Python | Agno

PythonTools enable an Agent to write and run python code.

Prerequisites

Create and activate a virtual environment, then install:

uv pip install agno openai

The Agent model uses an OpenAI key, separately from any toolkit provider credentials.

Set OpenAI Key

Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.

export OPENAI_API_KEY=sk-***

Example

The following agent will write a python script that creates the fibonacci series, save it to a file, run it and return the result.

cookbook/91_tools/python_tools.py

from agno.agent import Agent
from agno.tools.python import PythonTools

agent = Agent(tools=[PythonTools()])
agent.print_response("Write a python script for fibonacci series and display the result till the 10th number")

PythonTools can run arbitrary Python code and install packages with no command restriction. Keep human supervision for untrusted prompts, and run inside a sandbox (container, VM, or Daytona) for untrusted code execution.

Toolkit Params

Parameter	Type	Default	Description
`base_dir`	`Path`	`None`	Specifies the base directory for operations. Default is None, indicating the current working directory
`safe_globals`	`dict`	`None`	Dictionary of global variables that are considered safe to use during execution
`safe_locals`	`dict`	`None`	Dictionary of local variables that are considered safe to use during execution
`restrict_to_base_dir`	`bool`	`True`	If True, file operations cannot escape `base_dir`

Toolkit Functions

Function	Description
`save_to_file_and_run`	This function saves Python code to a file called `file_name` and then runs it. If successful, returns the value of `variable_to_return` if provided otherwise returns a success message. If failed, returns an error message. Make sure the file_name ends with `.py`
`run_python_file_return_variable`	This function runs code in a Python file. If successful, returns the value of `variable_to_return` if provided otherwise returns a success message. If failed, returns an error message.
`read_file`	Reads the contents of the file `file_name` and returns the contents if successful.
`list_files`	Returns a list of files in the base directory
`run_python_code`	This function runs Python code in the current environment. If successful, returns the value of `variable_to_return` if provided otherwise returns a success message. If failed, returns an error message.
`pip_install_package`	This function installs a package using pip in the current environment. If successful, returns a success message. If failed, returns an error message.
`uv_pip_install_package`	This function installs a package using uv and pip in the current environment. If successful, returns a success message. If failed, returns an error message.

You can use include_tools or exclude_tools to modify the list of tools the agent has access to. Learn more about selecting tools.

Developer Resources

Tools