Installation

MemoV offers multiple installation methods depending on your use case.

Prerequisites

Install uv first:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
 
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

MCP Integration (Recommended)

The fastest approach for AI agent integration - automatic updates on agent restart.

Claude Code

Run in your project root directory:

claude mcp add mem-mcp --scope project -- uvx --from git+https://github.com/memovai/memov.git mem-mcp-launcher stdio $(pwd)

Codex

Run in your project root directory:

codex mcp add mem-mcp -- uvx --from git+https://github.com/memovai/memov.git mem-mcp-launcher stdio $(pwd)

VS Code

Create .vscode/mcp.json in your project root:

{
  "servers": {
    "mem-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/memovai/memov.git",
        "mem-mcp-launcher",
        "stdio",
        "${workspaceFolder}"
      ]
    }
  }
}

Cursor

Go to Files > Preferences > Cursor Settings > MCP, then add:

{
  "mcpServers": {
    "mem-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/memovai/memov.git",
        "mem-mcp-launcher",
        "stdio",
        "${workspaceFolder}"
      ]
    }
  }
}

Claude Desktop

Create or edit ~/.config/claude/claude_desktop_config.json (on Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "memov": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/memovai/memov.git",
        "mem-mcp-launcher",
        "stdio",
        "."
      ]
    }
  }
}

RAG Mode Installation

To enable semantic search capabilities with VectorDB:

Claude Code with RAG

claude mcp add mem-mcp --scope project -- uvx --from "git+https://github.com/memovai/memov.git[rag]" mem-mcp-launcher stdio $(pwd)

VS Code / Cursor with RAG

Change the --from argument to:

"git+https://github.com/memovai/memov.git[rag]"

CLI Installation

If you want to use the mem CLI tool directly:

One-Line Install

curl -fsSL https://raw.githubusercontent.com/memovai/memov/main/install.sh | bash

Homebrew (macOS/Linux)

brew tap memovai/mem
brew install memov

APT (Debian/Ubuntu)

echo "deb [trusted=yes] https://memovai.github.io/memov/apt stable main" | sudo tee /etc/apt/sources.list.d/mem.list
sudo apt update
sudo apt install mem

From Source

git clone https://github.com/memovai/memov.git
cd memov
uv sync
uv pip install -e .
mem --help

Quick Start

Step 1: Verify Installation

mem --version
mem --help

Step 2: Initialize Your Project

cd your-project
mem init

This creates the .mem/ shadow timeline directory with:

.mem/memov.git/ - bare Git repository
.mem/branches.json - branch metadata
.mem/jump.json - jump history

Step 3: Track Files

mem track src/main.py src/utils.py

Step 4: Create Snapshots

mem snap --prompt "Added error handling" --response "Implemented try-catch blocks"

Step 5: View History

mem history
mem history --limit 10

Step 6: Launch Web UI

mem ui

Opens at http://localhost:38888

Troubleshooting

`uvx: command not found`

Install the uv package manager:

curl -LsSf https://astral.sh/uv/install.sh | sh

`mem: command not found`

Verify installation location and add to PATH:

which mem
echo $PATH

MCP Server Not Starting

Verify uv is installed
Test manual launch: mem-mcp-launcher stdio .
Check IDE logs for error messages

RAG Mode Tools Unavailable

Reinstall with RAG extras:

uvx --from "git+https://github.com/memovai/memov.git[rag]" mem-mcp-launcher

Development Setup

For contributors:

git clone https://github.com/memovai/memov.git
cd memov
uv sync
uv run pytest
pre-commit install

About Core Concepts