Agentic AI Coach is an open-source project that utilizes CrewAI to enable collaborative AI agents for various tasks. This project aims to foster community contributions by allowing members to submit their own AI agents. It is pioneered by the AI Makerspace community of DPS with the purpose to provide scalable coaching for entrepreneurial teams. DPS community of AI engineers are all invited to contribute by submitting Agents and Tasks, and Crews.
- Modular Architecture: Built using CrewAI, allowing easy addition of new agents and tasks.
- Community-driven: Encourage community members to contribute their own AI agents.
- Flexible Configuration: Easily customize agents and tasks through YAML configuration files.
- Extensible Tools: Support for custom tools to enhance agent capabilities.
To get started with Agentic AI Coach, follow these steps:
-
Clone the repository:
git clone DigitalProductschool/AgenticAICoach cd AgenticAICoach
-
Select one of the available applications. For example, responsible_ai.
-
Run the project following the README guidelines.
Our project follows CrewAI's recommended structure:
AgenticAICoach/
├── knowledgebase_learning/
├── responsible_ai/
│ ├── db/
│ ├── src/
│ │ └── ai_act_compliance_checker/
│ │ ├── config/
│ │ │ ├── agents.yaml
│ │ │ ├── tasks.yaml
│ │ ├── data/
│ │ ├── tools/
│ │ ├── __init__.py
│ │ ├── crew.py
│ │ ├── main.py
│ ├── .env.example
│ ├── .gitignore
│ ├── poetry.lock
│ ├── pyproject.toml
│ ├── README.md
│ ├── trained_agents_data.pkl
├── community_submissions/
│ ├── agent_template/
│ │ ├── tests/
│ │ │ └── test_agent.py
│ │ ├── agent.py
│ ├── coaching_application_template/
├── docs/
│ ├── CONTRIBUTING.md
│ ├── PULL_REQUEST_TEMPLATE.md
├── .env.example
├── .gitignore
├── LICENSE
└── README.md
We welcome contributions! Please see our Contributing Guidelines for more information on how to contribute to this project.
This project is licensed under the MIT License - see the LICENSE file for details.
- Special thanks to the CrewAI team for creating such an excellent framework!
- Thanks to all community members who contribute their agents to this project.