Cortexdb Memory Hermes
liliang-cn/cortexdb
Give a Python agent (such as Hermes Agent by Nous Research) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client…
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
Install Hermes Memory Providers
$ npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mnemosyne-oss/mnemosyne hermes-memory-providers --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mnemosyne-oss/mnemosyne.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hermes-memory-providers .claude/skills/hermes-memory-providers && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hermes-memory-providers" agent skill from https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providers into .claude/skills/hermes-memory-providers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-memory-providers", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providersType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mnemosyne-oss/mnemosyne hermes-memory-providers --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mnemosyne-oss/mnemosyne.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hermes-memory-providers .agents/skills/hermes-memory-providers && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hermes-memory-providers" agent skill from https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providers into .agents/skills/hermes-memory-providers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-memory-providers", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mnemosyne-oss/mnemosyne hermes-memory-providers --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mnemosyne-oss/mnemosyne.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hermes-memory-providers .cursor/skills/hermes-memory-providers && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hermes-memory-providers" agent skill from https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providers into .cursor/skills/hermes-memory-providers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-memory-providers", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mnemosyne-oss/mnemosyne.git --path skills/hermes-memory-providers--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mnemosyne-oss/mnemosyne hermes-memory-providers --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mnemosyne-oss/mnemosyne.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hermes-memory-providers .gemini/skills/hermes-memory-providers && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hermes-memory-providers" agent skill from https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providers into .gemini/skills/hermes-memory-providers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-memory-providers", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mnemosyne-oss/mnemosyne hermes-memory-providersInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mnemosyne-oss/mnemosyne.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hermes-memory-providers .github/skills/hermes-memory-providers && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hermes-memory-providers" agent skill from https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providers into .github/skills/hermes-memory-providers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-memory-providers", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mnemosyne-oss/mnemosyne hermes-memory-providers --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mnemosyne-oss/mnemosyne.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hermes-memory-providers .opencode/skills/hermes-memory-providers && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hermes-memory-providers" agent skill from https://github.com/mnemosyne-oss/mnemosyne/tree/main/skills/hermes-memory-providers into .opencode/skills/hermes-memory-providers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-memory-providers", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
hermes-memory-providers- GitHub stars
- 3.4k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 562 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
- Works in 5 steps: Install the package → Link the plugin → Activate → …
- Tasks that involve Vector databases
- SKILL.md covers What It Gives You, Quick Check, Install and MCP vs. Provider Plugin, plus 6 more sections
- Calls pip and python3
What it does
Hermes Memory Providers is an agent skill from mnemosyne-oss/mnemosyne. Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Vector databases, Agent memory and Knowledge graphs. It works with SQLite. The repository describes itself as: Zero-cloud AI memory that works everywhere. SQLite-backed. One pure-Python dependency. The licence is MIT.
When your agent uses it
- Tasks that involve Vector databases
- Tasks that involve Agent memory
- Tasks that involve Knowledge graphs
Example prompts
- “/hermes-memory-providers”
Requirements
- Python 3
- Docker
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit bf22366. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pippython3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Hermes Memory Providers loads about 1.8k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 562 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mnemosyne-oss/mnemosyne at commit bf22366, republished under its MIT licence (© mnemosyne-oss). 562 words, ~1,772 tokens.
Download SKILL.mdSave it as
.claude/skills/hermes-memory-providers/SKILL.md (or your agent's skills folder).- name
- hermes-memory-providers
- description
- Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
- version
- 2.0.0
- author
- Mnemosyne
- license
- MIT
- platforms
- linux, macos, windows
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 Memorycontext 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 pluginsInstall
Step 1 — Install the package
pip install mnemosyne-hermesDebian/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-hermesmnemosyne-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:
| Extra | When | RAM |
|---|---|---|
| (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 installThis 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 restartStep 3 — Activate
hermes config set memory.provider mnemosyne
hermes memory setupStep 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: falseDo 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 countsTest 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 statsgives "invalid choice: 'mnemosyne'", the plugin CLI registration didn't load. Usehermes hermes-mnemosyne statsas a fallback, or re-run Step 2 to relink.
Show full SKILL.md (255 more words)Show less
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 transportFor 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 pickerOr manually:
hermes config set memory.provider memoryThen 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 versionData 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=trueSee docs/hermes-llm-integration.md for the full behavior model and config.
Troubleshooting
| Symptom | Cause / Fix |
|---|---|
hermes memory status shows built-in only | Provider not loaded; restart Hermes after install. |
Plugin listed but unavailable | Missing 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 sessions | Provider loaded but session didn't restart; new sessions pick up the provider. |
mnemosyne_hermes import error in Docker | Use 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-agentskill — general Hermes setup, config, and plugin system
© mnemosyne-oss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/hermes-memory-providers of mnemosyne-oss/mnemosyne.
Open the folder on GitHubat commit bf22366
Compare with similar skills
Hermes Memory Providers next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hermes Memory Providers this skillmnemosyne-oss/mnemosyne | 3.4k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Cortexdb Memory Hermesliliang-cn/cortexdb | 274 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Cortexdb Memory Openclawliliang-cn/cortexdb | 274 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Cognee Session Memory and Improvetopoteretes/cognee | 32k | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | |
| Ogham Maintainogham-mcp/ogham-mcp | 115 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Ogham Recallogham-mcp/ogham-mcp | 115 | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
Cortexdb Memory Openclaw
liliang-cn/cortexdb
Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package.
Cognee Session Memory and Improve
topoteretes/cognee
Explains how cognee stores session memory by session_id and bridges it into the permanent graph with improve(), including the stages, results and settings.
Ogham Maintain
ogham-mcp/ogham-mcp
Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Ogham Recall
ogham-mcp/ogham-mcp
Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Cortexdb
liliang-cn/cortexdb
Use CortexDB for local-first AI memory, vector search, RAG, knowledge graphs, SPARQL/RDFS/SHACL, corpus-to-graph workflows, external structured-data import (CSV / SQL dumps), and MCP/tool calling.
More from mnemosyne-oss/mnemosyne
Mnemosyne Context
mnemosyne-oss/mnemosyne
Load this when working on the mnemosyne memory system — its repo, sync server, memory databases, or CI.
No Mistakes
mnemosyne-oss/mnemosyne
Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream.
Mnemosyne Memory Override
mnemosyne-oss/mnemosyne
Hard rule override that forces Mnemosyne for all durable memory storage.
Related
Works with
Questions about Hermes Memory Providers
What does Hermes Memory Providers do?
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs. Hermes Memory Providers is an agent skill from mnemosyne-oss/mnemosyne. Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
When should I use Hermes Memory Providers?
Hermes Memory Providers fits situations like: tasks that involve Vector databases; tasks that involve Agent memory; tasks that involve Knowledge graphs.
How do I install Hermes Memory Providers in Claude Code?
Run `npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a claude-code`. Or copy the skill folder (skills/hermes-memory-providers in mnemosyne-oss/mnemosyne) into .claude/skills/hermes-memory-providers in your project. Claude Code loads it when a task matches its description.
How do I install Hermes Memory Providers in Codex?
Run `npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a codex`. Or copy the skill folder (skills/hermes-memory-providers in mnemosyne-oss/mnemosyne) into .agents/skills/hermes-memory-providers in your project. Codex loads it when a task matches its description.
Can I use Hermes Memory Providers in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mnemosyne-oss/mnemosyne --skill hermes-memory-providers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hermes-memory-providers, .gemini/skills/hermes-memory-providers, .github/skills/hermes-memory-providers and .opencode/skills/hermes-memory-providers in your project.
What does Hermes Memory Providers need to run?
Going by SKILL.md and its folder, Hermes Memory Providers needs the command-line tools its instructions call (pip and python3). Our summary lists: Python 3; Docker.
Does Hermes Memory Providers access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Hermes Memory Providers safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Hermes Memory Providers use?
Hermes Memory Providers is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Hermes Memory Providers use?
About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Hermes Memory Providers?
Skills that share tags, products or a category with Hermes Memory Providers: Cortexdb Memory Hermes (liliang-cn/cortexdb, 274 stars), Cortexdb Memory Openclaw (liliang-cn/cortexdb, 274 stars), Cognee Session Memory and Improve (topoteretes/cognee, 32k stars) and Ogham Maintain (ogham-mcp/ogham-mcp, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hermes Memory Providers?
mnemosyne-oss (a GitHub organization) maintains it in mnemosyne-oss/mnemosyne, which has 3,375 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.
Source: mnemosyne-oss/mnemosyne on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.