Skip to main content

A powerful 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.

Project description

PilottAI

PilottAI Framework Logo

Build Intelligent Multi-Agent Systems with Python

Scale your AI applications with orchestrated autonomous agents

PyPI version Python 3.11+ License: MIT Documentation Status Code style: black

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 task routing
    • Context-aware processing
    • Specialized agent implementations
  • 🚀 Production Ready

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

    • Semantic storage
    • Task 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.core import AgentConfig, AgentRole, LLMConfig

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

# Setup agent configuration
config = AgentConfig(
  role="processor",
  role_type=AgentRole.WORKER,
  goal="Process documents efficiently",
  description="Document processing worker",
  max_queue_size=100
)


async def main():
  # Initialize system
  pilott = Pilott(name="DocumentProcessor")

  try:
    # Start system
    await pilott.start()

    # Add agent
    agent = await pilott.add_agent(
      agent_type="processor",
      config=config,
      llm_config=llm_config
    )

    # Process document
    result = await pilott.execute_task({
      "type": "process_document",
      "file_path": "document.pdf"
    })

    print(f"Processing result: {result}")

  finally:
    await pilott.stop()


if __name__ == "__main__":
  import asyncio

  asyncio.run(main())

Specialized Agents

PilottAI includes ready-to-use specialized agents:

Documentation

Visit our documentation for:

  • Detailed guides
  • API reference
  • Examples
  • Best practices

Example Use Cases

  • 📄 Document Processing

    # Process PDF documents
    result = await pilott.execute_task({
        "type": "process_pdf",
        "file_path": "document.pdf"
    })
    
  • 🤖 AI Agents

    # Create specialized agents
    researcher = await pilott.add_agent(
        agent_type="researcher",
        config=researcher_config
    )
    
  • 🔄 Task Orchestration

    # Orchestrate complex workflows
    task_result = await manager_agent.execute_task({
        "type": "complex_workflow",
        "steps": ["extract", "analyze", "summarize"]
    })
    

Advanced Features

Memory Management

# Store and retrieve context
await agent.enhanced_memory.store_semantic(
    text="Important information",
    metadata={"type": "research"}
)

Load Balancing

# Configure load balancing
config = LoadBalancerConfig(
    check_interval=30,
    overload_threshold=0.8
)

Fault Tolerance

# Configure fault tolerance
config = FaultToleranceConfig(
    recovery_attempts=3,
    heartbeat_timeout=60
)

Project Structure

pilott/
├── core/            # Core framework components
├── agents/          # Agent implementations
├── memory/          # Memory management
├── orchestration/   # System orchestration
├── 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-0.2.7.33.tar.gz (75.9 kB view details)

Uploaded Source

Built Distribution

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

pilottai-0.2.7.33-py3-none-any.whl (108.2 kB view details)

Uploaded Python 3

File details

Details for the file pilottai-0.2.7.33.tar.gz.

File metadata

  • Download URL: pilottai-0.2.7.33.tar.gz
  • Upload date:
  • Size: 75.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.10.17 Linux/6.11.0-1014-azure

File hashes

Hashes for pilottai-0.2.7.33.tar.gz
Algorithm Hash digest
SHA256 e0f125c3e94bc6b93d5d0ac98f6c16121d2091f1447eb2a5029402edef164681
MD5 5465840c8830846e6b15bcf9a6a45b8a
BLAKE2b-256 41447f2f6781936bacbe91e0b249149cb03598ed5126d6407cabb194af7e21c6

See more details on using hashes here.

File details

Details for the file pilottai-0.2.7.33-py3-none-any.whl.

File metadata

  • Download URL: pilottai-0.2.7.33-py3-none-any.whl
  • Upload date:
  • Size: 108.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.10.17 Linux/6.11.0-1014-azure

File hashes

Hashes for pilottai-0.2.7.33-py3-none-any.whl
Algorithm Hash digest
SHA256 944881c5c80722ed9a1dc678b501d57cf2cc5684e97e9108aba38f9ad5e7394c
MD5 ea74d8f2c3a7f2ee52b554f9a445d4d0
BLAKE2b-256 14158a49a6df701e0dfd33432fd3e4272527074b68994220b67a70b1ebec20b4

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