# Question on Memory Plugin Access Control and DLS/FLS Integration

**URL:** <https://forum.opensearch.org/t/question-on-memory-plugin-access-control-and-dls-fls-integration/27601>\
**Category:** Machine Learning\
**Created:** [December 10, 2025, 1:50am UTC](https://forum.opensearch.org/t/question-on-memory-plugin-access-control-and-dls-fls-integration/27601 "2025-12-10T01:50:28Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![bwa](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/bwa/32/9756_2.png) [@bwa](https://forum.opensearch.org/u/bwa)\
**Post date:** [December 10, 2025, 1:50am UTC](https://forum.opensearch.org/t/question-on-memory-plugin-access-control-and-dls-fls-integration/27601/1 "2025-12-10T01:50:28Z")

</div>

**Versions** (relevant - OpenSearch/Dashboard/Server OS/Browser):

**Describe the issue** :

**Configuration** :

**Relevant Logs or Screenshots** :

While reviewing the [OpenSearch Memory plugin code](https://github.com/opensearch-project/ml-commons/tree/main/memory), I noticed that access control seems limited to the conversation creator: an OpenSearch security user can only view memories from conversations they initiated. Even if a DLS rule granting broader access exists on the memory index, the plugin appears to enforce creator-only visibility, overriding DLS.

Is my understanding correct? If so, what is the reasoning behind not leveraging OpenSearch’s built-in DLS/FLS capabilities for memory access control? Are there plans to align this with the existing security model?

Thanks!

---

<div class="post-metadata">

**Author:** ![dhrubo](https://avatars.discourse-cdn.com/v4/letter/d/9e8a1a/32.png) [@dhrubo](https://forum.opensearch.org/u/dhrubo)\
**Post date:** [December 10, 2025, 6:42am UTC](https://forum.opensearch.org/t/question-on-memory-plugin-access-control-and-dls-fls-integration/27601/2 "2025-12-10T06:42:36Z")

</div>

Thanks for digging into this and for the detailed explanation.

The current Memory plugin is quite limited in how it handles access control today. In parallel, we’ve been working on a newer **Agentic Memory** capability in the ML Commons plugin, which is designed with a more flexible model in mind.

You can find the docs here: [https://docs.opensearch.org/latest/ml-commons-plugin/agentic-memory/](https://docs.opensearch.org/latest/ml-commons-plugin/agentic-memory/)

It might be worth taking a look to see if it better matches your use case, and we’d really appreciate any feedback you have on it.

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex019/uploads/mauve_hedgehog/original/2X/3/33547ea01a5b12dcca2958411d3edd97ae2ea8c1.png) [@system](https://forum.opensearch.org/u/system)\
**Post date:** [February 8, 2026, 6:43am UTC](https://forum.opensearch.org/t/question-on-memory-plugin-access-control-and-dls-fls-integration/27601/3 "2026-02-08T06:43:11Z")

</div>

Closed on February 8, 2026, 6:43am UTC

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.
