Getting Started
Installation
Set up your environment and install Cognee
Set up your environment and install Cognee to start building AI memory.
Prerequisites
- Python 3.9 – 3.12
- API key for OpenAI or your chosen LLM and embedding provider
.envfile- We recommend creating a
.envfile in your project root. - Cognee supports many configuration options, and a
.envfile keeps them organized.
- We recommend creating a
- Virtual environment
- We recommend uv.
- Run
uv venv && source .venv/bin/activateto create and activate one.
- PostgreSQL database if you plan to use PostgreSQL as your relational database (requires
postgresextra)
Setup
Default Setup (with OpenAI)
Default Setup (with OpenAI)
Environment: Add your OpenAI API key to your Installation: Install Cognee with uv:What this gives you: Cognee installed with default local databases (SQLite, LanceDB, Kuzu) — no external servers required.
.env file:Free Alternative
Free Alternative
Environment: Add the following to your Note: You can get a free API key from OpenRouter.Installation: Install Cognee with fastembed support:What this gives you: A free setup using OpenRouter for LLM calls and FastEmbed for embeddings. Lightweight and cost-free, but with limited model options.
.env file: