agentleFS
mnemosyne-ossmnemosyne-oss/mnemosyne/skills/hermes-memory-providers/SKILL.md

hermes-memory-providers

Skill3.7k starsChanged 5 months agoMITView on GitHub

Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.

  • Installs packages

1 other project uses a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 2 mentionsAug 2026: 2 mentionsSep 2026: 6 mentionsOct 2026: 7 mentionsNov 2026: 4 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the mnemosyne-oss/mnemosyne repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about mnemosyne-oss/mnemosyne

The biggest 5 of 21 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 21

Talked about on GitHub (21 times).

On GitHub · 21

16 more on GitHub
  • Other versions1 project uses a version of this.

    Word for word · 1

    1. AxDSan/mnemosyne★ 3.7k100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All without touching Hermes core — deployed purely through the plugin directory.

    line 33
  2. Very specific:

    Do NOT run hermes tools disable memory — that also kills all 20 Mnemosyne-registered tools.

    line 104
  3. Distinctive:

    Test in a conversation:

    line 114

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mnemosyne — Hermes Memory Provider

Mnemosyne is a local-first memory layer for AI agents. When deployed as a Hermes memory provider, it replaces the built-in MEMORY.md/USER.md system with SQLite-backed vector + FTS5 hybrid search, episodic consolidation, temporal knowledge graphs, and optional bidirectional sync.

100% local. Zero cloud. Sub-millisecond recall.

What It Gives You

  • System prompt injection — # Mnemosyne Memory context block in every prompt
  • Pre-turn prefetch — relevant memories injected before each LLM call
  • Post-turn sync — conversation turns auto-stored to episodic memory
  • 20 tools auto-injected into the model's tool surface (remember, recall, sleep, triples, scratchpad, graph, sync, diagnostics, etc.)
  • 3 lifecycle hooks — pre_llm_call, on_session_start, post_tool_call
  • CLI commands — hermes mnemosyne {stats|sleep|inspect|export|import|clear|version}

All without touching Hermes core — deployed purely through the plugin directory.

Quick Check

hermes memory status     # See active provider and installed plugins

Install

Step 1 — Install the package

pip install mnemosyne-hermes

Debian/Trixie users (bare pip blocked): use a venv first:

python3 -m venv ~/.hermes/hermes-agent/venv
source ~/.hermes/hermes-agent/venv/bin/activate
pip install mnemosyne-hermes

mnemosyne-hermes wraps the core mnemosyne-memory library with the plugin manifest and entry points Hermes needs. It does not pull embeddings or LLM deps — pair it with one of:

ExtraWhenRAM
(core only)Raspberry Pi, remote embedding API~50 MB
mnemosyne-memory[embeddings]Local vector search (fastembed ONNX)~800 MB
mnemosyne-memory[all]Local embeddings + local LLM consolidation~1.5 GB

Step 2 — Link the plugin

mnemosyne-hermes install

This creates the symlink ~/.hermes/plugins/mnemosyne/ → <installed package> so Hermes discovers it on startup.

Docker / read-only venv — use persistent wrapper mode so the plugin survives image rebuilds:

mnemosyne-hermes install --mode wrapper --python /path/to/venv/bin/python --hermes-home /opt/data
mnemosyne-hermes status --hermes-home /opt/data
hermes gateway restart

Step 3 — Activate

hermes config set memory.provider mnemosyne
hermes memory setup

Step 4 — (Optional) Disable built-in memory

Mnemosyne is additive by default — the built-in MEMORY.md/USER.md keeps running alongside it. To make Mnemosyne the sole memory system, edit ~/.hermes/config.yaml:

memory:
  memory_enabled: false
  user_profile_enabled: false

Do NOT run hermes tools disable memory — that also kills all 20 Mnemosyne-registered tools.

Step 5 — Verify

hermes memory status       # Should show "Provider: mnemosyne"
hermes mnemosyne stats     # Working + episodic memory counts

Test in a conversation:

hermes chat -q "Remember that I love apples. What do I love?"

You should see mnemosyne_remember and mnemosyne_recall calls succeed.

If hermes mnemosyne stats gives "invalid choice: 'mnemosyne'", the plugin CLI registration didn't load. Use hermes hermes-mnemosyne stats as a fallback, or re-run Step 2 to relink.

MCP vs. Provider Plugin

Mnemosyne ships an MCP server (mnemosyne mcp, stdio + SSE + Streamable HTTP transports) that exposes 29 tools — usable with any MCP-compatible client (Claude Desktop, etc.):

mnemosyne mcp                              # stdio transport
mnemosyne mcp --transport sse --port 8080  # SSE transport
mnemosyne mcp --transport streamable-http --port 8080  # native MCP http transport

For Hermes, prefer the provider plugin over MCP. The provider plugin gives deeper integration that MCP cannot: the pre_llm_call context injection hook, on_session_start initialization, post_tool_call memory capture, and the hermes mnemosyne CLI subcommands. MCP is a generic fallback for non-Hermes agents.

Switching Back

hermes memory off          # Disable external provider, revert to built-in
hermes memory setup        # Or use the interactive picker

Or manually:

hermes config set memory.provider memory

Then restart Hermes.

CLI Commands

hermes mnemosyne stats                # Current session stats
hermes mnemosyne stats --global       # Stats across all sessions
hermes mnemosyne inspect "query"      # Search memories
hermes mnemosyne sleep                # Run consolidation (working → episodic)
hermes mnemosyne export --output backup.json
hermes mnemosyne import --input backup.json
hermes mnemosyne clear                # Clear scratchpad
hermes mnemosyne version              # Show version

Data Location

~/.hermes/mnemosyne/
└── data/
    ├── mnemosyne.db              # Main SQLite database (WAL mode)
    ├── triples.db                # Standalone TripleStore
    └── banks/<name>/mnemosyne.db # Named memory banks (per-bank isolation)

Persists across sessions via ~/.hermes/ (including on ephemeral VMs like Fly.io).

Optional: Host LLM Routing

Mnemosyne's consolidation (sleep) and fact extraction can use a local GGUF or a remote OpenAI-compatible API. Hermes users with OAuth-backed providers (e.g. openai-codex) can route those LLM calls through Hermes' authenticated auxiliary client instead — no extra credentials needed:

export MNEMOSYNE_HOST_LLM_ENABLED=true

See docs/hermes-llm-integration.md for the full behavior model and config.

Troubleshooting

SymptomCause / Fix
hermes memory status shows built-in onlyProvider not loaded; restart Hermes after install.
Plugin listed but unavailableMissing Python deps in Hermes' venv; pip install mnemosyne-hermes in that venv.
hermes mnemosyne stats → "invalid choice"Plugin CLI registration didn't load; use hermes hermes-mnemosyne stats or relink (Step 2).
Memory not recalled across sessionsProvider loaded but session didn't restart; new sessions pick up the provider.
mnemosyne_hermes import error in DockerUse wrapper mode: mnemosyne-hermes install --mode wrapper --python <venv>/bin/python.

References

  • Hermes Integration Guide — canonical setup reference
  • Hermes Auxiliary LLM Integration — host LLM routing
  • Mnemosyne vs Hindsight Comparison — architecture and feature comparison
  • hermes-agent skill — general Hermes setup, config, and plugin system

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.