> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ariacompute.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Search Memory Nodes - POST /v1/workspaces/:workspace_id/cubes/:cube_id/search

> Semantic-search memory nodes within a cube via POST /v1/workspaces/:workspace_id/cubes/:cube_id/search. Minimum role viewer.

Run vector semantic search within a memory cube, returning the nodes most relevant to the query.

## Endpoint

```http theme={null}
POST /v1/workspaces/:workspace_id/cubes/:cube_id/search
```

## Authentication

`Authorization: Bearer <jwt>` or `X-API-Key <sk_...>`. Minimum role: **viewer**.

## Path parameters

**workspace\_id** `string` *required*

Workspace id.

**cube\_id** `string` *required*

Cube id.

## Request body

**query** `string`

Search text (used to build the query vector).

**k** `integer`

Number of most-similar nodes to return.

## Response

The response is an array; each element is a memory node (fields identical to [List Nodes](https://docs.ariacompute.com/api-reference/memo/nodes/list.md)).

## Example

```bash cURL theme={null}
curl -X POST https://memo.ariacompute.com/v1/workspaces/ws_01a2b3c4d5e6/cubes/cube_01a2b3c4d5e6/search \
  -H "Authorization: Bearer <jwt>" \
  -H "Content-Type: application/json" \
  -d '{"query":"user language preference","k":5}'
```

```json 200 theme={null}
[
  {
    "id": "node_01a2b3c4d5e6",
    "cube_id": "cube_01a2b3c4d5e6",
    "type": "text",
    "content": "User prefers Chinese replies.",
    "tier": 4,
    "meta": "{}",
    "auto": false,
    "source_type": "session",
    "source_id": "sess_01a2b3c4d5e6",
    "created_at": "2026-10-12T08:25:00Z"
  }
]
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.