Llmman Agent with Tools

Give a local model a web search tool.

Complete the Llmman server setup first. Keep the server running while using a second terminal with an activated Python environment:

uv pip install -U agno openai ddgs

Code

tool_use.py
"""Run `uv pip install ddgs` to install dependencies."""

from agno.agent import Agent
from agno.models.llmman import Llmman
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=Llmman(id="qwen3:0.6b-q4_K_M"),
    tools=[WebSearchTools()],
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("Whats happening in France?")

    # --- Sync + Streaming ---
    agent.print_response("Whats happening in France?", stream=True)

Save the code as tool_use.py and run:

python tool_use.py

Web search uses external websites even though model inference runs locally. The selected model must be able to call tools.