# Agent Memory API - Recall

> Agent Memory API - Recall is a paid API for AI agents from agent-memory-api-bix5.onrender.com, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-15).

Retrieves encrypted stored memories for an AI agent by semantic query and agent ID, returning matching memory records and a next recommended API action.

## Facts

- Endpoint: POST https://agent-memory-api-bix5.onrender.com/api/memory/recall
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-memory-api-recall-6018da0e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Pnqeh-bZavB2dzpVis4lL

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 agent-memory-api-recall-6018da0e -d '<json body>'
```

Example prompt: Search the encrypted memory for agent 'agent-42' and recall anything it knows about 'user onboarding preferences', returning up to 5 results.

## When to prefer this

Use this endpoint when an autonomous AI agent needs to recall previously stored context, facts, or interaction history by semantic query. Prefer this over generic vector DBs when you need AES-256 encrypted per-agent memory with built-in x402/USDC micropayment gating and an agentic next-step recommendation in the response.

## Known failure modes

- Missing required fields (agent_id or query) returns a 422 validation error
- No matching memories found returns an empty memories array
- Invalid agent_id returns empty or unauthorized response
- Service unavailable on Render free tier due to cold start or sleep — slow or timeout response
- Payment not processed via x402 results in 402 Payment Required before memory is returned

## How this service works

Pay-per-request encrypted memory APIs for autonomous AI agents using x402. Store, recall, and audit AI agent memory with AES-256 encryption. Built for USDC/Base payments and Japanese AI agent workflows.

## Output

Returns an array of matching encrypted memory objects associated with the agent, plus a next_recommended object suggesting the most relevant follow-up API to call (with its name, URL, reason, expected improvement, and price in USDC).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "query",
  "agent_id"
 ],
 "properties": {
  "tags": {
   "type": "string"
  },
  "limit": {
   "type": "string"
  },
  "query": {
   "type": "string"
  },
  "agent_id": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "RecallMemoryResponse",
 "required": [
  "memories",
  "next_recommended"
 ],
 "properties": {
  "memories": {
   "type": "array",
   "items": {
    "type": "object",
    "additionalProperties": true
   },
   "title": "Memories"
  },
  "next_recommended": {
   "type": "object",
   "title": "NextRecommendation",
   "required": [
    "api_name",
    "url",
    "reason",
    "expected_improvement",
    "price_usdc"
   ],
   "properties": {
    "url": {
     "type": "string",
     "title": "Url"
    },
    "reason": {
     "type": "string",
     "title": "Reason"
    },
    "api_name": {
     "type": "string",
     "title": "Api Name"
    },
    "price_usdc": {
     "type": "number",
     "title": "Price Usdc"
    },
    "expected_improvement": {
     "type": "string",
     "title": "Expected Improvement"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-memory-api-recall-6018da0e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-memory-api-bix5.onrender.com](https://www.zero.xyz/host/agent-memory-api-bix5.onrender.com/llms.txt)