Skip to main content

A for building scalable multi-agent systems with built-in orchestration,LLM integration, and intelligent job processing.

Project description

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

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

pilottai-0.2.7.38.tar.gz (53.9 kB view details)

Uploaded Source

Built Distribution

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

pilottai-0.2.7.38-py3-none-any.whl (75.5 kB view details)

Uploaded Python 3

File details

Details for the file pilottai-0.2.7.38.tar.gz.

File metadata

  • Download URL: pilottai-0.2.7.38.tar.gz
  • Upload date:
  • Size: 53.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.2.1 CPython/3.10.19 Linux/6.11.0-1018-azure

File hashes

Hashes for pilottai-0.2.7.38.tar.gz
Algorithm Hash digest
SHA256 7445ccf659372be020791267923fb13930eed5c6ac718479be5c6040c1f082b1
MD5 ae3dce977665bb1cc13781974d060528
BLAKE2b-256 b368d936756331fb68a035c50bdbc360e0c1b50561f579115ab609170cb564a5

See more details on using hashes here.

File details

Details for the file pilottai-0.2.7.38-py3-none-any.whl.

File metadata

  • Download URL: pilottai-0.2.7.38-py3-none-any.whl
  • Upload date:
  • Size: 75.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.2.1 CPython/3.10.19 Linux/6.11.0-1018-azure

File hashes

Hashes for pilottai-0.2.7.38-py3-none-any.whl
Algorithm Hash digest
SHA256 ffb6c02eeb02a021e6fc9966bca95e27a2f8aa2fe5f592aa357bb1fe94e8fa20
MD5 beae540b85d03d89d5910df4c68fcf9a
BLAKE2b-256 560e7c15a74247850195ff58dd86f56d45518e98365433e18c7e2b9ff8ad92b1

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