Development Setup

This guide walks you through setting up a local development environment for working on the Memori codebase. Follow these steps to clone the repository, install dependencies, and run the test suite.

Want a zero-setup option? The Memori Cloud at app.memorilabs.ai.

Prerequisites

Before you begin, make sure you have the following installed on your system:

Python 3.10 or higher — Memori requires Python 3.10+. Check your version with python --version.
git — For cloning the repository and managing branches.
pip — Python's package manager (usually included with Python).

Clone the Repository

Start by forking the repository on GitHub, then clone your fork locally:

git clone https://github.com/YOUR_USERNAME/Memori.git
cd Memori

If you plan to submit a pull request, make sure to keep your fork synced with the upstream repository:

git remote add upstream https://github.com/MemoriLabs/Memori.git
git fetch upstream

Install Dependencies

It is recommended to use a virtual environment to avoid conflicts with other Python projects:

Virtual Environment Setup

python -m venv .venv
source .venv/bin/activate    # macOS/Linux
# .venv\Scripts\activate     # Windows

Once your virtual environment is active, install Memori with development dependencies:

pip install -e ".[dev]"

This installs Memori in editable mode (-e) so that changes you make to the source code are immediately reflected without reinstalling. The [dev] extra includes testing and linting tools.

If the project uses a requirements-dev.txt file instead, install with:

pip install -e .
pip install -r requirements-dev.txt

Running Tests

Memori uses pytest for its test suite. Run all tests from the project root:

pytest

To run tests with verbose output:

pytest -v

To run a specific test file or test function:

# Run all tests in a specific file
pytest tests/test_openai.py

# Run a specific test function
pytest tests/test_openai.py::test_sync_completion

To run tests with coverage reporting:

pytest --cov=memori --cov-report=term-missing

Local Development Workflow

Here is a typical workflow for making changes to Memori:

Create a branch for your feature or fix:
```
git checkout -b feat/my-new-feature
```
Make your changes — Edit the source code in the memori/ directory.
Write tests — Add or update tests in the tests/ directory to cover your changes.
Run the tests to make sure nothing is broken:
```
pytest
```
Check code style — The project uses Ruff for linting and formatting:
```
# Lint
ruff check .

# Format
ruff format --check .
```

Commit your changes with a descriptive message:

git add .
git commit -m "feat: add support for Redis storage backend"

Push to your fork and open a pull request:
```
git push origin feat/my-new-feature
```

Project Structure

Here is a high-level overview of the Memori repository structure:

Directory	Purpose
`memori/`	Core library source code
`tests/`	Test suite (pytest)
`docs/`	Documentation source files
`examples/`	Example scripts and usage demos

The core integration logic for each LLM provider typically lives in separate modules within the memori/ directory. When adding support for a new provider, look at existing integrations (such as OpenAI or Anthropic) as templates.