Basic Stream

Code

from typing import Iterator  # noqa
from agno.agent import Agent, RunOutputEvent  # noqa
from agno.models.ollama import Ollama

agent = Agent(model=Ollama(host="http://localhost:11434", api_key=None, id="llama3.1:8b"), markdown=True)

# Get the response in a variable
# run_response: Iterator[RunOutputEvent] = agent.run("Share a 2 sentence horror story", stream=True)
# for chunk in run_response:
#     print(chunk.content)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story", stream=True)

Usage

Set up your virtual environment

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

Start the local Ollama service

Install Ollama and start its desktop app or service on http://localhost:11434. If you start it manually with ollama serve, keep that process running in a separate terminal.

In the terminal where you will pull models and run Python, select that server and clear the direct-cloud key. The native Ollama client also reads this key independently of Agno.

export OLLAMA_HOST=http://localhost:11434
unset OLLAMA_API_KEY

Pull the model

ollama pull llama3.1:8b

Install dependencies

uv pip install -U ollama agno

Run Agent

Save the code above as basic.py, then run:

python basic.py

Cloud Alternative

For easier setup without local installation, use Ollama Cloud with your API key:

from agno.agent import Agent
from agno.models.ollama import Ollama

# No local setup required - just set OLLAMA_API_KEY
agent = Agent(model=Ollama(id="gpt-oss:120b"))
agent.print_response("Share a 2 sentence horror story", stream=True)