Enterprise AI Agents 🤖

Production-ready AI agents for enterprise automation • Built with modern AI frameworks • Deployed on Streamlit

Explore Agents • Quick Start • Contributing

---

📋 Table of Contents

• Overview
• All Agents (Quick View)
• AI Agent Showcase
• Quick Start
• Project Structure
• Technologies Used
• Contributing
• Contact
• License

---

🎯 Overview

This repository is a comprehensive collection of 8 production-ready AI agents designed to solve real-world enterprise problems. Each agent is a fully functional, deployable application built with cutting-edge AI frameworks and best practices.

Key Highlights

• Multi-Agent Systems: Specialized agents working together to solve complex tasks
• Real-World Applications: From customer support to competitive analysis
• Production Ready: Deployed applications with live demos
• Modern Stack: Built with Agno, LangGraph, OpenAI, and more
• Open Source: MIT licensed, ready to customize and deploy

Categories

• Business Intelligence (2 agents)
• Content Creation (1 agents)
• Customer Support (1 agents)
• Recommendations (2 agents)
• Recruitment (1 agents)
• Research & Analysis (1 agents)

---

🔍 All Agents (Quick View)

#	Agent	Category	Status	Quick Links
1	📚 Deep Knowledge Agent	Research & Analysis	🟢 Live	Demo • Docs • Code
2	🏠 Airbnb Listing Finder Agent	Recommendations	🟢 Live	Demo • Docs • Code
3	💬 Customer Support Agent	Customer Support	🔵 Local	Docs • Code
4	📖 Bookey - The Book Recommender Agent	Recommendations	🟢 Live	Demo • Docs • Code
5	🔍 Competitor Analysis Agent	Business Intelligence	🟢 Live	Demo • Docs • Code
6	✍️ Blog Post Generator Agent	Content Creation	🟢 Live	Demo • Docs • Code
7	👔 Employee Recruiter Agent	Recruitment	🟢 Live	Demo • Docs • Code
8	🚀 Startup Idea Validator	Business Intelligence	🟢 Live	Demo • Docs • Code

---

🚀 AI Agent Showcase

Click on any card to explore the live demo or dive into the source code!

📚 Deep Knowledge Agent Performs iterative searches through knowledge base, breaking down complex queries into sub-questions for comprehensive answers. Category: Research & Analysis Impact: Drastically reduces research time	🏠 Airbnb Listing Finder Agent AI agent that finds Airbnb listings based on natural language queries, searches and filters listings, and presents top 10 recommendations. Category: Recommendations Impact: 90% reduction in search time	💬 Customer Support Agent Intelligent customer support agent that categorizes queries, analyzes sentiment, and provides appropriate responses or escalates issues. Category: Customer Support Impact: Automates tier-1 support
📖 Bookey - The Book Recommender Agent AI-powered literary curator that provides personalized book recommendations based on reading preferences and favorite titles. Category: Recommendations Impact: 80% reduction in book search time	🔍 Competitor Analysis Agent Automates competitive analysis by identifying competitors, scraping websites, and generating comprehensive strategic reports with SWOT analysis. Category: Business Intelligence Impact: 95% reduction in research time	✍️ Blog Post Generator Agent Multi-agent content creation pipeline that transforms topics into complete content suites: research, blog post, LinkedIn post, and Twitter thread. Category: Content Creation Impact: Automated end-to-end content creation
👔 Employee Recruiter Agent Automated AI-powered recruitment system from resume screening to interview scheduling and email communications. Category: Recruitment Impact: Automates screening and scheduling	🚀 Startup Idea Validator Validates startup ideas through AI-powered multi-phase analysis with market research, competitive analysis, and strategic recommendations. Category: Business Intelligence Impact: 95% time reduction (weeks to minutes)

---

🏁 Quick Start

Prerequisites

• Python 3.9 or higher
• uv (recommended) or pip
• API keys for respective services (OpenAI, OpenRouter, etc.)

Running an Agent

1. Clone the repository:

   git clone https://github.com/bhanuchaddha/enterprise-ai-agents.git
   cd enterprise-ai-agents

2. Navigate to an agent directory:

   cd <agent_folder_name>

3. Install dependencies:

   uv sync  # or: pip install -r requirements.txt

4. Set up environment variables: Create a .env file with required API keys (see agent's README for specifics)

5. Run the Streamlit app:

   streamlit run streamlit_app.py

---

📁 Project Structure

enterprise-ai-agents/
├── 1_deep_knowledge_agent/
│   ├── documentation/
│   │   ├── assets/
│   │   │   └── demo.png (or .gif, .jpg, .jpeg)
│   │   └── display-info.json
│   ├── streamlit_app.py
│   ├── README.md
│   └── pyproject.toml
├── 2_airbnb_listing_finder_agent/
│   └── ...
├── common/
│   └── shared utilities
├── generate_readme.py
└── README.md (this file)

Each agent directory contains:

• documentation/: Agent metadata and demo assets
  • display-info.json: Configuration for README generation
  • assets/demo.png (or .gif, .jpg, .jpeg): Demo image for showcase
• streamlit_app.py: Web UI application
• README.md: Detailed agent documentation
• pyproject.toml: Python dependencies

---

🛠 Technologies Used

This project leverages cutting-edge AI and development tools:

AI Frameworks

• Agno: Multi-agent orchestration framework
• LangGraph: Graph-based agent workflows
• LangChain: LLM application development

LLM Providers

• OpenAI: GPT-4, GPT-3.5, embeddings
• OpenRouter: Multi-model access (Claude, Gemini, Llama, etc.)

Tools & Services

• Streamlit: Interactive web applications
• LanceDB: Vector database for embeddings
• Exa API: Advanced web search and research
• MCP (Model Context Protocol): Tool integration

Infrastructure

• Python 3.9+: Core programming language
• uv: Fast Python package manager
• SQLite: Local data persistence

---

🤝 Contributing

We welcome contributions! Here's how to add a new agent:

Adding a New Agent

1. Create agent directory:

   mkdir <your_agent_name>
   cd <your_agent_name>

2. Create directory structure:

   mkdir -p documentation/assets

3. Add your demo image:

   • Place your demo image at documentation/assets/demo.png (or .gif, .jpg, .jpeg)
   • Supported formats: PNG, GIF, JPG, JPEG
   • Recommended: 800x600 or 1024x768, < 5MB

4. Create display-info.json:

   cp ../display-info-schema.json documentation/display-info.json

   Fill in your agent's details (see schema for required fields)

5. Implement your agent:

   • Add your agent code
   • Create streamlit_app.py for UI
   • Write detailed README.md

6. Regenerate main README:

   python generate_readme.py

7. Submit a pull request!

Contribution Guidelines

• Follow existing code structure and naming conventions
• Include comprehensive documentation
• Add demo GIF or video
• Test your agent thoroughly
• Update display-info.json with accurate information

---

👤 Contact

Bhanu Chaddha

• LinkedIn: linkedin.com/in/bhanu-chaddha
• GitHub: @bhanuchaddha

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

⭐ Star this repo if you find it useful! ⭐

Made with ❤️ by Bhanu Chaddha