Skip to main content

Build LLM Agents in a Pythonic way

Project description

PyAgentic

Python Version License: MIT Code style: black Tests

A declarative framework for building AI agents with OpenAI integration. PyAgentic provides a clean, type-safe way to create intelligent agents using Python's metaclass system and modern async patterns.

Features

  • Declarative Agent Definition - Define agents using simple class-based syntax
  • Type Safety - Full typing support with validation
  • Tool Integration - Easy function decoration for agent capabilities
  • Context Management - Sophisticated context handling with lifecycle management
  • OpenAI Integration - Native support for OpenAI's API with automatic schema generation
  • Async Support - Built-in async/await support for scalable applications
  • Extensible - Clean architecture for custom tools, context types, and validations

🚀 Quick Start

Installation

pip install pyagentic-core

Basic Example

from pyagentic import Agent, tool, ContextItem
from typing import List

class WeatherAgent(Agent):
    """An agent that provides weather information."""
    
    location: str = ContextItem(description="Current location")
    
    @tool
    def get_weather(self, city: str) -> str:
        """Get current weather for a city."""
        # Your weather API logic here
        return f"The weather in {city} is sunny and 75°F"
    
    @tool
    def get_forecast(self, city: str, days: int = 5) -> List[str]:
        """Get weather forecast for multiple days."""
        return [f"Day {i+1}: Partly cloudy" for i in range(days)]

# Create and use the agent
agent = WeatherAgent(location="San Francisco")
response = await agent.run("What's the weather like in New York?")
print(response)

Project Structure

pyagentic/
├── pyagentic/           # Core framework code
│   ├── _base/           # Internal implementation
│   └── __init__.py      # Public API
├── tests/               # Test suite
│   ├── _base/           # Core tests
│   ├── integration/     # Integration tests
│   └── performance/     # Performance tests
├── examples/            # Example agents
├── templates/           # Agent templates
├── docs/                # Documentation
├── scripts/             # Utility scripts
└── notebooks/           # Jupyter notebooks

Contributing

Contributions are welcome! Details coming soon.

Development Setup

# Install dependencies
uv sync --group dev

# Formatting
uv run black -l99 pyagentic

# Linting
uv run flake8 --max-line-length 99 pyagentic

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pyagentic_core-1.3.0.tar.gz (23.1 kB view details)

Uploaded Source

Built Distribution

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

pyagentic_core-1.3.0-py3-none-any.whl (25.9 kB view details)

Uploaded Python 3

File details

Details for the file pyagentic_core-1.3.0.tar.gz.

File metadata

  • Download URL: pyagentic_core-1.3.0.tar.gz
  • Upload date:
  • Size: 23.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for pyagentic_core-1.3.0.tar.gz
Algorithm Hash digest
SHA256 0ae8b3651140af6f1fb4f869028343755600f04ee3a74504fc14f8556989923a
MD5 fc05e385e4b6255bba4af378f46990c5
BLAKE2b-256 9697d0345fd54fa91899c44a78398754c36d01c36b1ceb6a99f4ecbed3b6a8ae

See more details on using hashes here.

Provenance

The following attestation bundles were made for pyagentic_core-1.3.0.tar.gz:

Publisher: release.yml on rmikulec/pyAgentic

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file pyagentic_core-1.3.0-py3-none-any.whl.

File metadata

  • Download URL: pyagentic_core-1.3.0-py3-none-any.whl
  • Upload date:
  • Size: 25.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for pyagentic_core-1.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 65eddef81801ebb6c56c12bef8a639fb64f67966884083ae29a8a7f4bedccee6
MD5 5f63bac42c92fbe9d57cef6b6272a2ab
BLAKE2b-256 685710b4d0ee902d6a8fd5567beb33b25760d82414d6481f8aeccfec121038c2

See more details on using hashes here.

Provenance

The following attestation bundles were made for pyagentic_core-1.3.0-py3-none-any.whl:

Publisher: release.yml on rmikulec/pyAgentic

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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