To set up the project locally for development, follow these steps:
- Python 3.12 or higher
- UV package manager (recommended) or pip
-
Install UV (if not already installed):
# macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh # Windows (PowerShell) powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
-
Create and activate virtual environment with dependencies:
# Create project environment and install dependencies uv sync # Activate the environment source .venv/bin/activate # macOS/Linux .venv\Scripts\activate # Windows
-
Install development dependencies:
uv sync --extra dev
-
Install optional dependencies (as needed):
# For GPU support uv sync --extra gpu # For advanced storage backends uv sync --extra storage # Install all extras uv sync --all-extras
-
Create a Virtual Environment:
python -m venv venv
-
Activate the Virtual Environment:
# Windows venv\Scripts\activate # macOS/Linux source venv/bin/activate
-
Install Dependencies:
# Install core dependencies pip install -e . # Install with development dependencies pip install -e ".[dev]" # Install with all optional dependencies pip install -e ".[dev,gpu,storage]"
# Run tests to verify everything is working
pytest
# Check code formatting
black --check src tests
# Run type checking
mypy srcThis setup supports:
- Windows (including WSL)
- macOS
- Linux
- Dev Containers for isolated development
Tyler Zervas
- GitHub: tzervas
- X: @vec_wt_tech
- Email: tz-dev@vectorweight.com
A dynamic memory learning layer for AI agents, designed for DevOps automation and homelab AI R&D.
- Persistent Learning: Enables AI agents to retain and build upon operational knowledge across sessions.
- Context-Aware Adaptation: Dynamically adjusts responses based on accumulated experience patterns.
- Cluster Focus: Designed for seamless deployment in containerized environments with proper monitoring and scaling.
- DevOps Integration: Provides native integration with existing CI/CD pipelines and infrastructure tools.