Home

Awesome

Gentopia

License: MIT PyPI Read the Docs Static Badge Static Badge Open Issues Dependency Status

Twitter Follow YouTube Channel Subscribers GitHub star chart

Gentopia is a lightweight and extensible framework for LLM-driven Agents and ALM research. It provides essential components to build, test and evaluate agents. At its core, Gentopia aims to assemble an agent with a single config, thus minimizing your effort in building, tuning, and sharing agents.

<img width="1140" alt="image" src="https://github.com/Gentopia-AI/Gentopia/assets/65674752/8cb8ec87-6e50-44d5-aedc-c4994e9a8aa2">

Gentopia maintains an agent platform GentPool to share specialized agents, where your agent interacts with other agents by cloning, hierarchical plug-in, or sharing environment. We provide a unique agent benchmark for holistic evaluation.

Motivation ๐Ÿง 

Agent practitioners start to realize the difficulty in tuning a "well-rounded" agent with tons of tools or instructions in a single layer. Recent studies like TinyStories, Specializing Reasoning, Let's Verify SbS, ReWOO, etc. also point us towards an intuitive yet undervalued direction ๐Ÿ‘‰

An LLM is more capable if you create a context/distribution shift specialized to some target tasks.

Sadly, there is no silver bullet for agent specialization. For example, you can

Isn't it beautiful if one shares his effort in specialized intelligence, allowing others to reproduce, build on, or interact with it? ๐Ÿค— This belief inspires us to build Gentopia, designed for agent specialization, sharing, and interaction, to stackingly achieve collective growth towards greater intelligence..

Core Features ๐Ÿ’ก

Quick Start ๐Ÿ

conda create --name gentenv python=3.10
conda activate gentenv
pip install gentopia

or if you want to build with open LLMs locally ๐Ÿ‘‰ pip install gentopia[huggingface]

First time to Gentopia? Grab a coffee โ˜• and

Take ~ 8 mins to check out the following demo tutorials YouTube Channel Subscribers

<div style="display: flex; justify-content: space-around;"> <a href="https://www.youtube.com/watch?v=7dZ3ZvsI7sw" target="_blank"> <img src="https://img.youtube.com/vi/7dZ3ZvsI7sw/hqdefault.jpg" alt="Video 1" style="width:32%;"> </a> <a href="https://www.youtube.com/watch?v=XTsv9pk6AOA" target="_blank"> <img src="https://img.youtube.com/vi/XTsv9pk6AOA/hqdefault.jpg" alt="Video 2" style="width:32%;"> </a> <a href="https://www.youtube.com/watch?v=diJ4IDaT4Z4" target="_blank"> <img src="https://img.youtube.com/vi/diJ4IDaT4Z4/hqdefault.jpg" alt="Video 3" style="width:32%;"> </a> </div>

Or check out the Quick Start Doc.

Documentation ๐Ÿ“–

See here for full documentation.

๐ŸŒŸ Highlight Topics ๐ŸŒŸ

News ๐Ÿ‘ท

[Oct 7] The companion paper was accepted by #EMNLP 23. See you in Singapore! ๐Ÿฆ™๐ŸŒŽ

[Aug 6] We've submitted our work as a paper for EMNLP 2023. Special thanks to the research team and professors from NCSU, GMU, and CMU for collaboration :)

Join us! ๐ŸŒŽ

Participate in this Utopia of superintelligence and help it grows! As a fully open-source project, we develop under public advice, ideas, and supervision. Meanwhile, here are ways you may contribute to Gentopia.