ðŧSetting up AI agents for prediction markets
To begin with your custom project implementation, you will have to setup the following dependencies.
Install the project dependencies with
poetry
, using Python >=3.10:
python3.10 -m pip install poetry
python3.10 -m poetry install
python3.10 -m poetry shell
Create a
.env
file in the root of the repo with the variables.
These keys are necessary for the agent to interact with the prediction market APIs and other services.
MANIFOLD_API_KEY=...
OPENAI_API_KEY=...
GNOSIS_WALLET_PVT_KEY=...
Depending on the agent you want to run, you may require additional variables. See an exhaustive list of additional variables you may want to consider. The Prediction Market Trader Agent can interact with AIOmen and Polymarket as well.
Interactive Streamlit Apps
An autonomous agent with function calling: Can be 'prodded' by the user to guide its strategy. You can find the deployment here.
streamlit run prediction_market_agent/agents/microchain_agent/app.py
Pick a prediction market question, or create your own, and pick one or more agents to perform research and make a prediction, deployed here.
streamlit run scripts/agent_app.py
Last updated