🦉 OWL: Towards General Multi-Agent Assistant for Real-World Task Automation
🦉 OWL is a cutting-edge framework for multi-agent collaboration that pushes the boundaries of task automation. Built on top of the Camel-AI Framework. OWL ranks #1 among open-source frameworks on GAIA benchmark.
Our vision is to revolutionize how AI agents collaborate to solve real-world tasks. By leveraging role-playing mechanisms and dynamic agent interactions, OWL enables more natural, efficient, and robust task automation across diverse domains.
Quick Start
- Clone the Github repository:
$ git clone xxx
- Set up Python Environment:
$ conda create -n owl python=3.11
$ conda activate owl
- Install Dependencies:
$ pip install -r requirements.txt
-
Set API Keys: We use
dotenvto manage API keys. Please copy and check the.env.examplefile to.envand fill in the necessary API keys. -
Run the Demo Code:
$ python run.py
Additionally, We have provided a script to reproduce the results on GAIA. You can check the run_gaia_roleplaying.py file and run the following command:
$ python run_gaia_roleplaying.py
Community
[Camel Link]
[This project]