MemoryServe

What it does

Post text and it is embedded and stored in a vector database keyed to your agent_id. Query by natural language and get back the most semantically similar memories. Built on Qdrant. The canonical x402 RAG pipeline: ScrapePay → MarkdownOpt → EmbedPay → MemoryServe. Delete by memory ID or wipe all memories for an agent (GDPR compliance). $0.001 per write or query. No account, no signup — pay per call via x402.

When to use it

• Store research summaries from ScrapePay + MarkdownOpt, recall by topic later
• RAG pipeline: embed with EmbedPay, store in MemoryServe, scrub recalls with MemScrub
• Per-user memory namespaces for personalised agent responses
• GDPR compliance: store then DELETE /memory/agent/{id} to wipe on user request

Request schema

{
  "agent_id": "my-agent-001",
  "namespace": "research",
  "content": "The Eiffel Tower was built in 1889 for the World Fair.",
  "tags": [
    "facts",
    "paris",
    "history"
  ]
}

Response schema

{
  "success": true,
  "memory_id": "7ea9afac-c3d1-4b2e-9f3a-1234abcd5678",
  "agent_id": "my-agent-001",
  "namespace": "research",
  "content_length": 53,
  "tags": [
    "facts",
    "paris",
    "history"
  ],
  "created_at": "2026-05-08T16:33:43Z",
  "payment_hash": "0x..."
}

Code example — TypeScript via MCP

Install the MCP server once; all 22 services become tool calls.

// Configure @melis-ai/x402-tools-mcp in your MCP client
// Then call the tool:

const result = await mcpClient.callTool("memoryserve", {
  "agent_id": "my-agent-001",
  "namespace": "research",
  "content": "The Eiffel Tower was built in 1889 for the World Fair.",
  "tags": [
    "facts",
    "paris",
    "history"
  ]
});

console.log(result);
// ["success","memory_id","agent_id","namespace","content_lengt...

Code example — Python via direct HTTP

import requests

# x402 payment header must be set by your wallet client
# See x402.org for client libraries

headers = {
    "Content-Type": "application/json",
    "x-payment": "<signed-x402-payment-header>",
}

resp = requests.post(
    "https://memoryserve.melis.ai/memory/write",
    json={
      "agent_id": "my-agent-001",
      "namespace": "research",
      "content": "The Eiffel Tower was built in 1889 for the World Fair.",
      "tags": [
        "facts",
        "paris",
        "history"
      ]
    },
    headers=headers,
)
print(resp.json())

Code example — curl with internal key bypass

For testing with an issued internal key (skips x402 payment flow):

curl -X POST https://memoryserve.melis.ai/memory/write \
  -H "Content-Type: application/json" \
  -H "x-internal-key: YOUR_KEY" \
  -d '{"agent_id":"my-agent-001","namespace":"research","content":"The Eiffel Tower was built in 1889 for the World Fair.","tags":["facts","paris","history"]}'

How is this different from alternatives?

Related services

FAQ