Recon is one of the most important phases that seem easy but takes a lot of effort and skill to do right. One needs to know about the right tools, correct queries/syntax, run those queries, correlate the information, and sanitize the output. All of this might be easy for a seasoned infosec/recon professional to do, but for rest, it is still near to magic. How cool it will be to ask a simple question like “Find me an open Memcached server in Singapore with UDP support?” or “How many IP cameras in Singapore are using default credentials?” in a chat and get the answer?

The integration of GPT-3, deep learning-based language models to produce human-like text, with well-known recon tools like Shodan, is the foundation of ReconPal. ReconPal also supports using voice commands to execute popular exploits and perform reconnaissance.

Built With

  • OpenAI GPT-3
  • Shodan API
  • Speech-to-Text
  • Telegram Bot
  • Docker Containers
  • Python 3

Getting Started

To get ReconPal up and running, follow these simple steps.


  • Telegram Bot Token Use BotFather and create a new telegram bot. Refer to the documentation at
  • Shodan API:
    Create a shodan Account and create a new API Key from
  • Google Speech-to-Text API:
    Enable Speech-to-Text in GCP and get the credentials. Refer to these steps from the documentation
  • OpenAI API Key:
    Create a free openAI account to try out the API.
  • Docker

sudo apt-get updates​
sudo apt-get install​
sudo curl -L “$(uname -s)-$(uname -m)” -o​ /usr/local/bin/docker-compose​
chmod +x /usr/local/bin/docker-compose


  • Clone the repo

git clone

  • Enter your OPENAI, SHODAN API keys, and TELEGRAM bot token in docker-compose.yml


Start reconpal

docker-compose up


Open the telegram app and select the created bot to use ReconPal.

  • Click on start or just type in the input box.


  • Register the model


  • Test the tool with some commands.