Skip to main content

​
Quick Start Guide

This guide will walk you through running your first AI agent example. We’ll use the Agno HackerNews Analysis agent as it’s simple, well-documented, and demonstrates core AI agent concepts.

​
What You’ll Build

By the end of this guide, you’ll have a working AI agent that can:
  • Analyze trending topics on HackerNews
  • Track user engagement patterns
  • Provide insights about tech trends
  • Answer questions about tech news in natural language
1

Clone the Repository

First, clone the Awesome AI Apps repository to your local machine:
git clone https://github.com/Arindam200/awesome-ai-apps.git
cd awesome-ai-apps
The repository contains 70+ examples. For this quickstart, we’ll focus on just one.
2

Navigate to the Agno Starter Project

Change into the Agno starter agent directory:
cd starter_ai_agents/agno_starter
This project contains:
  • main.py - The main agent code
  • requirements.txt - Python dependencies
  • .env.example - Template for environment variables
  • README.md - Detailed project documentation
3

Set Up Your API Key

This agent uses Nebius Token Factory for AI inference. You’ll need to get a free API key:
  1. Visit Nebius Token Factory
  2. Sign up for a free account
  3. Generate an API key from your dashboard
Then, create your .env file:
cp .env.example .env
Edit .env and add your API key:
NEBIUS_API_KEY=your_actual_api_key_here
Never commit your .env file to version control. It’s already in .gitignore for your safety.
4

Install Dependencies

Install the required Python packages. We recommend using uv for faster installs, but pip works too:
uv sync
uv is a fast Python package installer. Install it with: pip install uv
5

Run Your First Agent

Start the agent:
python main.py
You should see output like this:
🤖 Tech News Analyst is ready!

I can help you with:
1. Top stories and trends on HackerNews
2. Detailed analysis of specific topics
3. User engagement patterns
4. Tech industry insights

Type 'exit' to quit or ask me anything about tech news!

You:
6

Try Example Queries

Now you can interact with the agent! Try these example queries:
What are the most discussed topics on HackerNews today?

Analyze the engagement patterns in the top stories

What tech trends are emerging from recent discussions?
The agent will use the HackerNews API to fetch data and provide intelligent analysis using the Nebius AI model.Type exit when you’re done to quit the agent.

​
Understanding the Code

Let’s look at the key components of this agent. Here’s the main code from main.py: 
from agno.agent import Agent
from agno.tools.hackernews import HackerNewsTools
from agno.models.nebius import Nebius
import os
from dotenv import load_dotenv

load_dotenv()

# Create the agent with tools and model
agent = Agent(
    name="Tech News Analyst",
    instructions=[INSTRUCTIONS],  # System prompt defining behavior
    tools=[HackerNewsTools()],     # HackerNews API integration
    show_tool_calls=True,          # Show when tools are called
    model=Nebius(
        id="Qwen/Qwen3-30B-A3B",
        api_key=os.getenv("NEBIUS_API_KEY")
    ),
    markdown=True,                  # Format output as markdown
)

# Interactive loop
while True:
    user_input = input("\nYou: ").strip()
    if user_input.lower() == 'exit':
        break
    agent.print_response(user_input)

​
Key Concepts

Agent

The core Agent class orchestrates the LLM, tools, and instructions

Tools

HackerNewsTools() gives the agent access to the HackerNews API

Model

Nebius provides the AI inference using Qwen3-30B model

Instructions

System prompt that defines the agent’s personality and capabilities

​
Next Steps

Congratulations! You’ve successfully run your first AI agent. Here’s what to explore next:

​
Try More Examples

Finance Agent

Build an agent that tracks stock prices and market data

AWS Strands Course

Complete 8-lesson course on building production agents

MCP Agents

Learn to integrate external tools via Model Context Protocol

RAG Applications

Build document Q&A systems with retrieval augmentation

​
Customize Your Agent

Try modifying the agent to fit your needs:
  1. Change the model: Replace Qwen/Qwen3-30B-A3B with other models available on Nebius
  2. Add more tools: Combine HackerNewsTools with DuckDuckGoTools or YFinanceTools
  3. Modify instructions: Update the system prompt to change the agent’s behavior
  4. Enable memory: Uncomment memory=True for context retention across conversations

​
Explore Different Frameworks

The repository includes examples using 10+ different frameworks: 
# Try OpenAI Agents SDK
cd starter_ai_agents/openai_agents_sdk

# Try AWS Strands
cd starter_ai_agents/aws_strands_starter

# Try LangChain + LangGraph
cd starter_ai_agents/langchain_langgraph_starter
Each project has its own README.md with specific setup instructions.

​
Common Issues

Make sure you’ve installed dependencies:
pip install -r requirements.txt
Or if using uv:
uv sync
Ensure your .env file exists and contains a valid NEBIUS_API_KEY:
NEBIUS_API_KEY=your_actual_api_key_here
Don’t use quotes around the key.
This project requires Python 3.10 or higher. Check your version:
python --version
If needed, use python3.10 or python3.11 instead of python.
Make sure show_tool_calls=True is set in the Agent configuration. This displays when the agent uses tools like the HackerNews API.

​
Getting Help

If you run into issues:
  1. Check the project’s README.md for specific instructions
  2. Review the Prerequisites page for system requirements
  3. Open an issue on GitHub
  4. Join the community discussions
Each of the 70+ examples has its own detailed README with setup instructions, usage examples, and technical details.

​
Ready to Build?

Now that you’ve run your first agent, explore the full collection of examples to find patterns that match your use case. Every project is designed to be a starting point you can customize and extend. Happy building! 🚀

Build docs developers (and LLMs) love

Get started for freeTalk to us