docs: add Mnemosyne to memory providers page#34679
Closed
AxDSan wants to merge 1 commit into
Closed
Conversation
Adds Mnemosyne as a documented external memory provider alongside Memori. Mnemosyne is a local-first, zero-cloud memory provider with 23 tools, vector search + FTS5 hybrid ranking, knowledge graph, episodic consolidation, multi-agent validation, and shared surface. Changes: - Add Mnemosyne section with setup, tools, and key capabilities - Add Mnemosyne row to the comparison table - Remove stale '8 providers' count from header and cross-references (replace with 'supported providers' to stay maintainable) - Update cross-references in overview.md, memory.md, integrations/index.md - Same updates in Chinese (zh-Hans) i18n files
Collaborator
Contributor
Author
|
Good catch — I see #34356 from @Bartok9 went up at 04:17 UTC, about 12 hours before this one. Credit where it's due for first submission. The two PRs overlap on the core docs section but diverge in scope:
Best path IMO: merge scopes into whichever PR the maintainers prefer as the base. Happy to forward-port the i18n/cross-ref/stale-count changes onto #34356 if that's cleaner — those aren't Mnemosyne-specific, they're general doc hygiene. |
Contributor
Author
This was referenced May 29, 2026
Contributor
Author
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Mnemosyne — a local-first, zero-cloud memory provider — to the memory providers page. 23 tools, SQLite-backed vector search + FTS5 hybrid ranking, knowledge graph, episodic consolidation, multi-agent validation, shared surface, and import/export. No API keys. No network calls.
Changes
Alignment with Contributing Guidelines
Per CONTRIBUTING.md policy (enforced in prior submissions like #34271), new memory providers must be standalone plugin repos — not in-tree additions under
plugins/memory/. Mnemosyne follows this convention: the adapter ships aspip install mnemosyne-hermeswith entry-point discovery viamnemosyne-hermes install, noplugin.yamlor core changes needed.Setup:
pip install mnemosyne-hermes mnemosyne-hermes install hermes config set memory.provider mnemosyneNo API key. No cloud. Just local SQLite with vector search at
$HERMES_HOME/mnemosyne/.