A collection of example code and tools for building, running, and experimenting with AI agents. This project is designed to help developers understand the core concepts of agent-based systems and how to implement them in practice.
- Modular agent architecture
- Example agents with different behaviors
- Easy-to-extend framework
- Sample tasks and environments
This project demonstrates agent-based systems by simulating interactions between specialized AI agents. Each agent is designed with a specific role (such as researcher, writer, summarizer, or translator) and communicates with other agents to accomplish complex tasks. The examples show how agents can collaborate, share information, and process tasks in a pipeline or cooperative workflow.
- CrewAI - Framework for orchestrating role-playing AI agents
Agent- Core component for creating specialized AI agents with specific roles and goalsTask- Defines structured work items that agents can process and completeCrew- Manages agent interactions and coordinates workflows between multiple agentsLLM- Language Model interface for agent communications and task processing- Uses Groq's Llama3-70B model for question answering over the retrieved context
- Python (version 3.11+ recommended)
- pip or uv
Clone the repository and install dependencies:
git clone [email protected]:adagio/AI_Agents_example.git
cd AI_Agents_example
uv pip install -r requirementes.inTo run the example featuring two agents, the "Technical Researcher" and the "Technical Writer", use:
python ia_en_medicina.pyTo run the example featuring the "Documentation Summarizer" and the "Technical Translator" agents, use:
python technical_documentation.py