https://github.com/pilottai/pilottai
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.
https://github.com/pilottai/pilottai
agent-framework agents ai generative-ai llm multi-agent-systems opensource pilottai pydantic python
Last synced: 8 months ago
JSON representation
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.
- Host: GitHub
- URL: https://github.com/pilottai/pilottai
- Owner: pilottai
- License: mit
- Created: 2025-01-19T19:05:40.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-08-19T14:43:58.000Z (10 months ago)
- Last Synced: 2025-09-15T14:30:47.354Z (9 months ago)
- Topics: agent-framework, agents, ai, generative-ai, llm, multi-agent-systems, opensource, pilottai, pydantic, python
- Language: Python
- Homepage: https://pilottai.com
- Size: 3.4 MB
- Stars: 235
- Watchers: 8
- Forks: 15
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
- Security: .github/security.md
Awesome Lists containing this project
README
PilottAI
Build Intelligent Multi-Agent Systems with Python
Scale your AI applications with orchestrated autonomous agents
[](https://badge.fury.io/py/pilottai)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](https://docs.pilottai.com)
[](https://github.com/psf/black)
[](https://github.com/pygig/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
```bash
pip install pilottai
```
## Quick Start
```python
from pilottai import Pilott
from pilottai.core import AgentConfig, AgentType, LLMConfig
# Configure LLM
llm_config = LLMConfig(
model_name="gpt-4",
provider="openai",
api_key="your-api-key"
)
# Setup agent configuration
config = AgentConfig(
title="processor",
agent_type=AgentType.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_job({
"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:
- 🎫 [Customer Service Agent](pilottai/examples/customer_service.py): Ticket and support management
- 📄 [Document Processing Agent](pilottai/examples/document_processing.py): Document analysis and extraction
- 📧 [Email Agent](pilottai/examples/email_service.py): Email handling and template management
- 🧠 [Learning Agent](pilottai/examples/teacher.py): Knowledge acquisition and pattern recognition
- 📢 [Marketing Expert Agent](pilottai/examples/marketing_expert.py): Campaign management and content creation
- 📊 [Research Analyst Agent](pilottai/examples/research_analyst.py): Data analysis and research synthesis
- 💼 [Sales Representative Agent](pilottai/examples/sales_rep.py): Lead management and proposals
- 🌐 [Social Media Agent](pilottai/examples/social_media_manager.py): Content scheduling and engagement
- 🔍 [Web Search Agent](pilottai/examples/web_search.py): Search operations and analysis
## 📚 Documentation
👉 **[Read the full documentation here](https://docs.pilottai.com)**
The documentation includes:
- Detailed guides
- API reference
- Examples
- Best practices
## Example Use Cases
- 📄 **Document Processing**
```python
# Process PDF documents
result = await pilott.execute_job({
"type": "process_pdf",
"file_path": "document.pdf"
})
```
- 🤖 **AI Agents**
```python
# Create specialized agents
researcher = await pilott.add_agent(
agent_type="researcher",
config=researcher_config
)
```
- 🔄 **Job Orchestration**
```python
# Orchestrate complex workflows
job_result = await manager_agent.execute_job({
"type": "complex_workflow",
"steps": ["extract", "analyze", "summarize"]
})
```
## Advanced Features
### Memory Management
```python
# Store and retrieve context
await agent.enhanced_memory.store_semantic(
text="Important information",
metadata={"type": "research"}
)
```
### Load Balancing
```python
# Configure load balancing
config = LoadBalancerConfig(
check_interval=30,
overload_threshold=0.8
)
```
### Fault Tolerance
```python
# 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](.github/CONTRIBUTING.md) for details on:
- Development setup
- Coding standards
- Pull request process
## Support
- 📚 [Documentation](https://docs.pilottai.com)
- 💬 [Discord](https://discord.gg/pilottai)
- 📝 [GitHub Issues](https://github.com/pilottai/pilott/issues)
- 📧 [Email Support](mailto:support@pilottai.com)
## License
PilottAI is MIT licensed. See [LICENSE](LICENSE) for details.
---
Built with ❤️ by the PilottAI Team