Genpilot

🚀 GenPilot

GenPilot simplifies the creation, development, and management of single and multi - agent systems by integrating generative AI. Adhering to the Model Context Protocol (MCP), it achieves seamless compatibility with various MCP servers, enabling developers and end - users to efficiently transform concepts and prototypes into mature solutions. All of this is accomplished through intuitive and user - friendly terminal and web interfaces.

🚀 Quick Start

✨ Features

• MCP Agents: Leverage servers provided by the MCP ecosystem to empower agents with stronger capabilities, enabling them to connect and interact in a richer and more scalable environment.
• Multi - Agent Systems: Seamlessly scale from single - task to complex multi - agent workflows, inspired by [routines and handoffs](https://cookbook.openai.com/examples/orchestrating_agents#executing - routines).
• User - Friendly Interface: Provide an intuitive interface to support prototyping and rapid implementation, whether through web interfaces (Streamlit, Chainlit) or the terminal. It's easy to get started without extra effort.
• Enhanced Autonomy: GenPilot can register and call tools internally, reducing dependence on external agents and minimizing unnecessary interactions.
• Controlled Operations: GenPilot's operations are managed by three permission levels:
  • auto: Request permission only for system or environment modification operations.
  • always: Request permission for all operations.
  • none: Do not request any permission.
• Structured Prompts and Automatic Optimization: Improve agents' understanding ability through a structured prompt mechanism, enabling them to parse user intentions more accurately. Additionally, GenPilot supports an automated optimization function to help users efficiently adjust model parameters.
• Modular Design: Components are loosely coupled for easy maintenance and expansion.
• Multi - Language Support: Built - in multi - language processing capabilities to meet global requirements.
• Dynamic Loading Mechanism: Support real - time loading of new tools and services to maintain system flexibility.
• Customizable Interface: Provide a highly customizable user interface to meet personalized needs.

📦 Installation

Requires Python 3.10 or higher.

pip install genpilot

💻 Usage Examples

Basic Usage

The client is initialized using litellm. For detailed information about different providers, please refer to the guide.

import genpilot as gp
import asyncio

# 1. User Interface: Supports the Streamlit interface, allowing all agents to share the same chat interface.
terminal = gp.TerminalChat()

# 2. Define a tool for searching and summarizing information
def search_and_summarize(query):
    """Search for information on the Internet and return a summary."""
    return f"Here is a summary about '{query}': [Summary content]."

# 3. Define an agent responsible for summarizing search results
info_explorer = gp.Agent(
    name="Info Explorer",
    model_config={
        "name": "groq/llama-3.3-70b-versatile",
    },
    chat=terminal,
    tools=[search_and_summarize],
    system=(
        "Your role is to search the Internet and summarize relevant information for a given query."
        "Use the search tool to find and condense the information required by the user, ensuring it is clear and relevant."
    ),
)

# 4. Use the agent to handle a query
response = asyncio.run(info_explorer("What are the latest developments in AI currently?"))
print(response)

Advanced Usage

Example 1: Basic Information Query

response = asyncio.run(info_explorer("What's the weather like in Beijing today?"))
print(response)

Output:

Here is a summary about 'What's the weather like in Beijing today': [According to real - time data, the temperature range in Beijing today is between -5°C and 3°C, and the sky condition is mainly cloudy.]

Example 2: Complex Problem Solving

response = asyncio.run(info_explorer("How to optimize the response time of a company's online customer service?"))
print(response)

Output:

To optimize the response time of a company's online customer service, the following measures are recommended:
1. Implement an intelligent routing system to automatically assign customer requests to the most suitable customer service representatives.
2. Configure real - time monitoring tools to promptly detect and handle latency issues.
3. Conduct regular staff training to improve service efficiency and quality.

As shown in the above examples, GenPilot agents can effectively understand and solve user needs and provide structured feedback. This feature will greatly enhance the user experience and work efficiency in practical applications.

We hope the above content helps you better understand the features and advantages of GenPilot. For further information, please visit its official website or refer to the relevant documentation.