hermes - 💡(How to fix) Fix Feature: Add native plugin for Memorose long-term memory backend [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
NousResearch/hermes-agent#17461Fetched 2026-04-30 06:47:29
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Participants
Timeline (top)
labeled ×4

Currently, Hermes Agent supports multiple third-party memory providers (Mem0, Supermemory, Honcho, etc.) located in plugins/memory/.

However, it lacks a dedicated integration for the Memorose System, which provides extremely fast, local/hybrid persistent memory. This issue proposes a MemoryProvider plugin implementation for Memorose that fully hooks into the tool schemas (memorose_store, memorose_search) and the system prompt injection lifecycle.

Root Cause

Currently, Hermes Agent supports multiple third-party memory providers (Mem0, Supermemory, Honcho, etc.) located in plugins/memory/.

However, it lacks a dedicated integration for the Memorose System, which provides extremely fast, local/hybrid persistent memory. This issue proposes a MemoryProvider plugin implementation for Memorose that fully hooks into the tool schemas (memorose_store, memorose_search) and the system prompt injection lifecycle.

Fix Action

Fix / Workaround

Implementation Details

The proposed implementation lives in plugins/memory/memorose/__init__.py and integrates via:

  1. MEMOROSE_API_KEY and MEMOROSE_BASE_URL configuration variables.
  2. Exposing the memorose_search and memorose_store tool schemas to the agent context window via get_tool_schemas().
  3. Dispatching memory actions through the standard handle_tool_call() interface to the Memorose backend API.
RAW_BUFFERClick to expand / collapse

Description

Currently, Hermes Agent supports multiple third-party memory providers (Mem0, Supermemory, Honcho, etc.) located in plugins/memory/.

However, it lacks a dedicated integration for the Memorose System, which provides extremely fast, local/hybrid persistent memory. This issue proposes a MemoryProvider plugin implementation for Memorose that fully hooks into the tool schemas (memorose_store, memorose_search) and the system prompt injection lifecycle.

Implementation Details

The proposed implementation lives in plugins/memory/memorose/__init__.py and integrates via:

  1. MEMOROSE_API_KEY and MEMOROSE_BASE_URL configuration variables.
  2. Exposing the memorose_search and memorose_store tool schemas to the agent context window via get_tool_schemas().
  3. Dispatching memory actions through the standard handle_tool_call() interface to the Memorose backend API.

I have already prepared the code for this integration. I can submit a Pull Request if this feature aligns with the project's memory provider ecosystem goals.

extent analysis

TL;DR

Implement a MemoryProvider plugin for the Memorose System by integrating it into the existing plugin architecture in plugins/memory/.

Guidance

  • Review the proposed implementation in plugins/memory/memorose/__init__.py to ensure it aligns with the project's memory provider ecosystem goals.
  • Verify that the MEMOROSE_API_KEY and MEMOROSE_BASE_URL configuration variables are properly handled and secured.
  • Check the implementation of get_tool_schemas() to ensure it correctly exposes the memorose_search and memorose_store tool schemas.
  • Test the integration by dispatching memory actions through the handle_tool_call() interface to the Memorose backend API.

Example

No code example is provided as the implementation details are already outlined in the issue.

Notes

The success of this integration depends on the correctness of the proposed implementation and its alignment with the project's goals. It is essential to review and test the implementation thoroughly.

Recommendation

Apply workaround: Implement the proposed MemoryProvider plugin for the Memorose System, as it seems to be a well-thought-out solution that aligns with the project's architecture.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix Feature: Add native plugin for Memorose long-term memory backend [1 participants]