz/host/memory.reversecaptcha.fun/llms.txt)