mem0ai/mem0

feat(ts-sdk): add AWS S3 Vectors vector store

Open

#5,785 opened on 2026年6月23日

GitHub で見る
 (0 comments) (0 reactions) (0 assignees)Python (6,343 forks)batch import
enhancementhelp wantedsdk-typescriptsize:Lvector-store

Repository metrics

Stars
 (55,741 stars)
PR merge metrics
 (平均マージ 6d 11h) (30d で 208 merged PRs)

説明

Summary

The Python SDK supports AWS S3 Vectors as a vector store provider, but the TypeScript OSS SDK (mem0ai/oss) does not. Add it to bring the TS SDK to parity.

Python reference mem0/vector_stores/s3_vectors.py
Registered in (Python) mem0/utils/factory.py (VectorStoreFactory)
Target file (TypeScript) mem0-ts/src/oss/src/vector_stores/s3_vectors.ts
Suggested implementation Use the AWS-official @aws-sdk/client-s3vectors.

Requirements

  • Implement S3Vectors in mem0-ts/src/oss/src/vector_stores/s3_vectors.ts, extending VectorStore (mem0-ts/src/oss/src/vector_stores/base.ts) and mirroring the Python provider's behavior (insert / search / get / update / delete / list / reset).
  • Register the "s3_vectors" provider in mem0-ts/src/oss/src/utils/factory.ts (VectorStoreFactory).
  • Add config typing in mem0-ts/src/oss/src/types/.
  • Add a unit test under mem0-ts/src/oss/src/tests/.
  • Add @aws-sdk/client-s3vectors to mem0-ts/package.json (optional/peer dependency, lazy-imported like other providers).
  • Update docs under docs/ if this provider is user-facing.

Reference pattern

Mirror an existing TS provider: vector_stores/qdrant.ts.

Notes

Mirror mem0/vector_stores/s3_vectors.py. AWS credential chain.


Part of the TypeScript ↔ Python SDK provider-parity effort. One provider per issue (atomic).

コントリビューターガイド