AI Agentsagentagent-based-frameworkagentic-agiagentic-frameworkagentic-workflow
Installation
# Add to your Claude Code skills
git clone https://github.com/PathOnAIOrg/LiteMultiAgent
README.md
LiteMultiAgent
In our exploration of building multi-agent systems, we have investigated AutoGen, CrewAI, LangGraph, and MetaGPT, but failed to find a multi-agent system that intuitively makes multi-agent systems more efficient. We have found that most examples provided by these frameworks could be accomplished with just one agent. We reimplemented the multi-agent examples using only one agent with a set of self-defined tools. However, we then realized that this system is not scalable when we have more and more tools. But if we can categorize the agents with different sets of tools into categories, then we are building a hierarchy of agents, where we could accomplish more types of tasks. At the same time, because of this design, the execution of sub-agents is naturally parallelized by parallel function calling, since agents use sub-agents as tools.
Disclaimer: Please note that LiteMultiAgent is not affiliated with any for-profit company. This is a collaborative project from PathOnAI.org, an open-source AI research community, where Danqing Zhang (danqing.zhang.personal@gmail.com) is the main contributor. If anyone claims LiteMultiAgent is affiliated with any for-profit company, please contact Danqing Zhang (danqing.zhang.personal@gmail.com) for verification.
📰 News
[2024-10-29] Generate and register tools for function calling at runtime: example
[2024-10-02] Major framework refactoring introduces new agent classes: Function Calling, React, and High-Level Planning. It also defines Atomic agents using functions as tools and Composite agents employing both functions and sub-agents as tools, enhancing overall system flexibility.
[2024-10-01] Integrate LiteWebAgent into LiteMultiAgent repo to enable hierarchical multi-agent framework with web browsing capacities.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
151,568
ai-agent
ai-agents
autonomous-agent
autonomous-agents
gpt
llm
llm-agent
llm-agents
llm-framework
multi-agent
multi-agent-systems
web-agent
[2024-09-28] LiteMultiAgent was refactored into a flexible hierarchical multi-agent framework, adding ToolRegistry, AgentFactory, and AgentManager, allowing users to register their own base tools and create custom agent hierarchies.
[2024-08-06] the initial version of LiteMultiAgent was released, showcasing a hierarchical multi-agent system capable of accomplishing a wide range of tasks.
✈️ 1. Getting Started
(1) Installation
From PyPI: https://pypi.org/project/litemultiagent/
pip install litemultiagent
Set up locally
First set up virtual environment, and allow your code to be able to see 'litemultiagent'
Then please create a .env file, and update your API keys:
cp .env.example .env
(Optional) Supabase Database Set Up
If you want to save log to Supabase. Set up a Supabase project and retrieve the database URL from: https://supabase.com/dashboard/project/[PROJECT_NAME]/settings/database.
The DATABASE_URL follows: postgresql://:@:/. You can get this from Project Settings -> Database -> Connection string.
Save this URL in the .env file as SUPABASE_DATABASE_URL. Then, run:
python supabase_db_setup.py
This will create the multiagent table in your database
(2) Quickstart
After setting up your API keys, you can explore the examples in the examples folder:
The atomic agent uses functions as its tools.
The composite agent can utilize sub-agents as tools while also leveraging functions.
For how to contribute, see CONTRIBUTE. If you would like to contribute to the codebase, issues or pull requests are always welcome!
📄 3. Citing LiteMultiAgent
@misc{zhang2024litemultiagent,
title={LiteMultiAgent: The Library for LLM-based multi-agent applications},
author={Zhang, Danqing and Rama, Balaji and He, Shiying and Ni, Jingyi},
year = 2024,
publisher = {Zenodo},
doi = {10.5281/zenodo.15500241},
url = {https://doi.org/10.5281/zenodo.15500241}
}
