LLM-based simulation framework
Project description
Simulatrex
Simulatrex is a Large Language Model (LLM) based simulation framework designed to run social science simulations involving multi-agent structures and hierarchies. It provides a robust and flexible platform for creating and running complex simulations, making it an ideal tool for researchers and developers in the field of social sciences, artificial intelligence, and more.
Features
- Multi-Agent Simulations: Simulatrex allows you to create simulations with multiple agents, each with their own identities, initial conditions, and cognitive models.
- Dynamic Environments: Simulatrex supports both static and dynamic environments, allowing for a wide range of simulation scenarios.
- Event-Driven: Simulatrex simulations are event-driven, with a built-in event engine to process events and update the environment.
- Evaluation Engine: Simulatrex includes an evaluation engine to evaluate the outputs of the agents based on predefined objectives and metrics.
- Language Model Integration: Simulatrex integrates with language models like OpenAI's GPT-4, enabling agents to generate human-like responses.
Installation
To install Simulatrex, you need to have Python 3.6 or higher. You can install it using pip:
pip install simulatrex
Usage
Here is a basic example of how to use Simulatrex:
import asyncio
import dotenv
from simulatrex import SimulationEngine
dotenv.load_dotenv()
async def main():
engine = SimulationEngine("./data/1_consumer_price_simulation_config.json")
await engine.run()
if __name__ == "__main__":
asyncio.run(main())
In this example, we're creating a new SimulationEngine with a configuration file and then running the simulation.
Project details
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.
Source Distribution
Built Distribution
Hashes for simulatrex-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 295105f35ed7ffa67a2f07c4e8c6b3b32261f1ae9c173e0b985936766ac8230d |
|
MD5 | 7e47505b42af3484300a216cd7967cd0 |
|
BLAKE2b-256 | aa2bcb9129660f6296f4879f1ecd6daa5f1f99ad92443dc33f221e2ba41587fb |