# mnemodb

Keeps agent memory inside plain Markdown files in your repository, with Git history, trust levels, and lifecycle tracking.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: mnemodb
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mnemodb/mnemodb
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/mnemodb

## What it does

MnemoDB structures persistent agent context as plain `.mem.md` files in the repository. Each entry uses a standard Markdown heading accompanied by inline metadata for source attribution, confidence, and supersession. You can inspect the files manually and review memory updates via standard `git diff`.

Under the hood, the server exposes eleven memory-focused tools, including `memory_recall`, `memory_remember`, and `memory_compact`. The internal trust model flags facts gathered from tool executions as untrusted, preventing external outputs from overwriting manual rules set by the engineer.

Running the package requires `npx`, and storage defaults to a local `.memory/` directory created upon the first saved entry.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `MNEMO_STORE` — 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 MNEMO_STORE=<MNEMO_STORE> --transport stdio mnemodb -- npx -y @mnemodb/mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add mnemodb --env MNEMO_STORE=<MNEMO_STORE> -- npx -y @mnemodb/mcp
```
Replace <…> with your own values

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e MNEMO_STORE=<MNEMO_STORE> mnemodb npx -y @mnemodb/mcp
```
Replace <…> with your own values

## When to use it
- store agent decisions in plain repository files that track cleanly in Git
- prevent tool outputs from overwriting instructions set by the developer
- retire stale context entries through auditable compaction
- share agent knowledge between Claude Code, Cursor, and other MCP clients

## Example prompts
- Remember that our team prefers pnpm over npm for package management
- Recall project architectural decisions before drafting this service
- Run a compaction pass to archive expired context entries

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
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