Add Amazon S3 Vector Memory tool for memory management #260
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
September 20, 2025 13:47
- Provides persistent memory storage using Amazon S3 Vectors - Includes automatic user isolation for security - Supports store, retrieve, and list operations - Uses Amazon Bedrock for text embeddings - Configurable via environment variables
- Provides persistent memory storage using Amazon S3 Vectors - Includes automatic user isolation for security - Supports store, retrieve, and list operations - Uses Amazon Bedrock for text embeddings - Configurable via environment variables
elizabethfuentes12
requested a deployment
to
manual-approval
GitHub Actions
Waiting
cagataycali
reviewed
Sep 25, 2025
|
|
||
| Usage: | ||
| from strands import Agent | ||
| from strands_tools.s3_vector_memory import s3_vector_memory |
There was a problem hiding this comment.
I'd love to add more abilities into s3 vector implementation like scaffolding an S3 vectors when it's not available,
here's one example implementation: https://github.com/strands-agents/samples/blob/feat/research-agent-sample/02-samples/14-research-agent/src/strands_research_agent/tools/s3_memory.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR introduces a new Amazon S3 Vector Memory tool that provides AWS-native memory management for Strands agents using Amazon S3 Vectors as the backend storage.
Key Features:
• Persistent memory storage using Amazon S3 Vectors with vector similarity search
• Automatic user isolation for security (all operations require user_id)
• Three core operations: store, retrieve, and list memories
• Integration with Amazon Bedrock for text embeddings (default: amazon.titan-embed-text-v2:0)
• Flexible configuration via environment variables with sensible defaults
• Similarity-based memory retrieval with configurable thresholds
• Automatic memory key generation with timestamps and unique identifiers
Use Cases:
• Multi-session agent conversations with persistent context
• User-specific memory isolation in multi-tenant applications
• Scalable memory backend for production agent deployments
• AWS-native alternative to existing memory solutions
Related Issues
Documentation PR
Type of Change
New Tool
Testing
How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli
hatch run prepareChecklist
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.