> ## Documentation Index > Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt > Use this file to discover all available pages before exploring further. # Introduction This guide walks through the basics of building Agents with Agno. The examples build on each other, introducing new concepts and capabilities progressively. Each example contains detailed comments, example prompts, and required dependencies. ## Setup Create a virtual environment: ```bash theme={null} python3 -m venv .venv source .venv/bin/activate ``` Install the required dependencies: ```bash theme={null} pip install openai duckduckgo-search duckduckgo-search lancedb tantivy pypdf requests exa-py newspaper4k lxml_html_clean sqlalchemy agno ``` Export your OpenAI API key: ```bash theme={null} export OPENAI_API_KEY=your_api_key ``` ## Examples Build a news reporter with a vibrant personality. This Agent only shows basic LLM inference. Add web search capabilities using DuckDuckGo for real-time information gathering. Add a vector database to your agent to store and search knowledge. Add persistence to your agents with session management and history capabilities. Create an agent team specializing in market research and financial analysis. Generate a structured output using a Pydantic model. Create and integrate custom tools with your agent. Build an AI research agent using Exa with controlled output steering. Create a research workflow combining web searches and content scraping. Create an agent that can understand images. Create an Agent that can generate images using DALL-E. Create an Agent that can generate videos using ModelsLabs. Create an Agent that can process audio input and generate responses. Create an Agent with session state management. Evaluate dependencies at agent.run and inject them into the instructions. Create an Agent with persistent session memory across conversations. Create an Agent that stores user memories and summaries. Handle function retries for failed or unsatisfactory outputs. Add user confirmation and safety checks for interactive agent control. Each example includes runnable code and detailed explanations. We recommend following them in order, as concepts build upon previous examples.