Skip to content
BeeAI Framework

Quickstart

  1. Clone the starter repo

    Chose your preferred programming language and get started with the BeeAI Framework starter template.

    Terminal window
    git clone https://github.com/i-am-bee/beeai-framework-py-starter.git
    cd beeai-framework-py-starter

  2. Install the dependencies

    If you’re using python, make sure you have uv installed.

    Terminal window
    uv sync

  3. Configure your Environment Variables

    Create an .env file with the contents from .env.template

    Terminal window
    cp .env.template .env

  4. Configure your LLM Backend

    If you choose to run a local model, Ollama must be installed and running, with the granite4.1:8b model pulled. If you run into issues, run ollama list to verify the model name and ensure granite4.1:8b is installed or that your alias points to it.

    Terminal window
    ollama pull granite4.1:8b

    or

    If you chose to use a hosted model, edit the LLM_CHAT_MODEL_NAME in the .env file.

    Terminal window
    # Examples (pick one that matches your provider/account):
    LLM_CHAT_MODEL_NAME="openai:gpt-5-mini"

    Add your API key for your preferred provider to your .env file and uncomment the line.

    Terminal window
    # Examples (pick one that matches your provider/account):
    OPENAI_API_KEY="YOUR API KEY"

  5. Run the Agent

    This agent is an activity planner that can help you plan your day. Prompt it with your task and location. Exit the loop by typing “q” and enter.

    Take a look inside the code file to understand the example agent.

    Terminal window
    uv run python beeai_framework_starter/agent.py

    Congratulations! You’ve ran your first BeeAI agent.

Explore more examples in our Python and TypeScript libraries.