Search Memories

POST /v1/search — Full-text search without embedding costs.

POST /v1/search

Search Memories

cURL

curl --request POST \
  --url https://api.memoclaw.com/v1/search \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "limit": 123,
  "namespace": "<string>",
  "memory_type": "<string>",
  "tags": [
    "<string>"
  ],
  "session_id": "<string>",
  "agent_id": "<string>"
}
'

200

{
  "memories": [
    {
      "id": "<string>",
      "content": "<string>",
      "importance": 123,
      "memory_type": "<string>",
      "namespace": "<string>",
      "tags": [
        "<string>"
      ],
      "created_at": "<string>"
    }
  ],
  "total": 123,
  "query": "<string>"
}

This endpoint requires wallet authentication for identity. It is free — no payment required.

Price: FREE

Full-text keyword search using BM25 ranking. A lightweight alternative to /v1/recall when you don’t need semantic embeddings or want to reduce costs.

This endpoint uses PostgreSQL full-text search (tsvector) rather than vector similarity, making it faster and free from embedding API costs.

Request Body

query · string · required

Search query string. Max 1,000 characters.

limit · number

Maximum number of results. Default: 10. Max: 100.

namespace · string

Filter by namespace.

memory_type · string

Filter by memory type: correction, preference, decision, project, observation, or general.

tags · string[]

Filter by tags.

session_id · string

Filter by session ID.

agent_id · string

Filter by agent ID.

Response (200 OK)

memories · array

Array of matching memories sorted by BM25 relevance.

Show Memory object

id · string

UUID of the memory.

content · string

Memory text content.

importance · number

Importance score (0-1).

memory_type · string

Memory type.

namespace · string

Namespace.

tags · string[]

Tags.

created_at · string

ISO 8601 timestamp.

total · number

Total number of matches.

query · string

The search query used.

When to Use Search vs Recall

Use Case	Endpoint
Natural language semantic search	/v1/recall
Keyword/exact match search	/v1/search
Need vector similarity scoring	/v1/recall
Reduce embedding API costs	/v1/search
Find memories with specific words	/v1/search

Example

curl

curl -X POST https://api.memoclaw.com/v1/search \
  -H "Content-Type: application/json" \
  -H "x-wallet-auth: 0xYourWallet:1699900000:0xSignature..." \
  -d '{
    "query": "dark mode preferences",
    "limit": 10,
    "tags": ["preferences"]
  }'

Response

{
  "memories": [
    {
      "id": "550e8400-e29b-41d4-a716-446655440000",
      "content": "User prefers dark mode",
      "importance": 0.8,
      "memory_type": "preference",
      "namespace": "default",
      "tags": ["preferences", "ui"],
      "created_at": "2026-02-13T10:30:00Z"
    }
  ],
  "total": 1,
  "query": "dark mode preferences"
}