A project-local memory store that keeps evidence-backed facts in a SQLite database, a small file-based database. When a fact is corrected, related memories can be retired.

Use it to save and retrieve project facts, decisions, preferences, and procedures for later coding sessions.

It reduces repeated explanations while keeping project memory local and traceable. Corrections help prevent outdated guidance from being reused.

mnemosyne — Plugin for Claude Code by 28naem-del

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/28naem-del/mnemosyne

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/28naem-del/mnemosyne/claude-code/github.svg)](https://agentmods.dev/plugins/28naem-del/mnemosyne/claude-code)

Your own site

<a href="https://agentmods.dev/plugins/28naem-del/mnemosyne/claude-code"><img src="https://agentmods.dev/badge/plugins/28naem-del/mnemosyne/claude-code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/28naem-del/mnemosyne/claude-code"><img src="https://agentmods.dev/badge/plugins/28naem-del/mnemosyne/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mnemosyne scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/claude-code/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "name": "mnemosyne",
  "displayName": "Mnemosyne",
  "version": "3.0.0-rc.4",
  "description": "Evidence-tracked local memory over MCP: one SQLite file per project at .mnemosyne/memory.sqlite; corrections retire dependent memories.",
  "author": {
    "name": "28naem-del",
    "url": "https://github.com/28naem-del"
  },
  "homepage": "https://mnemosy.ai",
  "repository": "https://github.com/28naem-del/mnemosyne",
  "license": "MIT",
  "keywords": ["memory", "mcp", "sqlite", "local-first"]
}

Contents

What it installs

The manifest is a name and a version. 1 MCP server travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

MCP server mnemosyne A not measured

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 15 lines scan A e83a4a8d50d4

Subscribe to this mod's changes

mnemosyne is a plugin published in the GitHub repository 28naem-del/mnemosyne (154 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.

LLM Memory and context ai-agents model-context-protocol sqlite

cpersona

Hooks and an agent skill that make an agent use CPersona's memory at the right moments: look before the first action and before each answer, store as it goes, and restore the task after the conversation is compacted. Connect the CPersona MCP server separately.

Cloto-dev/CPersona · not measured

rekal-skills

Skills and hooks for rekal: memory redirect hooks, session capture (rekal-save), project bootstrap (rekal-init), and maintenance (rekal-hygiene).

janbjorge/rekal · not measured

lore

Memory for Claude Code that reasons about you and improves itself: Honcho-pattern belief store with deriver, dreamer and dialectic (/lore:ask), automatic skillification with a closed judge/update/retire loop, on a Hermes-pattern core — hard-capped curated memory, FTS5 session search, staged review.

docwilde/LORE · not measured

token-optimizer

Context-window optimization tools (caching, compression, smart file tooling) for the Gemini CLI.

ooples/token-optimizer-mcp · not measured

hypermnesia-mcp

Cortex — persistent memory for Claude Code that remembers across sessions automatically. Install and forget. Inspectable neuroscience-inspired mechanisms with published references; committed ablations do not establish a retrieval gain from all 36 mechanisms. (Renamed from the 'cortex' plugin to match the…

cdeust/Cortex · not measured

cortex

Persistent local-first memory MCP server: remember/recall with thermodynamic heat and decay, knowledge graph, autonomous wiki, local SQLite store by default. Requires uv (uvx) on PATH; hooks-based auto-capture is Claude Code-only — on Gemini CLI memory is manual-tool-driven.