# memtomem

A local memory layer for AI coding agents that indexes notes and code, then retrieves them with keyword and semantic search.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 18
- Author: memtomem
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/memtomem/memtomem
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/memtomem

## What it does

memtomem builds a searchable knowledge base from Markdown notes, documents, and code. It handles `.md`, `.json`, `.yaml`, `.toml`, `.py`, and JavaScript/TypeScript files, combining BM25 keyword matching with vector similarity. Your files remain the source of truth while the database can be rebuilt.

The server runs locally and connects to Claude Code with `claude mcp add memtomem -- uvx memtomem`. Core memory actions happen when the agent calls them; client hooks are optional integrations. Python 3.12 or newer is required, so check that runtime before setup.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add memtomem -- uvx memtomem
```
uvx runs the command named after the package; if the README names another one, use uvx --from memtomem <command>

### Codex

**Platform CLI**
```bash
codex mcp add memtomem -- uvx memtomem
```
uvx runs the command named after the package; if the README names another one, use uvx --from memtomem <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "memtomem": {
            "command": "uvx",
            "args": [
                "memtomem"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from memtomem <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "memtomem": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "memtomem"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from memtomem <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add memtomem uvx memtomem
```
uvx runs the command named after the package; if the README names another one, use uvx --from memtomem <command>

## When to use it
- carry notes across agent sessions
- retrieve related content by meaning
- index Markdown and code together
- give Claude Code access to local memory

## Example prompts
- Check the memtomem connection and call the `mem_status` tool.
- Search memory for deployment notes and return related entries.
- Save this decision to memory with the `ops` tag.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74559
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433

---
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