Skip to main content

​
Code

cookbook/11_models/llama_cpp/tool_use_stream.py
"""Run `uv pip install` to install dependencies."""

from agno.agent import Agent
from agno.models.llama_cpp import LlamaCpp
from agno.tools.hackernews import HackerNewsTools

agent = Agent(
    model=LlamaCpp(id="ggml-org/gpt-oss-20b-GGUF"),
    tools=[HackerNewsTools()],
    markdown=True,
)
agent.print_response("Whats happening in France?", stream=True)

​
Usage

1

Set up your virtual environment

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

Install LlamaCpp

Follow the LlamaCpp installation guide and start the server:
llama-server -hf ggml-org/gpt-oss-20b-GGUF --ctx-size 0 --jinja -ub 2048 -b 2048
3

Install dependencies

uv pip install -U agno
4

Run Agent

python cookbook/11_models/llama_cpp/tool_use_stream.py