# AMEM.SEM.CREATE

> Create an agent's semantic memory store for embeddings of a fixed dimension.

URL: https://docs.hotkv.com/commands/amem-sem-create/

```
AMEM.SEM.CREATE agent_id dimensions
```

- Group: Agent memory
- Complexity: O(1)
- HotKV Cloud: Performance and Scale plans
- On-Premise: requires the agent-memory license feature

Agent memory gives AI agents four kinds of memory. Semantic memory holds an agent's long-term facts, each with an embedding your application computes, and recalls them by cosine similarity to a query embedding. `AMEM.SEM.CREATE` creates the store for `agent_id`, for
embeddings of exactly `dimensions` values (1 to 65536). You must create it
before you store facts with [AMEM.SEM.STORE](https://docs.hotkv.com/commands/amem-sem-store/index.md).

## Return value

| Case | RESP2 | RESP3 |
| --- | --- | --- |
| Store created | Simple string `OK` | Same |

Errors:

- `ERR invalid dimensions (must be 1-65536)` if `dimensions` is not an integer in that range.
- `ERR agent store already exists` if the agent already has a semantic store.
- `ERR wrong number of arguments for 'amem.sem.create' command` if the argument count is wrong.
- `NOLICENSE agent-memory requires a HotKV license. Contact sales@hotkv.com` if your license does not include the `agent-memory` feature.

## Examples

```
127.0.0.1:6379> AMEM.SEM.CREATE knowledge-base 1536
OK
127.0.0.1:6379> AMEM.SEM.CREATE notes 3
OK
```

## Compatibility

HotKV-only command. Redis and Valkey have no equivalent.

## See also

[AMEM.SEM.STORE](https://docs.hotkv.com/commands/amem-sem-store/index.md), [AMEM.SEM.RECALL](https://docs.hotkv.com/commands/amem-sem-recall/index.md), [AMEM.SEM.FORGET](https://docs.hotkv.com/commands/amem-sem-forget/index.md), [AMEM.SEM.LIST](https://docs.hotkv.com/commands/amem-sem-list/index.md), [AMEM.SEARCH](https://docs.hotkv.com/commands/amem-search/index.md), [AI features guide](https://docs.hotkv.com/ai-features/index.md)