A demonstration project showing how to build a multi-tool AI Agent using OpenAI’s Responses API. Although intended as an example, it also works amazingly well for network connectivity checking.
The agent runs in a terminal. It chooses which network tools to use for your query, interprets their output, and explains the results in plain language.
The included tools are:
pingcurlnetstattracertnslookupipconfig
If you're learning the Responses API or experimenting with AI agents that use multiple tools, this example shows a simple pattern without extra framework code. The source is in a single file.
It is also a powerful diagnostic tool in its own right.
Basic Connectivity >> How is the connection to google?
Comprehensive Analysis >> Describe the connectivity to www.amazon.com. Be exhaustive.
Performance Comparison >> Compare response times between AWS on the East and West coast.
DNS Troubleshooting >> I can't reach example.com. Is it a DNS problem?
Local Network Diagnostics >> Show me my current network configuration and default gateway.
Port Analysis >> What services are currently listening on my machine?
Route Investigation >> Why might packets to cloudflare.com be taking an unusual path?
Multi-Protocol Testing >> Can I reach github.com? Check both ping and HTTP connectivity.
Security Assessment >> Are there any unexpected connections to external IP addresses?
Network Path Optimization
>> Which endpoint has better routing from my location: https://www.nasa.gov or https://www.esa.int ?
Self Check >> Run a self-diagnostic.
- Python 3.9 or higher
- OpenAI API Key
Once published, you can install the package directly:
pip install connectivity-agent- Clone the repository:
git clone https://github.com/brocla/connectivity_agent.git
cd connectivity_agent- Install the package:
pip install -e .Or install the required dependencies manually:
pip install openai>=2.8.0The Connectivity Agent requires an OpenAI API key to function. You can obtain an API key from OpenAI's platform.
You have two options for providing your API key:
Option 1: Environment Variable (Recommended)
Set the OPENAI_API_KEY environment variable:
On Windows:
setx OPENAI_API_KEY "your-api-key-here"On Linux/Mac:
export OPENAI_API_KEY="your-api-key-here"To make it permanent on Linux/Mac, add the export command to your ~/.bashrc or ~/.zshrc file.
Option 2: Direct Configuration
The OpenAI Python client will automatically look for the API key in the environment variable. Alternatively, you can modify the code to pass the key directly (not recommended for security reasons).
After installation and API key setup, run the agent:
If installed via pip:
connectivity-agentIf running from source:
python connectivity_agent.pyThe agent will start an interactive REPL where you can ask connectivity-related questions.
Thanks to Thomas Ptacek for his article You Should Write an Agent