Installation¶

Requirements¶

Python 3.11 or higher
pip 23+
GEMINI_API_KEY (optional — required for LLM reasoning and embeddings)

From PyPI¶

pip install engram-mem

Installs the engram CLI and engram-mcp MCP server entry point.

In a Virtual Environment (Recommended)¶

python3 -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install engram-mem

From Source¶

git clone https://github.com/docaohieu2808/Engram-Mem.git
cd engram
pip install -e .

Docker¶

docker build -t engram:latest .
docker run -e GEMINI_API_KEY="your-key" -p 8765:8765 engram:latest

See Docker deployment for production setup with PostgreSQL and Redis.

Verify Installation¶

engram --version
engram health

Post-Install Setup¶

# Initialize config file at ~/.engram/config.yaml
engram init

# Set API key
export GEMINI_API_KEY="your-key"

# Or add to ~/.engram/config.yaml:
# llm:
#   api_key: your-key

Auto-Setup Wizard¶

engram setup

Detects and configures all installed AI agents (Claude Code, Cursor, OpenClaw, Windsurf, Cline, Aider, Zed). Use --dry-run to preview without writing, --status to check current connections.

Upgrading¶

pip install --upgrade engram-mem

Check the Changelog for breaking changes before upgrading.