getting-started.md

Getting Started

Memory Engine is permanent memory for AI agents. Store, search, and organize knowledge that persists across conversations.

Install

curl -fsSL https://install.memory.build | sh && me mcp install

This installs the me binary to ~/.local/bin. Make sure it's on your PATH.

Sign up and log in

me login

This starts an OAuth flow via GitHub -- authorize in your browser and the CLI stores your session.

Store your first memory

me memory create "PostgreSQL 18 supports native UUIDv7 generation." \
  --tree notes.postgres \
  --meta '{"topic": "database"}'

Search

# Semantic search (by meaning)
me memory search "UUID generation in Postgres"

# Keyword search
me memory search --fulltext "UUIDv7"

# Hybrid (both combined)
me memory search --semantic "UUID generation" --fulltext "PostgreSQL 18"

Browse the tree

me memory tree

Connect to AI tools

Register Memory Engine as an MCP server with your AI coding tools:

me mcp install

This auto-detects Claude Code, Gemini CLI, Codex CLI, and OpenCode on your PATH and registers me with each one. After installation, your AI agent has access to 10 memory tools -- create, search, get, update, delete, and more.

See MCP Integration for details.

What's next

• Core Concepts -- understand memories, tree paths, metadata, search modes
• Access Control -- users, roles, grants, and ownership
• Memory Packs -- install pre-built knowledge collections
• MCP Integration -- how AI agents use Memory Engine
• CLI Reference -- full command reference
• MCP Tool Reference -- full MCP tool reference