> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Missionaries And Cannibals Puzzle

> Solve the missionaries-and-cannibals river crossing with an ASCII diagram, contrasting gpt-4o built-in chain-of-thought with a deepseek-reasoner reasoning model.

Demonstrates DeepSeek-backed reasoning for logic puzzle solving.

```python logical_puzzle.py theme={null}
"""
Missionaries And Cannibals Puzzle
=================================

Demonstrates DeepSeek-backed reasoning for logic puzzle solving.
"""

from agno.agent import Agent
from agno.models.deepseek import DeepSeek
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
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 solutions as an ascii diagram"
)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.6"),
    reasoning_model=DeepSeek(id="deepseek-reasoner"),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(task, stream=True, show_full_reasoning=True)
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai
```

**2. Export your API keys**

```bash Mac/Linux theme={null}
export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:DEEPSEEK_API_KEY="your_deepseek_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

Save the code above as `logical_puzzle.py`, then run:

```bash theme={null}
python logical_puzzle.py
```

Full source: [cookbook/10\_reasoning/agents/logical\_puzzle.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/10_reasoning/agents/logical_puzzle.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.