> ## Documentation Index
> Fetch the complete documentation index at: https://infino-29-bot-sync-openapi-spec.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent memory: long-term recall for AI agents

> Give AI agents long-term memory with Infino. Hybrid BM25 and vector recall over an agent's history, with SQL over the same store, on object storage.

An agent that talks with someone over weeks needs to remember the conversation and recall
the right pieces later. Infino stores each message once, its text alongside an embedding,
and serves recall over that single table: by keyword, by meaning, by both fused together,
and by SQL. Memory lives on a local path or object storage, so it grows with the agent's
history rather than a fixed cluster.

## What memory needs from a store

| Need                                 | How Infino serves it                                                                  |
| ------------------------------------ | ------------------------------------------------------------------------------------- |
| Recall by meaning and by exact terms | Hybrid search fuses BM25 and vector matches with reciprocal-rank fusion, in one query |
| Structured questions over history    | SQL over the same table: filter by session or date, `GROUP BY`, `COUNT`               |
| Forgetting                           | `delete` by id, or find-and-delete by query                                           |

A plain vector store gives you the first of these and nothing else. Keeping keyword search,
semantic search, and SQL in one engine is what removes the separate keyword index, the
rerank service, and the second database an agent memory usually needs.

## Build it

The [agent-memory example](https://github.com/infino-ai/infino/tree/main/infino-node/examples/agent-memory)
is a runnable implementation on the Node binding. It loads one real, months-long,
multi-session conversation from [LOCOMO](https://github.com/snap-research/locomo), a public
long-term conversational-memory dataset, turns each message into a memory timestamped with
its session, and then demonstrates hybrid recall, SQL over memory, and deletion against it.

```bash theme={null}
npm install @infino-ai/infino
```

Start from the [Quickstart](/quickstart) for the shape of a table, embeddings, and search,
then follow the example for the memory-specific parts.

## Why Infino for agent memory

* **Hybrid recall in one engine.** Keyword (BM25) and semantic (vector) matches are fused
  in a single query, so an agent finds memories by exact terms and by meaning at once, with
  no separate keyword index or rerank service.
* **Object-storage-native.** Memory is stored as Apache Parquet on a local path or object
  storage; it scales with the agent's history rather than a fixed cluster.
* **SQL over memory.** The same store answers structured and time-based questions over an
  agent's history.

## See also

* [Agent-memory example](https://github.com/infino-ai/infino/tree/main/infino-node/examples/agent-memory)
* [Tutorials](/tutorials)
* [How Infino works](/core-concepts)