Skip to main content

autogen-agentai

PyPI version Python versions License Documentation Status

An extension for Microsoft AutoGen that allows running agents from agent.ai.

Overview

autogen-agentai is a Python package that serves as an extension for Microsoft's AutoGen framework, enabling the use of agent.ai agents within AutoGen. It enables developers to:

  • Agent Integration: Seamlessly integrate agent.ai agents into AutoGen workflows
  • Agent Communication: Enable communication between AutoGen agents and agent.ai agents
  • Simplified API: Provide a simple interface to configure and use agent.ai services
  • Extensibility: Extend AutoGen's capabilities with agent.ai's specialized AI agents

Key Features (Planned)

  • Agent Interoperability

    • Connect AutoGen's agent ecosystem with agent.ai's specialized agents
    • Enable cross-platform agent communication
    • Maintain agent context across different platforms
    • Synchronize agent states and knowledge
  • Configuration Management

    • Simple configuration for agent.ai API connections
    • Credential management for agent.ai services
    • Environment-based configuration options
    • Persistent configuration storage
  • Workflow Integration

    • Integrate agent.ai agents into existing AutoGen workflows
    • Create hybrid workflows combining agents from both platforms
    • Enable task delegation between different agent types
    • Support for complex multi-agent scenarios
  • Developer Tools

    • Debugging utilities for agent interactions
    • Logging and monitoring capabilities
    • Testing utilities for agent.ai integration
    • Documentation and examples

Installation

pip install autogen-agentai

Or with Poetry:

poetry add autogen-agentai

Quick Example

from autogen_agentai import AgentAIExtension
import autogen

# Initialize the extension
agent_ai_extension = AgentAIExtension(api_key="your_agentai_api_key")

# Create an AutoGen agent with agent.ai capabilities
assistant = autogen.AssistantAgent(
    name="assistant",
    llm_config={"config_key": "config_value"},
    extensions=[agent_ai_extension]
)

# Use the agent normally in AutoGen workflows
# The agent will have access to agent.ai capabilities

Documentation

For detailed documentation, visit autogen-agentai.readthedocs.io.

The documentation includes:

  • Getting Started Guide
  • API Reference
  • Examples and Tutorials
  • FAQ

Contributing

We welcome contributions! Please check out our contributing guidelines for details on:

  • Setting up your development environment
  • Running tests
  • Submitting pull requests

License

This project is licensed under the GNU General Public License v3.0 (GPLv3).

Metadata

Release files for autogen-agentai 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for autogen-agentai 0.1.0
File Size Uploaded
autogen_agentai-0.1.0.tar.gz 15.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for autogen-agentai 0.1.0
File Interpreter ABI Platform
autogen_agentai-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 31.3 kB

Release files / autogen_agentai-0.1.0.tar.gz

Download URL autogen_agentai-0.1.0.tar.gz
Size 15.4 kB
Tags Source
SHA-256 checksum
How to use checksums
b5e8cd827adc6e6eee10c7ccfe4311d31976b0f2b7ade4483818863f7e7feb54
BLAKE2b-256 checksum
How to use checksums
615588b59d3e8f03c49980a60e727be3124afa484f6dfe6471dadc122f2b031f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.0.1 CPython/3.12.8 Windows/11

Release files / autogen_agentai-0.1.0-py3-none-any.whl

Download URL autogen_agentai-0.1.0-py3-none-any.whl
Size 15.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3cb3c31e51ab154c6ac58d95b32a196375acddcc92fe3a4f48b9a818421fc0c0
BLAKE2b-256 checksum
How to use checksums
3f463a5ea7f9225b5cce7bdb6b9f54d74caed2bdcc05ef8829d3867fafda946f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.0.1 CPython/3.12.8 Windows/11

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page