Inspiring the future of intelligent automation, one project at a time.
- 📌 About This Repository
- 🤖 Why Agentic AI?
- 🧩 Use Cases
- 🏗 Architecture
- 🧠 Project Showcase
- 🛠 Technologies Used
- ⚙️ Getting Started
- 🤝 Contributing
- 📄 License
A practical collection of agentic AI applications designed to address real-world challenges in recruitment, productivity, finance, data analysis, game building, landing page generation, multi-agent email classification, and book creation.
This repository showcases how agent-based systems, LLMs, and modular automation frameworks can be used to solve practical challenges. Each project here isn’t just a demo — it’s a working system that:
solves a real problem,
uses open and modern tools like Groq, CrewAI, and Phidata,
and is easy to run, customize, and learn from.
Whether you're a beginner learning how LLM agents work or a developer looking to build your own AI assistant — these examples are a great place to start.
Traditional AI workflows often involve single-shot predictions or static pipelines. Agentic AI introduces persistent, goal-driven agents capable of reasoning, planning, and adapting their behavior over time.
Key advantages:
- ✅ Autonomy – Agents can operate independently or in collaboration
- 🔁 Modularity – Plug-and-play components using orchestration frameworks
- 🧠 LLM-Powered Intelligence – Natural language reasoning, dynamic decision making
- 📡 Interoperability – Easily integrates with APIs, databases, and user-facing apps
The repository addresses a diverse range of automation opportunities:
- Recruitment – Resume parsing, JD matching, candidate ranking
- Productivity – Email classification, content writing, task generation
- Finance – Stock analysis, forecasting, scenario planning
- Data Science – Automated EDA, natural language to SQL reporting
- Enterprise Ops – Agent orchestration across workflows and microservices
- Game Development – Automated game prototyping and asset generation
- Web & Marketing – Landing page generation and optimization
- Communication – Multi-agent email classification and workflow automation
- Creative Content – Book creation with agent collaboration
We believe agent-based systems are the future of automation. The projects here are powered by:
- Multi-agent orchestration tools such as CrewAI and LangGraph
- LLMs such as Groq LLaMA 70B and OpenAI-compatible backends
- Fast iteration layers via Streamlit/FastAPI interfaces
- Storage and retrieval using SQLite, Redis, and Pandas
- Reusability of prompts, roles, tasks, and agents across domains
| Project | Description | Highlights |
|---|---|---|
end-to-end-recruiting |
Automates screening, JD matching, and candidate ranking | ✨ Reduces manual effort · LLM-powered parsing · CrewAI agents |
multi-agent-email-classification |
Collaborative agents for advanced email sorting and workflow automation | 🤖 Multi-agent reasoning · Customizable pipelines |
content-writing |
Rapid content drafting, editing, and ideation | 📝 Faster workflows · Prompt customization · Streamlit UI |
game-builder-agents |
Automated game prototyping and asset generation | 🎮 LLM-driven game logic · Asset creation · Fast iteration |
landing_page_generator |
Instantly generate and optimize landing pages | 🌐 AI-powered design · Customizable templates |
book-creation-agents |
End-to-end book writing and structuring with agents | 📚 Multi-agent collaboration · Chapter planning · Content generation |
data-analyst |
Auto-EDA, charting, and report generation from CSV/SQLite | 📈 Multi-agent orchestration · Natural language to SQL |
financial-agent |
Forecasting, what-if analysis, and scenario planning | 💰 Scenario engines · User-friendly config & output |
Each project is self-contained, with its own documentation and setup instructions. You can explore them individually or use them as templates for your own agentic AI solutions.
- Language Models: Groq LLaMA 70B, OpenAI-compatible APIs
- Frameworks: CrewAI, LangGraph, Phidata
- Frontend & Apps: Streamlit, FastAPI
- Database & Storage: SQLite, Pandas
- Containers & Deployment: Docker
- Orchestration: Multi-agent frameworks, modular execution graphs
Getting started is straightforward. Each project folder contains a README with detailed setup and usage instructions. In general, you can clone the repository and set up any project as follows:
▶️ Setup Instructions (click to expand)
git clone https://github.com/Dash10107/agentic-ai.git
cd agentic-ai
# Navigate to a project folder, e.g.:
cd end-to-end-recruiting
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
# See the project's README for detailsIf you run into any issues or have questions, each project README includes troubleshooting tips and contact information.
We welcome your ideas, feedback, and pull requests! See individual project READMEs for guidelines.
This repository is licensed under the MIT License. You're free to use, modify, and distribute with attribution.
⭐️ If you find these projects valuable, star this repo and help spread the agentic AI movement!
