autogen/python/samples/agentchat_chess_game

• AgentChat Chess Game
• • Setup
  • Run

AgentChat Chess Game

This is a simple chess game that you can play with an AI agent.

Setup

Install the chess package with the following command:

pip install "chess"

To use OpenAI models or models hosted on OpenAI-compatible API endpoints,
you need to install the autogen-ext[openai] package. You can install it with the following command:

pip install "autogen-ext[openai]"
# pip install "autogen-ext[openai,azure]" for Azure OpenAI models

To run this sample, you will need to install the following packages:

pip install -U autogen-agentchat pyyaml

Create a new file named model_config.yaml in the the same directory as the script
to configure the model you want to use.

For example, to use gpt-4o model from OpenAI, you can use the following configuration:

provider: autogen_ext.models.openai.OpenAIChatCompletionClient
config:
  model: gpt-4o
  api_key: replace with your API key or skip it if you have environment variable OPENAI_API_KEY set

To use o3-mini-2025-01-31 model from OpenAI, you can use the following configuration:

provider: autogen_ext.models.openai.OpenAIChatCompletionClient
config:
  model: o3-mini-2025-01-31
  api_key: replace with your API key or skip it if you have environment variable OPENAI_API_KEY set

To use a locally hosted DeepSeek-R1:8b model using Ollama throught its compatibility endpoint,
you can use the following configuration:

provider: autogen_ext.models.openai.OpenAIChatCompletionClient
config:
  model: deepseek-r1:8b
  base_url: http://localhost:11434/v1
  api_key: ollama
  model_info:
    function_calling: false
    json_output: false
    vision: false
    family: r1

For more information on how to configure the model and use other providers,
please refer to the Models documentation.

Run

Run the following command to start the game:

python main.py

By default, the game will use a random agent to play against the AI agent.
You can enable human vs AI mode by setting the --human flag:

python main.py --human