A simple framework for creating distributed llm agent swarms
Project description
AgentKit
Overview
AgentKit is a simple framework designed for creating distributed LLM (Large Language Model) agent swarms. It provides an easy-to-use interface for managing communication and data processing among distributed agents, leveraging the power of modern libraries such as zmq for messaging, fastapi and uvicorn for web APIs, pydantic for data validation, and litellm for language model interactions.
Installation
Install AgentKit using pip:
pip install agentkit
Ensure you have Python 3.8 or higher installed to meet the compatibility requirements.
Quick Start
Look at the examples directory for a simple chat agent. More documentation will come!
Features
- Easy integration with ZeroMQ for efficient messaging.
- Web API support through FastAPI and Uvicorn.
- Robust data validation with Pydantic.
- Seamless interaction with large language models via Litellm.
- Designed for scalability and flexibility in distributed environments.
Documentation
TBD!
Contributing
We welcome contributions! If you're interested in improving AgentKit, please check out our issues section on GitHub.
License
AgentKit is licensed under the MIT License. See the LICENSE file in the source code for more information.
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.
