LiteMultiAgent
Please note that the LiteMultiAgent repository is in development mode. We have open-sourced the repository to foster collaboration between contributors.
repo owner: Danni (Danqing) Zhang (danqing.zhang.personal@gmail.com)
main contributors: Balaji Rama (balajirw10@gmail.com), Shiying He (sy.he0303@gmail.com) and Jingyi Ni (jingyi.ni.personal@gmail.com)
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.
📰 News
- [2024-10-02] Major framework refactoring introduces new agent classes: Function Calling, React, and High-Level Planning. It also defines Atomic agents using function tools and Composite agents employing both functions and sub-agents, enhancing overall system flexibility.
- [2024-10-01] Integrate LiteWebAgent into LiteMultiAgent repo to enable hierarchical multi-agent framework with web browsing capacities.
- [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'
python3 -m venv venv
. venv/bin/activate
pip install -e .
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.
python examples/atomic/IOAgent.py
python examples/composite/MasterAgent.py
🚀 2. Contributions
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},
author={Zhang, Danqing and Rama, Balaji and He, Shiying and Ni, Jingyi},
journal={https://danqingz.github.io/blog/2024/07/27/LiteMultiAgent.html},
year={2024}
}
Metadata
Release files for litemultiagent 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| litemultiagent-0.1.5.tar.gz | 5.0 kB | Without provenance | Details for litemultiagent-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| litemultiagent-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for litemultiagent-0.1.5-py3-none-any.whl |
Total release size: 10.9 kB
Release files / litemultiagent-0.1.5.tar.gz
| Download URL | litemultiagent-0.1.5.tar.gz |
|---|---|
| Size | 5.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
72795ba42adf7dfaf3fbc4021f4cee036803dbf88778ac0479d1a9431d7814b8
|
|
BLAKE2b-256 checksum How to use checksums |
25dff000b0c8b273c2de020c4531eabf957b8871d752d1338b5e38e72197b9ec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/5.1.1 CPython/3.12.7
|
Release files / litemultiagent-0.1.5-py3-none-any.whl
| Download URL | litemultiagent-0.1.5-py3-none-any.whl |
|---|---|
| Size | 6.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
860965d6ec3d8282976214e7d0ad2b67bf7ab2fc425dabab41742086be0aa45d
|
|
BLAKE2b-256 checksum How to use checksums |
97fbfd28cefcc3ceeccc87c66f009998f037dd60a83deb4860063c1d8ede0b3c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/5.1.1 CPython/3.12.7
|
Security for litemultiagent 0.1.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.