AssistantAGI

A Python package for an AI assistant with AGI capabilities.

Installation

# Create a virtual environment
python -m venv venv

# Activate the virtual environment
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install the package and dependencies
pip install -e .

Usage

As a Module

from assistant_agi import process

# Process a query
response = process("What's 25 + 17?")
print(response)

# Access the agent directly
from assistant_agi import agent
response = agent.chat("What's the weather like today?")

Command Line Interface

You can run the assistant directly from the command line:

# Using the console script
assistant-agi

# Or using the Python module
python -m assistant_agi.assistant

REST API

You can run the assistant as a REST API server:

# Install with API dependencies
pip install -e ".[api]"

# Run the API server
assistant-agi-api

# Or using the Python module
python -m assistant_agi.api

Node.js Integration

You can call the assistant from Node.js using the provided client:

const AssistantAGI = require('./node_client');

// Create an instance of the AssistantAGI client
const assistant = new AssistantAGI();

// Process a query
assistant.process("What's 25 + 17?")
  .then(response => console.log(response))
  .catch(error => console.error(error));

// Chat with the agent
assistant.chat("What's the weather like today?")
  .then(response => console.log(response))
  .catch(error => console.error(error));

Features

• Intelligent query processing with strands-agents
• Calendar tracking, restaurant reservations, and concert ticket booking
• Interactive command-line interface with visual feedback
• Extensible architecture for adding custom tools
• Easy integration with other systems

Visual Interface

The assistant includes a sophisticated visual interface with:

• Animated spinners showing processing status
• Color-coded messages for different states
• Progress tracking for tool operations
• Graceful error handling

Development

# Create a development environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

VSCode Integration

For the best development experience with VSCode:

1. Open the project in VSCode
2. Select the Python interpreter from the virtual environment:
   • Press Cmd+Shift+P (or Ctrl+Shift+P on Windows)
   • Type "Python: Select Interpreter"
   • Choose the interpreter from the venv folder

License

MIT