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

# storage • AI Agents Framework

> Storage adapter implementations for PraisonAI.

# storage

AI Agents Framework

Storage adapter implementations for PraisonAI.

Heavy implementations that follow StorageBackendProtocol for:

* Redis (praisonai\[redis])
* MongoDB (praisonai\[mongodb])
* PostgreSQL (praisonai\[postgresql])
* DynamoDB (praisonai\[dynamodb])
* Valkey (praisonai\[valkey])

NOTE: `praisonai.storage` holds the canonical, low-level storage adapters.
It is NOT dead code — `praisonai.persistence` builds on top of it. For
example `praisonai.persistence.state.redis.RedisStateStore` is a thin wrapper
around `RedisStorageAdapter` defined here, and `MongoDBStateStore` obtains
its pymongo client from `MongoDBStorageAdapter`, so this module is
load-bearing and canonical for the backends that `persistence` wraps.
Valkey shares driver init via `persistence._valkey_client`.

Note on remaining duplication: `persistence.state.dynamodb` keeps its own
boto3 setup because it uses a different partition-key schema (`pk`) than the
adapter (`key`); collapsing it would change stored-data layout. The
`persistence.state` stores layer per-key TTL, hash operations
(`hget`/`hset`) and counters on top of the KV/blob adapters here.

Application code that just needs a persistence layer should use
`create_state_store`, `create_conversation_store`, or
`create_knowledge_store` from `praisonai.persistence.factory`.

## Import

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai import storage
```

***

## Related Documentation

> [card] [RAG Concept](https://praison.ai/docs/docs/concepts/rag)

> [card] [RAG Overview](https://praison.ai/docs/docs/rag/overview)

> [card] [Chunking Strategies](https://praison.ai/docs/docs/rag/strategies/overview)


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