Streaming Agent

Make sure to start the proxy server:

1litellm --model gpt-5-mini --host 127.0.0.1 --port 4000

Code

1from kern.agent import Agent, RunOutput  # noqa
2from kern.models.litellm import LiteLLMOpenAI
3
4agent = Agent(model=LiteLLMOpenAI(id="gpt-5-mini"), markdown=True)
5
6agent.print_response("Share a 2 sentence horror story", stream=True)

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export LITELLM_API_KEY=xxx

Install dependencies

1uv pip install -U litellm[proxy] openai kern-ai

Start the proxy server

1litellm --model gpt-5-mini --host 127.0.0.1 --port 4000

Run Agent

1python cookbook/11_models/litellm/basic_stream.py