MCP ExplorerExplorer

Minion Manus

@femtoon a year ago
3 MIT
FreeCommunity
AI Systems
minion implementation for manus and mcp

Overview

What is Minion Manus

Minion-Manus is a toolkit designed for implementing and managing tools for Large Language Model (LLM) agents, providing a standardized framework for tool creation and integration.

Use cases

Use cases include creating calculators for mathematical expressions, developing chatbots that require specific tools for user queries, and building asynchronous tools for improved performance in applications.

How to use

To use Minion-Manus, install it via pip and create tools by defining classes that inherit from the Tool or AsyncTool base classes, specifying inputs, outputs, and the execution logic.

Key features

Key features include a simple class-based API, support for synchronous and asynchronous execution, schema validation for inputs and outputs, adapters for integration with other frameworks, and comprehensive type hints and documentation.

Where to use

Minion-Manus can be used in various fields that require LLM integration, such as natural language processing, chatbots, automated customer support, and any application needing tool management for LLMs.

Content

Minion Manus

A simplified wrapper for smolagents that makes it easy to create and run AI agents.

Installation

pip install minion-manus

Usage

Here’s a simple example of how to use Minion Manus:

from minion_manus import MinionAgent, AgentConfig

# Configure the agent
agent_config = AgentConfig(
    model_id="gpt-4",  # or your preferred model
    name="Research Assistant",
    description="A helpful research assistant",
    instructions="You are a helpful research assistant that can search the web and visit webpages.",
    model_args={"api_key_var": "OPENAI_API_KEY"}  # Will use OPENAI_API_KEY from environment
)

# Create and run the agent
agent = MinionAgent(agent_config)

# Run the agent with a question
result = agent.run("What are the latest developments in AI?")
print("Agent's response:", result)

Configuration

The AgentConfig class accepts the following parameters:

  • model_id: The ID of the model to use (e.g., “gpt-4”)
  • name: Name of the agent (default: “Minion”)
  • description: Optional description of the agent
  • instructions: Optional system instructions for the agent
  • tools: List of tools the agent can use
  • model_args: Optional dictionary of model-specific arguments
  • agent_args: Optional dictionary of agent-specific arguments

Environment Variables

Make sure to set up your environment variables in a .env file:

OPENAI_API_KEY=your_api_key_here

Development

To set up for development:

# Clone the repository
git clone https://github.com/yourusername/minion-manus.git
cd minion-manus

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

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

License

MIT License

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers