What is Mangaba Ai

Mangaba.AI is a framework designed to create and manage teams of autonomous AI agents that collaborate to solve complex tasks. It allows for the creation of specialized agents, facilitates communication between them, and supports the execution of sequential tasks with shared context.

Use cases

Use cases for Mangaba.AI include scenarios where a researcher gathers information, an analyst processes the data, and a writer generates reports, all working in tandem to achieve a common goal.

How to use

To get started with Mangaba.AI, first obtain your API key from Google AI Studio. Then, install the necessary dependencies using pip, and finally, run your first example script to see multiple agents working together.

Key features

Key features of Mangaba.AI include the ability to create autonomous agents with specific roles, A2A communication for collaboration, MCP context management for maintaining continuity between tasks, support for multiple AI models (Gemini, OpenAI, Anthropic), and integrations with platforms like Slack, GitHub, Jira, and Discord.

Where to use

Mangaba.AI can be utilized in various fields such as research, data analysis, content generation, and project management, where complex tasks require collaboration among multiple AI agents.

Mangaba.AI

Framework for developing intelligent autonomous agents.

Project Structure

mangaba_ai/
├── .github/                    # GitHub configurations
├── docs/                       # Documentation
│   ├── api/                   # API documentation
│   ├── guides/                # Usage guides
│   └── examples/              # Documented examples
├── src/                       # Source code
│   ├── core/                  # Framework core
│   │   ├── agents/           # Agent implementations
│   │   ├── models/           # Data models
│   │   ├── protocols/        # Protocols and interfaces
│   │   └── tools/            # Base tools
│   ├── integrations/         # Optional integrations
│   └── utils/                # General utilities
├── tests/                     # Tests
│   ├── unit/                 # Unit tests
│   ├── integration/          # Integration tests
│   └── e2e/                  # End-to-end tests
├── examples/                  # Examples
│   ├── basic/                # Basic examples
│   └── advanced/             # Advanced examples
└── scripts/                   # Utility scripts

Installation

1. Clone the repository:

git clone https://github.com/your-username/mangaba_ai.git
cd mangaba_ai

2. Create and activate a virtual environment:

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

3. Install dependencies:

pip install -r requirements.txt

4. Configure environment variables:

cp .env.example .env
# Edit the .env file with your settings

Basic Usage

from mangaba_ai import MangabaAI

# Initialize the framework
ai = MangabaAI()

# Create an agent
agent = ai.create_agent(
    name="my_agent",
    role="Analyst",
    goal="Analyze data and generate insights"
)

# Create a task
task = ai.create_task(
    description="Analyze sales data",
    agent=agent
)

# Execute the task
result = await ai.execute([task])

Documentation

• Quick Start Guide
• API Documentation
• Examples

Development

1. Install development dependencies:

pip install -r requirements-dev.txt

2. Configure pre-commit hooks:

pre-commit install

3. Run tests:

pytest

Contributing

1. Fork the project
2. Create your feature branch (git checkout -b feature/new-feature)
3. Commit your changes (git commit -am 'Add new feature')
4. Push to the branch (git push origin feature/new-feature)
5. Create a Pull Request

License

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