Skip to content

pilottai/pilottai

PilottAI

PilottAI Framework Logo

Build Intelligent Multi-Agent Systems with Python

Scale your AI applications with orchestrated autonomous agents

PyPI version Python 3.10+ License: MIT Documentation Status Code style: black

⭐ Star us | 🧠 Agentic AI | 🧰 Multi-Agent Framework | ⚡ Build Anything with LLMs

pip install pilottai

Overview

PilottAI is a Python framework for building autonomous multi-agent systems with advanced orchestration capabilities. It provides enterprise-ready features for building scalable AI applications.

Key Features

  • 🤖 Hierarchical Agent System

    • Manager and worker agent hierarchies
    • Intelligent job routing
    • Context-aware processing
    • Specialized agent implementations
  • 🚀 Production Ready

    • Asynchronous processing
    • Dynamic scaling
    • Load balancing
    • Fault tolerance
    • Comprehensive logging
  • 🧠 Advanced Memory

    • Semantic storage
    • Job history tracking
    • Context preservation
    • Knowledge retrieval
  • 🔌 Integrations

    • Multiple LLM providers (OpenAI, Anthropic, Google)
    • Document processing
    • WebSocket support
    • Custom tool integration

Installation

pip install pilottai

Quick Start

from pilottai import Pilott
from pilottai.tools import Tool
from pilottai.agent import Agent
from duckduckgo_search import DDGS
from pilottai.core import AgentConfig, AgentType, LLMConfig

# Configure LLM
llm_config = LLMConfig(
  model_name="gpt-4",
  provider="openai",
  api_key="your-api-key"
)

def duckduckgo_search(query, max_results=5):
    """Perform a DuckDuckGo search and return top results."""
    with DDGS() as ddgs:
        results = ddgs.text(query, max_results=max_results)
        return [{"title": r["title"], "link": r["href"], "snippet": r["body"]} for r in results]

search_tool = Tool(
                name="duckduckgo_search",
                description="Search DuckDuckGo for relevant information on any topic",
                function=duckduckgo_search,
                parameters={
                    "query": "str - The search query",
                    "num_results": "int - Number of results to return (max 10)"
                }
            )

query = "Type your question here"

search_agent = Agent(
                title="search_specialist",
                goal="Find the most relevant and credible sources for any given query",
                description="An expert at formulating search queries and identifying high-quality, relevant sources",
                jobs=f"Search for information about: '{query}' using DuckDuckGo and rank the results by relevance and credibility. Return the top 5 most relevant sources.",
                tools=[search_tool],
                llm_config=llm_config
              )


synthesis_results = await Pilott(agents=[search_agent], name="Search Bot", llm_config=llm_config).serve()

Specialized Agents

PilottAI includes ready-to-use specialized agents:

📚 Documentation

👉 Read the full documentation here

The documentation includes:

  • Detailed guides
  • API reference
  • Best practices

Project Structure

pilott/
├── core/            # Core framework components
├── agents/          # Agent implementations
├── memory/          # Memory management
├── tools/           # Tool integrations
└── utils/           # Utility functions

Contributing

We welcome contributions! See our Contributing Guide for details on:

  • Development setup
  • Coding standards
  • Pull request process

Support

License

PilottAI is MIT licensed. See LICENSE for details.


Built with ❤️ by the PilottAI Team

About

Python framework for building scalable multi-agent systems with built-in orchestration, LLM integration, and intelligent task processing. Features dynamic scaling, fault tolerance, and advanced load balancing.

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages