Skip to main content

A multi AI agent CLI tool using Microsoft Autogen Framework

Project description

VaahAI

License Python Status

VaahAI is a multi-agent AI CLI tool built with Microsoft's Autogen Framework, designed to enhance code quality and development workflows through AI-powered code review, auditing, generation, and scaffolding capabilities.

๐ŸŒŸ Features

  • Multi-Agent Architecture: Specialized AI agents collaborate to perform complex tasks
  • Code Review: Comprehensive code review focusing on quality, style, and best practices
  • Code Audit: Security vulnerability detection, compliance checking, and architectural assessment
  • Code Generation: AI-powered code generation from natural language descriptions
  • Multiple LLM Support: OpenAI, Claude, Junie, and local models via Ollama
  • Flexible Configuration: Layered configuration system with global defaults and project-specific settings
  • Git Integration: Commit applied changes, generate meaningful commit messages, and prepare pull requests

๐Ÿš€ Getting Started

Prerequisites

  • Python 3.9+
  • Poetry (Python package manager)
  • Git
  • Docker (optional, for code execution)

Installation

# Clone the repository
git clone https://github.com/webreinvent/vaahai.git
cd vaahai

# Install dependencies with Poetry
poetry install

# Activate the Poetry virtual environment
poetry shell

Development Setup

# Install development dependencies
poetry install --with dev

# Run tests
poetry run pytest

# Format code
poetry run black vaahai
poetry run isort vaahai

# Lint code
poetry run flake8 vaahai
poetry run mypy vaahai

Configuration

# Run the configuration wizard
poetry run vaahai config init

# Or manually edit the configuration file
nano ~/.vaahai/config.toml

๐Ÿ› ๏ธ Usage

CLI Command Structure

VaahAI provides a modular CLI organized into logical command groups. The command structure follows this hierarchy:

vaahai [command_group] [command] [action] [options]

Where:

  • vaahai is the main CLI application
  • command_group is one of the logical groups (core, project, dev)
  • command is a specific command within that group
  • action is a subcommand or action for that command
  • options are additional flags and parameters

Core Commands

  • vaahai config: Configuration management
    • vaahai config init: Set up initial configuration
    • vaahai config show: Display current configuration
  • vaahai version: Display version information

Project Commands

  • vaahai review: Code review commands
    • vaahai review run: Run a code review on specified path
  • vaahai audit: Security and compliance audit commands
    • vaahai audit run: Run a security/compliance audit on specified path

Development Commands

  • vaahai dev helloworld: Test command to verify proper functioning
    • vaahai dev helloworld run: Execute the hello world test
  • vaahai dev showcase: Demonstrate Rich formatting capabilities

All commands support the --help flag for detailed usage information. For backward compatibility, direct command access (e.g., vaahai helloworld instead of vaahai dev helloworld) is also supported.

Global Options

The following options are available for all commands:

  • --verbose: Enable verbose output (can also be set with VAAHAI_VERBOSE=1)
  • --quiet: Suppress non-essential output (can also be set with VAAHAI_QUIET=1)
  • --config PATH: Specify a custom configuration file path
  • --help: Show help message and exit

Basic Commands

# Show help information
vaahai --help

# Show help for a specific command group
vaahai dev --help

# Show help for a specific command
vaahai dev helloworld --help

# Test installation and configuration
vaahai dev helloworld run
# Or using backward compatibility
vaahai helloworld run

# Review code in a file or directory
vaahai review run --path ./my_project --depth standard
# This follows the structure: vaahai [command_group] [command] [action] [options]

# Audit a project for security and compliance
vaahai audit run --path ./my_project --security --compliance owasp

# Show version information
vaahai version

# View Rich formatting showcase
vaahai dev showcase

Example Workflow

# Initialize configuration
vaahai config init

# Review a Python file
vaahai review run --path ./app.py --focus quality

# Apply suggested changes
vaahai apply --file review_suggestions.json

# Commit the changes
vaahai commit --message "Fix code quality issues in app.py"

Terminal Output

VaahAI CLI uses Rich for consistent, styled terminal output. Output behavior can be controlled with:

  • Verbose mode: Set --verbose flag or VAAHAI_VERBOSE=1 environment variable
  • Quiet mode: Set --quiet flag or VAAHAI_QUIET=1 environment variable

For more details on the Rich integration, see the Rich Integration Documentation.

๐Ÿ—๏ธ Project Structure

vaahai/
โ”œโ”€โ”€ ai_docs/         # AI-specific documentation
โ”œโ”€โ”€ ai_prompts/      # Prompt templates for AI agents
โ”œโ”€โ”€ docs/            # User and developer documentation
โ”‚   โ””โ”€โ”€ cli/         # CLI-specific documentation
โ”œโ”€โ”€ specs/           # Project specifications and requirements
โ”œโ”€โ”€ vaahai/          # Main package
โ”‚   โ”œโ”€โ”€ agents/      # Agent implementations
โ”‚   โ”œโ”€โ”€ cli/         # CLI commands and handlers
โ”‚   โ”‚   โ”œโ”€โ”€ commands/  # Command implementations
โ”‚   โ”‚   โ”‚   โ”œโ”€โ”€ core/      # Core command group
โ”‚   โ”‚   โ”‚   โ”‚   โ”œโ”€โ”€ config/    # Configuration commands
โ”‚   โ”‚   โ”‚   โ”‚   โ””โ”€โ”€ version/   # Version commands
โ”‚   โ”‚   โ”‚   โ”œโ”€โ”€ project/   # Project command group
โ”‚   โ”‚   โ”‚   โ”‚   โ”œโ”€โ”€ audit/     # Audit commands
โ”‚   โ”‚   โ”‚   โ”‚   โ””โ”€โ”€ review/    # Code review commands
โ”‚   โ”‚   โ”‚   โ”œโ”€โ”€ dev/       # Development command group
โ”‚   โ”‚   โ”‚   โ”‚   โ”œโ”€โ”€ helloworld/  # Hello world test command
โ”‚   โ”‚   โ”‚   โ”‚   โ””โ”€โ”€ showcase/   # Rich formatting showcase
โ”‚   โ”‚   โ”‚   โ””โ”€โ”€ helloworld/  # Legacy direct command (for backward compatibility)
โ”‚   โ”‚   โ”œโ”€โ”€ main.py     # CLI entry point
โ”‚   โ”‚   โ””โ”€โ”€ utils/      # CLI utilities
โ”‚   โ”‚       โ”œโ”€โ”€ console.py  # Rich formatting utilities
โ”‚   โ”‚       โ””โ”€โ”€ help.py     # Custom help formatting
โ”‚   โ”œโ”€โ”€ config/      # Configuration management
โ”‚   โ”œโ”€โ”€ llm/         # LLM provider integrations
โ”‚   โ””โ”€โ”€ utils/       # Utility functions and helpers
โ””โ”€โ”€ tests/           # Test suite
    โ””โ”€โ”€ cli/         # CLI tests

๐Ÿ“ Documentation

For more detailed documentation, please refer to:

๐Ÿค Contributing

We welcome contributions from the community! Please see our Contributing Guidelines for more details on how to get involved.

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

๐Ÿ™ Acknowledgements

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vaahai-0.2.12.tar.gz (22.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vaahai-0.2.12-py3-none-any.whl (34.5 kB view details)

Uploaded Python 3

File details

Details for the file vaahai-0.2.12.tar.gz.

File metadata

  • Download URL: vaahai-0.2.12.tar.gz
  • Upload date:
  • Size: 22.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.13.3 Darwin/24.5.0

File hashes

Hashes for vaahai-0.2.12.tar.gz
Algorithm Hash digest
SHA256 81c5b6bcba244c53019de35798b886a52f2eb405e52911b4f1e5ec67270c08d6
MD5 6d3557063c46129af8bf37f213566dc6
BLAKE2b-256 178e976ab85549def7eedd0bbdce3cf02f0d8ef2d4f7bdbd034e16f1984ceb9d

See more details on using hashes here.

File details

Details for the file vaahai-0.2.12-py3-none-any.whl.

File metadata

  • Download URL: vaahai-0.2.12-py3-none-any.whl
  • Upload date:
  • Size: 34.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.13.3 Darwin/24.5.0

File hashes

Hashes for vaahai-0.2.12-py3-none-any.whl
Algorithm Hash digest
SHA256 6d25b785f8efeef488078f252677baae85a8f3f420f91b7df715d259e55f64db
MD5 d9bbf7f4dfc1d3cdb2ba8386bec41a91
BLAKE2b-256 5e6ef52e48c9b94e0953414e0a8df579709f855fb9eda2c4328e6314aca9a4cf

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page