Code
reasoning_agent.py
Usage
1
Set up your virtual environment
2
Set your API key
3
Install dependencies
4
Run Agent
Save the code above as
reasoning_agent.py, then run:Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Solve a river-crossing logic puzzle with a MiMo agent in thinking mode, streaming the full reasoning trace.
from agno.agent import Agent
from agno.models.xiaomi import MiMo
task = (
"Three missionaries and three cannibals need to cross a river. "
"They have a boat that can carry up to two people at a time. "
"If, at any time, the cannibals outnumber the missionaries on either side of the river, the cannibals will eat the missionaries. "
"How can all six people get across the river safely? Provide a step-by-step solution and show the solution as an ascii diagram."
)
agent = Agent(
model=MiMo(id="mimo-v2.5-pro", use_thinking=True),
markdown=True,
)
if __name__ == "__main__":
agent.print_response(task, stream=True, show_full_reasoning=True)
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
Set your API key
export MIMO_API_KEY=xxx
Install dependencies
uv pip install -U openai agno
Run Agent
reasoning_agent.py, then run:python reasoning_agent.py
Was this page helpful?