Skip to content

A lightweight AI Agent built from scratch in Python implementing the ReAct (Reason + Act) pattern. Demonstrates autonomous tool use for cybersecurity workflows (IP scanning) without external dependencies.

Notifications You must be signed in to change notification settings

Said-Slassi/Simple-Agentic-AI

ย 
ย 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

3 Commits
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿค– Simple Agentic AI Demo (Python)

A "ReAct" (Reason + Act) Agent built from scratch in Python without external LLM libraries.

๐Ÿš€ Overview

This project demonstrates the core concept of Agentic AIโ€”moving beyond chatbots to systems that can autonomously execute tools.

Unlike a standard LLM which only outputs text, this agent:

  1. Reasons about a user request.
  2. Decides which tool to use (Calculator or Security Scanner).
  3. Executes the tool in a safe Python environment.
  4. Returns the actual result to the user.

๐Ÿ› ๏ธ Features

  • Mock LLM Brain: Simulates decision-making logic using Regex patterns.
  • Tools:
    • calculate(): Safely evaluates mathematical expressions.
    • check_ip_reputation(): Simulates a cybersecurity scan for malicious IPs.
  • Safety: Implements input sanitization and error handling.

๐Ÿ’ป How to Run

  1. Clone the repository:
    git clone [https://github.com/krinathakkar646/Simple-Agentic-AI.git](https://github.com/krinathakkar646/Simple-Agentic-AI.git)
    
  2. Run the Agent
    python agent.py

About

A lightweight AI Agent built from scratch in Python implementing the ReAct (Reason + Act) pattern. Demonstrates autonomous tool use for cybersecurity workflows (IP scanning) without external dependencies.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%