Installation¶
Python¶
Basic Installation¶
With Optional Backends¶
# Local development (SQLite + FAISS + local embeddings)
pip install alma-memory[local]
# Production databases
pip install alma-memory[postgres] # PostgreSQL + pgvector
pip install alma-memory[qdrant] # Qdrant vector database
pip install alma-memory[pinecone] # Pinecone vector database
pip install alma-memory[chroma] # ChromaDB
# Enterprise
pip install alma-memory[azure] # Azure Cosmos DB + Azure OpenAI
# Everything
pip install alma-memory[all]
Requirements¶
- Python 3.10 or higher
- pip 21.0 or higher
TypeScript / JavaScript¶
Via GitHub Packages¶
# Configure npm for the scope (one-time)
echo "@rbkunnela:registry=https://npm.pkg.github.com" >> ~/.npmrc
# Install
npm install @rbkunnela/alma-memory
Or with yarn:
Requirements¶
- Node.js 18.0.0 or higher (for native
fetchsupport) - A running ALMA MCP server for the TypeScript SDK to connect to
Verify Installation¶
Next Steps¶
- Quick Start Guide - Build your first memory-powered agent
- Configuration - Set up storage backends and agent scopes