diff --git a/src/oss/python/integrations/providers/aws.mdx b/src/oss/python/integrations/providers/aws.mdx
index e98405e30..6c88fd51d 100644
--- a/src/oss/python/integrations/providers/aws.mdx
+++ b/src/oss/python/integrations/providers/aws.mdx
@@ -177,6 +177,63 @@ See a [usage example](/oss/integrations/document_loaders/glue_catalog).
 from langchain_community.document_loaders.glue_catalog import GlueCatalogLoader
 ```
 
+## Memory
+> You can use AWS databases to store `LangGraph` checkpointers.  These could include `Amazon DynamoDB`, `Amazon Aurora`, or `ElastiCache for Valkey`.
+> To use these, install the `langgraph-checkpoint-aws` library:
+
+<CodeGroup>
+    ```bash pip
+    pip install langgraph-checkpoint-aws
+    ```
+
+    ```bash uv
+    uv add langgraph-checkpoint-aws
+    ```
+</CodeGroup>
+
+### Overview
+> LangGraph checkpointers are used to save the state of a LangGraph thread at its current point in time.  
+> This allows you to pause and resume threads, or to recover from failures without losing progress.
+> Refer to the [LangGraph Checkpointers documentation](/guides/langgraph/checkpointers/) for more information.
+
+### DynamoDB Checkpointer
+> If your preferred database is DynamoDB, you can integrate the Dynamo DB Checkpointer for LangGraph.  
+
+> See a [usage example](https://github.com/langchain-ai/langchain-aws/blob/main/libs/langgraph-checkpoint-aws/README.md#4-dynamodb-checkpoint-storage), 
+> and for a demo, refer to this [Jupiter Notebook](https://github.com/langchain-ai/langchain-aws/blob/main/samples/memory/dynamodb_saver.ipynb).
+
+### Valkey Checkpointer
+> If your preferred database is ElastiCache for Valkey, you can integrate the Valkey Checkpointer for LangGraph.
+
+> See a [usage example](https://github.com/langchain-ai/langchain-aws/blob/main/libs/langgraph-checkpoint-aws/README.md#5-valkey-checkpoint-storage),
+> and for a demo, refer to this [Jupiter Notebook](https://github.com/langchain-ai/langchain-aws/blob/main/samples/memory/valkey_saver.ipynb)
+
+### Aurora Checkpointer
+> If your preferred database is `Amazon Aurora`, you can integrate the `Postgres` Checkpointer for LangGraph.
+> To use this checkpointer you'll need to install the `langgraph-checkpoint-postgres` library:
+
+<CodeGroup>
+    ```bash pip
+    pip install langgraph-checkpoint-postgres
+    ```
+
+    ```bash uv
+    uv add langgraph-checkpoint-postgres
+    ```
+</CodeGroup>
+
+> A simple example of using the `PostgresSaver` checkpointer instance is shown below (without connection pooling):
+<CodeGroup>
+    ```python
+    from langgraph.checkpoint.postgres import PostgresSaver
+
+    with PostgresSaver.from_conn_string(os.getenv("DB_URI")) as checkpointer:
+        # use the checkpointer
+    ```
+</CodeGroup>
+
+> See the [reference documentation](https://reference.langchain.com/python/langgraph/checkpoints/#langgraph.checkpoint.postgres) for details.
+
 ## Vector stores
 
 ### Amazon OpenSearch Service
@@ -259,6 +316,53 @@ vds = InMemoryVectorStore.from_documents(
 ```
 See a [usage example](/oss/integrations/vectorstores/memorydb).
 
+### Amazon ElastiCache for Valkey
+
+[Amazon ElastiCache for Valkey](https://docs.aws.amazon.com/AmazonElastiCache/latest/dg/engine-versions.html) is a fully
+managed, Valkey-compatible caching service that delivers ultra-fast performance. Valkey supports native vector search
+capabilities to store, index and search over vector embeddings with microsecond latency an up to 99% recall.
+
+We need to install the `langchain-aws` and `valkey-glide` packages:
+
+<CodeGroup>
+```bash pip
+    pip install langchain-aws valkey-glide
+```
+
+```bash uv
+    uv add langchain-aws valkey-glide
+```
+</CodeGroup>
+
+See an usage example [here](https://github.com/langchain-ai/langchain-aws/blob/main/libs/langgraph-checkpoint-aws/README.md#7-valkey-store-for-document-storage).
+
+For a demo reference, check [this Jupyter Notebook](https://github.com/langchain-ai/langchain-aws/blob/main/samples/memory/valkey_store.ipynb)
+
+### Amazon Aurora PostgreSQL (pgvector)
+
+[Amazon Aurora PostgreSQL-Compatible Edition](https://docs.aws.amazon.com/AmazonRDS/latest/AuroraUserGuide/AuroraPostgreSQL.Reference.html) with
+the [pgvector](https://github.com/pgvector/pgvector) extension provides a powerful solution for storing and searching vector embeddings. `pgvector` adds
+the ability to store, and search over ML-generated vector embeddings, supporting both exact and approximate near neighbor search.
+
+Developers can use Aurora PostgreSQL with `pgvector` as a unified store for both RAG retrieval and agentic long-term memory, 
+simplifying architecture by consolidating semantic search capabilities in a single managed database.
+
+To leverage this integration, we need to install the `langchain-postgres` package:
+
+<CodeGroup>
+```bash pip
+    pip install langchain-postgres
+```
+
+```bash uv
+    uv add langchain-postgres
+```
+</CodeGroup>
+
+Refer to [pgvector integration documentation](https://docs.langchain.com/oss/python/integrations/vectorstores/pgvector) for detailed usage instructions.
+
+For a comprehensive guide on using `pgvector` with Aurora PostgreSQL for RAG applications, consider reading [this AWS Blog post](https://aws.amazon.com/blogs/database/leverage-pgvector-and-amazon-aurora-postgresql-for-natural-language-processing-chatbots-and-sentiment-analysis/).
+
 ## Retrievers
 
 ### Amazon Kendra