# Mnemosyne

The Mnemosyne local MCP server stores an agent’s knowledge and its evidence in SQLite. When a source is corrected, dependent memories are retired.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 162 repo stars
- Author: 28naem-del
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/28naem-del/mnemosyne
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/mnemosyne

## What it does

Mnemosyne keeps an agent’s long-term memory in a single SQLite file. Each record retains its source and trust tier, and earlier versions remain inspectable after a correction. When a source changes, dependent records are retired so the agent can work from the current evidence.

Connect the server to Claude Code, Codex, Cursor, and other clients through MCP. The project also offers a TypeScript SDK, CLI, and HTTP interface. Its local engine runs without a model API key, a separate database server, or Docker. Node.js 22.16 or later is required.

Corrections can affect procedures and skills linked to the original record. That means an agent should not keep following instructions grounded in a superseded requirement.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `MNEMOSYNE_INDEX_MODE` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env MNEMOSYNE_INDEX_MODE=<MNEMOSYNE_INDEX_MODE> --transport stdio mnemosyne -- npx -y mnemosy-ai
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add mnemosyne --env MNEMOSYNE_INDEX_MODE=<MNEMOSYNE_INDEX_MODE> -- npx -y mnemosy-ai
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mnemosyne": {
            "command": "npx",
            "args": [
                "-y",
                "mnemosy-ai"
            ],
            "env": {
                "MNEMOSYNE_INDEX_MODE": "<MNEMOSYNE_INDEX_MODE>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mnemosyne": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "mnemosy-ai"
            ],
            "env": {
                "MNEMOSYNE_INDEX_MODE": "<MNEMOSYNE_INDEX_MODE>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e MNEMOSYNE_INDEX_MODE=<MNEMOSYNE_INDEX_MODE> mnemosyne npx -y mnemosy-ai
```
Replace <…> with your own values

## When to use it
- retain agent knowledge across sessions
- inspect the evidence behind a memory
- retire procedures after a source is corrected
- trace records that affected a retrieval

## Example prompts
- Save this decision with its source so you can use it in later sessions.
- Correct the stored requirement and retire instructions that depend on it.
- Show which records affected this retrieval.

## Similar
- [ontology](https://affpapa.org/en/nevibecode/skills/ontology.md) — skill · 3700 installs
- [agent-recall](https://affpapa.org/en/nevibecode/plugins/agent-recall.md) — plugin · ★ 15 repo stars
- [how-it-works](https://affpapa.org/en/nevibecode/skills/how-it-works.md) — skill · 5600 installs
- [lore](https://affpapa.org/en/nevibecode/mcp/lore.md) — MCP server · ★ 16 repo stars
- [kernel](https://affpapa.org/en/nevibecode/plugins/kernel.md) — plugin · ★ 1596 repo stars
- [Mnemosyne OS](https://affpapa.org/en/nevibecode/mcp/mnemosyne-os.md) — MCP server · ★ 24 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
