Skip to main content

A reference implementation of the Moya AI framework.

Project description

MOYA - Meta Orchestration framework for Your Agents

MOYA is a reference implementation of our research paper titled "Engineering LLM Powered Multi-agent Framework for Autonomous CloudOps". The framework provides a flexible and extensible architecture for creating, managing, and orchestrating multiple AI agents to handle various tasks autonomously.

Preprint of the paper can be accessed at arXiv.

Features

  • Agent Management: Create, register, and manage multiple AI agents.
  • Orchestration: Orchestrate conversations and tasks across multiple agents.
  • Memory Tools: Integrate memory tools to maintain conversation context and history.
  • Streaming Responses: Support for streaming responses from agents.
  • Extensibility: Easily extend the framework with new agents, tools, and orchestrators.

Getting Started

Prerequisites

  • Python 3.10+
  • Install required dependencies:
    pip install .
    

Quick Start Examples

OpenAI Agent

Interactive chat example using OpenAI agent with conversation memory.

# filepath: /Users/kannan/src/github/moya/examples/quick_start_openai.py

python -m examples.quick_start_openai

Bedrock Agent

Interactive chat example using BedrockAgent with conversation memory.

# filepath: /Users/kannan/src/github/moya/examples/quick_start_bedrock.py

AWS_PROFILE=my_profile_name python -m examples.quick_start_bedrock

Multi-Agent Orchestration

Example demonstrating multi-agent orchestration with language and task classification.

# filepath: /Users/kannan/src/github/moya/examples/quick_start_multiagent.py

python -m examples.quick_start_multiagent

Dynamic Agent Creation

Example demonstrating dynamic agent creation and registration during runtime. moya

# filepath: /Users/kannan/src/github/moya/examples/dynamic_agents.py


python -m examples.dynamic_agents

Directory Structure

moya/
├── agents/                # Agent implementations (OpenAI, Bedrock, Ollama, Remote)
├── classifiers/           # Classifier implementations for agent selection
├── memory/                # Memory repository implementations
├── orchestrators/         # Orchestrator implementations for managing agent interactions
├── registry/              # Agent registry and repository implementations
├── tools/                 # Tool implementations (e.g., MemoryTool)
├── examples/              # Example scripts demonstrating various use cases
└── README.md              # This README file

Contributing

We welcome contributions to the MOYA framework. Please follow these steps to contribute:

  1. Fork the repository.
  2. Create a new branch for your feature or bugfix.
  3. Make your changes and commit them with descriptive messages.
  4. Push your changes to your fork.
  5. Create a pull request to the main repository.

License

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

Contact

For any questions or inquiries, please contact the authors of the research paper or open an issue on the GitHub repository.

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

mcmoya-0.1.1.tar.gz (18.9 kB view details)

Uploaded Source

Built Distribution

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

mcmoya-0.1.1-py3-none-any.whl (28.8 kB view details)

Uploaded Python 3

File details

Details for the file mcmoya-0.1.1.tar.gz.

File metadata

  • Download URL: mcmoya-0.1.1.tar.gz
  • Upload date:
  • Size: 18.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.0

File hashes

Hashes for mcmoya-0.1.1.tar.gz
Algorithm Hash digest
SHA256 3729c526efeb3800ec6dc1d321bc21a855cae9b33f65da0382b15acac4352d19
MD5 461cc8967d4d58a4edc0e9a0627a0dcd
BLAKE2b-256 c26f646d155fbbc19fa2320c5495872b4276a17f65fcbe528aabcadc596f7a79

See more details on using hashes here.

File details

Details for the file mcmoya-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: mcmoya-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 28.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.0

File hashes

Hashes for mcmoya-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0cfddc48c455ff6b5561e26365c877adfc3f5b7d4bbaa7035dacf02e80a34f48
MD5 b3923ef452a77ad11705a51601fc7ee0
BLAKE2b-256 f945a8d9b1abdfc77580172d16a2c2227fcab741a53b1f3d74eb0b095cb8e2de

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