Pre-submission checklist | 提交前检查

• I have searched existing issues and this hasn't been mentioned before | 我已搜索现有问题，确认此问题尚未被提及
• I have read the project documentation and confirmed this issue doesn't already exist | 我已阅读项目文档并确认此问题尚未存在
• This issue is specific to MemOS and not a general software issue | 该问题是针对 MemOS 的，而不是一般软件问题

Bug Description | 问题描述

The .env file had NEO4J_BACKEND=neo4j-community, which should activate the Neo4jCommunityGraphDB backend. However, this class does not override the add_nodes_batch() method, which is used by the add memory pipeline for performance reasons. As a result, the call silently falls back to the base implementation in Neo4jGraphDB, defined in neo4j.py, which does not handle writes appropriately for the community edition. This leads to the add memory step appearing to complete successfully, but actually skipping data insertion into Qdrant.

How to Reproduce | 如何重现

Every time adding a memory when using neo4j-community.

Environment | 环境信息

NEO4J_BACKEND=neo4j-community

Additional Context | 其他信息

No response

Willingness to Implement | 实现意愿

• I'm willing to implement this myself | 我愿意自己解决
• I would like someone else to implement this | 我希望其他人来解决