Skip to content

Ask the HotKV docs

Answers come only from these docs and can be wrong; check the linked pages before you rely on them.

AMEM.SEM.STORE

Last updated
AMEM.SEM.STORE agent_id key content value [value ...] [TTL seconds]
Group
Agent memory
Complexity
O(log N) where N is the number of facts
Arity
-5 (at least 5 words, counting the command name)
Flags
write, slow
Keys
first 1, last 1, step 1
HotKV Cloud
Performance and Scale
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.STORE stores content under key with its embedding, given as one argument per value after content. The number of values must match the store’s dimensions. Storing an existing key replaces the fact.

Option Effect
TTL seconds After this many seconds the fact is no longer recalled. Must follow the last vector value. Omitted or 0 means no expiry.
Case RESP2 RESP3
Fact stored Simple string OK Same

Errors:

  • ERR agent not found or dimension mismatch if the agent has no semantic store or the vector has the wrong number of values.
  • ERR invalid vector component if a vector value is not a finite number.
  • ERR empty embedding vector if no vector values are given.
  • ERR invalid TTL if TTL is not a non-negative integer.
  • ERR wrong number of arguments for 'amem.sem.store' 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.
127.0.0.1:6379> AMEM.SEM.STORE notes fact-1 "Paris is the capital of France." 0.1 0.2 0.3
OK
127.0.0.1:6379> AMEM.SEM.STORE notes fact-2 "The user prefers metric units." 0.7 0.1 0.2 TTL 86400
OK

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

AMEM.SEM.CREATE, AMEM.SEM.RECALL, AMEM.SEM.FORGET, AMEM.SEM.LIST, AMEM.SEARCH, AI features guide