WebNinja: AI Assistant for Web Research

Hi! I want to share my small hobby project — WebNinja. Inspired by AI Manus (and the community's playful "anus" 😄), I decided to create my own mini-version of a web research agent.

What is it?

WebNinja is a simple yet functional tool that:

  • 🤖 Uses AI (Grok or GPT-4) to analyze information
  • 🔍 Collects data from websites
  • 📊 Generates reports based on the collected data

How can it be used?

For designers:

  • Quick analysis of design trends
  • Collecting references from various sites
  • Monitoring new things in UI/UX

For developers:

  • Tracking tech news
  • Analyzing new tools and frameworks
  • Collecting feature implementation examples

For others:

  • Marketing research
  • Competitor analysis
  • Monitoring news in any field

How to get started?

  1. Clone the repository:
git clone https://github.com/mirvald-space/WebNinja.git
  1. Install dependencies:
python -m venv .myenv
source .myenv/bin/activate  # for Linux/Mac
pip install -r requirements.txt
  1. Create a .env file and add your API key:

GROK_API_KEY=your-key-here or OPENAI_API_KEY=your-key-here

  1. Run the example:
python examples/research_agent.py

Usage examples

For designers:

topic = "UI design trends 2024"
agent.research(topic, depth=3)  # Checks 3 sources

For developers:

topic = "New features in Python 3.12"
agent.research(topic, max_time=180)  # 3 minutes for search

For marketers:

topic = "AI tools market analysis"
agent.research(topic)

What can you get?

  • 📝 Structured report with key facts
  • 🔍 Comparison of information from different sources
  • 💡 Conclusions and recommendations
  • 🌐 Links to sources for further study

Limitations

Of course, this is a hobby project, so it has its limitations:

  • Works only with open sources
  • Requires an API key for AI models
  • May miss some details
  • Sometimes needs additional result verification

Where to find it?

From me

I created this tool for my own needs, but I'll be glad if it helps someone else. You can use it as is or take it as a basis for your own experiments.

If you're interested in the project — subscribe to my Telegram, where I share other useful stuff for designers and developers!


P.S.: This is an experimental project, so use it with an understanding of its limitations. But for quick information gathering — it's a fully working tool! 😉

m.space