# Ai Engineering Hub

> A collection of LLM-powered Real-World applications and projects

- **Type:** MCP server
- **Install:** `agentstack add mcp-fcyber-labs-ai-engineering-hub`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [fcyber-labs](https://agentstack.voostack.com/s/fcyber-labs)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [fcyber-labs](https://github.com/fcyber-labs)
- **Source:** https://github.com/fcyber-labs/ai-engineering-hub

## Install

```sh
agentstack add mcp-fcyber-labs-ai-engineering-hub
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 🌟 AI Engineering Hub ✨ 5/15 projects · more on the way

A comprehensive showcase of enterprise-grade LLM applications featuring RAG architectures, intelligent AI agents, autonomous agentic systems, Model Context Protocol (MCP), LangChain/LangGraph frameworks, and cutting-edge generative AI patterns

This repository features LLM apps that use models from OpenAI, Anthropic, Google, xAI and open-source models like Qwen or Llama that you can run locally on your computer.

  
[](README.md)
[](README.de.md)
[](README.ru.md)
[](README.zh.md)

[📂 Featured AI Projects](#-featured-ai-projects) •
[🚀 Getting Started](#-getting-started) •
[🤔 Why AI Engineering Hub?](#-why-ai-engineering-hub) •
[🤝 Contributing](#-contributing) •
[🙏 Thank You](#-thank-you-community-for-the-support)

---

**5 projects live. More shipping every few weeks.**

This is where I build and document real AI engineering work — not tutorials copied from docs, not "hello world" agents. Every project here started from a problem I actually wanted to solve, and the code reflects that.

The stack changes per project depending on what fits. LangGraph when I need stateful agent loops. Groq when inference speed matters. Local models when I want to understand what's actually happening under the hood. Each folder has a working app, a proper README, and usually a live demo you can try right now without cloning anything.

If you're an engineer looking to see how these systems get built in practice — not in theory — this is the repo for that.
---

## What's here

|#|Project|What it does|Stack|Demo|
|---|---|---|---|---|
|01|[Agentic RAG Assistant](https://claude.ai/chat/752de37c-c299-4a89-85fe-c56f772a11e5#-1-agentic-rag-assistant)|Smart Q&A with self-correction and hallucination detection|LangGraph · Hybrid Search · GPT-4o|[🤗 Try it](https://huggingface.co/spaces/fcyber/agentic_rag)|
|02|[Voice AI Assistant](https://claude.ai/chat/752de37c-c299-4a89-85fe-c56f772a11e5#-2-voice-ai-assistant)|Talk to an AI, get voice responses back|Groq · Whisper · gTTS · Streamlit|[🌐 Live app](https://fcyber-labs-voice-ai-assistant.streamlit.app/)|
|03|[AI Podcast Generator](https://claude.ai/chat/752de37c-c299-4a89-85fe-c56f772a11e5#-3-ai-news-podcast-generator)|News URLs → produced podcast episode with MP3|LangGraph · BART · Groq · gTTS|[🤗 Try it](https://huggingface.co/spaces/fcyber/ai-podcast)|
|04|[YouTubeScriptMaster](https://claude.ai/chat/752de37c-c299-4a89-85fe-c56f772a11e5#-4-youtubescriptmaster)|YouTube video → structured script and summary|LangGraph · Groq · yt-dlp · BART|[🤗 Try it](https://huggingface.co/spaces/fcyber/YouTubeScriptMaster)|
|05|[AI Presentation Generator](https://claude.ai/chat/752de37c-c299-4a89-85fe-c56f772a11e5#-5-ai-presentation-generator)|Plain text → full PowerPoint deck with AI images|LangGraph · Groq · python-pptx · Streamlit|[🤗 Try it](https://huggingface.co/spaces/fcyber/YouTubeScriptMaster)|

---

## 📂 Featured AI Projects

### 👨‍💼 [1. Agentic RAG Assistant](./01-agentic-rag-assistant)    
[](01-agentic-rag-assistant/assets/project_1.gif) [](https://huggingface.co/spaces/fcyber/agentic_rag)

#### Smart Q&A Assistant with intelligent routing, query refinement, hallucination checking, and self-correction loops.

### 🤖 [2.  Voice AI Assistant](./02-voice-ai-assistant)  
[](02-voice-ai-assistant/assets/project_2.gif) [](https://fcyber-labs-voice-ai-assistant.streamlit.app/)

#### Voice AI Assistant featuring real-time speech recognition, ultra-fast Groq inference, natural voice synthesis, and downloadable audio responses.

### 🎧 [3.  AI News Podcast Generator - AI DAILY DIGEST](./03-ai-podcast-generator)
[](03-ai-podcast-generator/assets/project3_demo.gif) [](https://huggingface.co/spaces/fcyber/ai-podcast)

#### AI Podcast Generator transforms top AI news headlines into fully-produced podcast episodes automatically. Simply enter URLs of AI news sources, and the app scrapes, summarizes, and converts the content into a professional podcast script with downloadable MP3 audio. Choose your source - either extract the best AI news from top 50 websites or discover trending stories from HackerNews.

### 📺 [4. YouTubeScriptMaster](./04-YouTubeScriptMaster)
[](assets/project4-demo.gif) [](https://huggingface.co/spaces/fcyber/YouTubeScriptMaster)

#### Automatically generate structured scripts from any YouTube link with YouTube Summary Master. The system intelligently chunks long videos, extracts metadata, and creates rich summaries including executive overviews, TL;DR, semantic sections, key insights, and named entities – all in a beautifully formatted markdown document. Choose between lightning-fast Groq API or privacy-focused local BART processing, then download both summary and raw transcript with one click.

 
 
 
 
 
 
 

### 👨‍🎨 [5.  AI Presentation Generator](./05-ai-presentation-generator)
[](assets/project5-demo.gif) [](https://huggingface.co/spaces/fcyber/YouTubeScriptMaster)

#### AI Presentation Generator is an AI-powered presentation engine that transforms raw text into polished, executive-ready PowerPoint decks using a structured LangGraph pipeline. It extracts key insights, organizes content into compelling narratives, generates concise summaries, and enhances each slide with AI-generated visuals and modern glassmorphism design. The result is a high-impact, visually consistent .pptx presentation that rivals professional-grade work—delivering one clear, memorable takeaway per slide.

---

### 🚧 More Projects Coming Soon

🔮 Planned Projects (Click to Expand)

| Project | Description | Status |
| :--- | :--- | :--- |
| 🗣️ **Voice RAG Agent** | Voice-enabled Q&A with real-time transcription | `Planned` |
| 🌐 **MCP Browser Agent** | Browser automation with Model Context Protocol | `Planned` |
| 🤝 **Multi-Agent Research** | Collaborative research agents with handoffs | `Planned` |
| 📄 **Chat with PDF** | Document Q&A with hybrid search | `Planned` |
| 💬 **Stateful Memory** | Conversational AI with persistent memory | `Planned` |

---

## 🚀 Getting Started
### 🎯 Quick Start Comparison (Updated)

| Method | Command | Time | Requires |
|--------|---------|------|----------|
| **Python** | `pip install -r requirements.txt && python app.py` | 2-5 min | Python 3.9+ |
| **Docker** | `docker-compose up -d` | 30 sec | Docker + Compose |
| **Hugging Face** | [](https://huggingface.co/spaces/fcyber/agentic_rag) | 1 sec | Web browser |

### 📦 Option 1: Python (Local Setup)

1. **Clone the repository**
   ```bash
   git clone https://github.com/fcyber-labs/ai-engineering-hub.git
   ```

2. **Navigate to the desired project directory**
   ```bash
   cd ai-engineering-hub/01-agentic-rag-assistant
   ```

3. **Install the required dependencies**
   ```bash
   pip install -r requirements.txt
   ```

4. **Run Python apps**
   ```bash
   python app.py
   ```

#### Follow the project-specific instructions in each project's `README.md` file to set up and run the app.
• • •

### 🐳 Option 2: Docker Compose (Recommended)
[](https://hub.docker.com/r/fcyber/agentic-rag-assistant)
[](https://docs.docker.com/compose/)

1. **Clone the repository**
```bash
git clone https://github.com/fcyber-labs/ai-engineering-hub.git
```

2. **Navigate to the desired project directory**
```bash
cd ai-engineering-hub/01-agentic-rag-assistant
```

3. **Set up environment variables**
```bash
cp .env.example .env
# Edit .env with your GROQ_API_KEY keys
```

4. **Run with Docker Compose**
```bash
docker-compose up -d
```

5. **View logs (optional)**
```bash
docker-compose logs -f
```

6. **Open in browser**
```bash
http://localhost:7860
```

7. **Stop the container**
```bash
docker-compose down
```

**That's it!** The project includes a pre-configured `Dockerfile` and `docker-compose.yml` — no additional setup needed.

• • •

### 🤗 Option 3: Hugging Face Spaces

[](https://huggingface.co/spaces/fcyber/)

```bash
# No installation needed! Click the badge above to try the live demo.
# Or clone and run locally:
pip install huggingface-hub
huggingface-cli download fcyber/agentic-rag-assistant
python app.py  # Gradio apps run with python
```
---
## 📝 Article

I wrote an article related to this project: 
- [Why Integrating Apple’s Ecosystem into a Local RAG Project Is Harder Than It Looks ](https://medium.com/@fcyber/why-integrating-apples-ecosystem-into-a-local-rag-project-is-harder-than-it-looks-3949f9f03131)
This article explores the real-world challenges of integrating Apple’s CLaRa-7B-Instruct into a local RAG system. While the model offers impressive compression and reasoning capabilities, running it locally introduces significant hardware, architectural, and deployment complexity. I break down what made it difficult and what I learned from the process.

---

## 🛠️ Technology Stack
| Category | Technologies |
| --- | --- |
| LLM Frameworks | LangChain, LangGraph, LlamaIndex |
| Models | GPT-4, Claude 3.5, Sonnet, Gemini 1.5 Pro, Llama 3.1, Qwen 2.5 |
| Vector Databases | Pinecone, Chroma, Weaviate, Qdrant |
| Embeddings | OpenAI, Cohere, HuggingFace, Voyage |
| Frontend | Streamlit, Gradio, Chainlit |
| Monitoring | LangSmith, Arize Phoenix, Weights & Biases |
| Deployment | Streamlit Cloud, Hugging Face Spaces, Docker, AWS |

---

## 🤝 Contributing
We welcome contributions! Please follow these steps:
- Fork the repository
- Create a feature branch 
   ```bash
  git checkout -b feature/amazing-project
   ```
- Commit your changes 
  ```bash
  git commit -am 'Add amazing project'
  ```
- Push to the branch
  ```bash
  git push origin feature/amazing-project
  ```
- Open a Pull Request

### ✅ Contribution Checklist
- Self-contained project directory
- Comprehensive README with setup instructions
-Working demo with clear setup steps
-.env.example with all required variables
-requirements.txt with pinned versions
-Screenshots demonstrating functionality 
---
## 🙏 Thank You, Community, for the Support!
 

⭐ Star this repository if you find it useful! ⭐

 

 
---
 

## 📊 Repository Stats

| ⭐ **Stars** | 🍴 **Forks** | 👀 **Watchers** |
|:-----------:|:-----------:|:--------------:|
| [](https://github.com/fcyber-labs/ai-engineering-hub/stargazers) | [](https://github.com/fcyber-labs/ai-engineering-hub/network/members) | [](https://github.com/fcyber-labs/ai-engineering-hub/watchers) |

| 🐛 **Issues** | 🔀 **PRs** | 📦 **Releases** |
|:------------:|:----------:|:---------------:|
| [](https://github.com/fcyber-labs/ai-engineering-hub/issues) | [](https://github.com/fcyber-labs/ai-engineering-hub/pulls) | [](https://github.com/fcyber-labs/ai-engineering-hub/releases) |

| 👥 **Contributors** | 📅 **Last Commit** | 📝 **License** |
|:------------------:|:------------------:|:--------------:|
| [](https://github.com/fcyber-labs/ai-engineering-hub/graphs/contributors) | [](https://github.com/fcyber-labs/ai-engineering-hub/commits/main) | [](https://github.com/fcyber-labs/ai-engineering-hub/blob/main/LICENSE) |

---
[](https://star-history.com/#fcyber-labs/ai-engineering-hub&Date)
---
Built with ❤️ by AI Engineers for AI Engineers

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [fcyber-labs](https://github.com/fcyber-labs)
- **Source:** [fcyber-labs/ai-engineering-hub](https://github.com/fcyber-labs/ai-engineering-hub)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-fcyber-labs-ai-engineering-hub
- Seller: https://agentstack.voostack.com/s/fcyber-labs
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.