Wen is an agentic cli assistant that helps you execute shell commands and multi-step tasks using natural language.
- AI-powered command generation
- Multi-step task execution
- Command safety analysis
- Cross-platform support
- Conversation history with context
- Clone this repository:
git clone <your-repo-url>
cd wen-cli- Install the package in development mode:
pip3 install -e .To install globally so you can run wen from anywhere:
pip3 install -e . --userVerify PATH Setup: After installation, verify that ~/.local/bin is in your PATH:
echo $PATH | grep -q "\.local/bin" && echo "PATH OK" || echo "Add ~/.local/bin to PATH"If the command shows "Add ~/.local/bin to PATH", you'll need to add it to your shell configuration file (.bashrc, .zshrc, etc.):
export PATH="$HOME/.local/bin:$PATH"pip install -e . --userVerify PATH Setup: After installation, verify that the Python Scripts directory is in your PATH:
echo %PATH% | findstr "Scripts" && echo PATH OK || echo Add Python Scripts to PATHIf the command shows "Add Python Scripts to PATH", you'll need to add the Scripts directory to your system PATH. The typical location is:
%APPDATA%\Python\Python3x\Scripts
Where 3x is your Python version (e.g., Python39, Python310, etc.).
- Install and start Ollama:
# Install Ollama (if not already installed)
# Visit https://ollama.ai for installation instructions
# Start Ollama service
ollama serve
# Pull a model (e.g., llama3.2)
ollama pull llama3.2- Test the connection:
python3 test_ollama.pyAfter installation, you can run the CLI from anywhere:
wenThe CLI will start and you can interact with it using natural language to execute commands.
- "find my documents folder"
- "setup a new python project"
- "open visual studio code"
- "list all python files in current directory"
The wen command provides an AI-powered CLI assistant. It doesn't conflict with any system commands.
- Python 3.7+
- Ollama installed and running
- Local AI model (e.g., llama3.2, codellama, etc.)
- No internet connection required (runs locally)
MIT License