Minecraft Webcam

Real-time face tracking that transforms your webcam feed into a Minecraft character with facial animations. Eyes blink when you blink, mouth opens when you talk.

Features

• Real-time Face Tracking — 30 FPS with 468 facial landmarks via MediaPipe
• Head Movement — Pitch (up/down), yaw (left/right), roll (tilt)
• Facial Animations — Eyes blink automatically, mouth opens when talking
• Custom Skins — Supports any standard Minecraft skin (64x64 format)
• Animated Skin Support — Create custom facial expressions stored in unused texture space
• Virtual Camera Output — Use the avatar in video calls or streaming (via OBS)
• System Tray Integration — Runs minimized while active

Technical Highlights

• MediaPipe Face Mesh — 468 3D facial landmarks
• Minecraft Skin Parser — Exact specification compliance (64x32 and 64x64)
• Perspective-correct rendering — Smooth 60 FPS UI updates
• Unused texture space — Rows 32-40 store custom animations
• Depth sorting — Painter’s algorithm for proper rendering order

Tech Stack

How It Works

1. MediaPipe detects 468 facial landmarks at 30 FPS
2. Head rotation calculated from nose and eye positions
3. Minecraft skin texture mapped to 3D quad with perspective correction
4. Avatar output sent to virtual camera for use in other apps

Browser Automation

An interactive elements analyzer using Playwright that crawls websites, identifies clickable elements, and generates visual reports with color-coded bounding boxes.

Features

• Full Page Screenshot Capture — Complete page screenshots for visual analysis
• Interactive Element Detection — Identifies:
  • Input fields (text, search, email, password)
  • Buttons (native and custom)
  • Links (anchor tags)
  • Custom elements with event listeners
• Event Listener Detection — Heuristically identifies React, Vue, and inline handlers
• Visual Reports — Color-coded bounding boxes:
  • Green: Input fields
  • Red: Buttons
  • Blue: Links
  • Orange: Generic interactive elements
• Structured Output — JSON and text reports with detailed element metadata

Technical Highlights

• Playwright for browser automation (Chromium)
• Pillow + NumPy for image processing and visualization
• JavaScript injection for DOM analysis
• Event listener heuristics for framework detection
• Python for all scripting

Tech Stack

Usage

# Default (YouTube)
python main.py

# Custom URL
python main.py https://example.com

Knowledge Arbitrage

A graph-based filesystem that combines Neo4j’s relationship modeling with LanceDB’s vector search capabilities. Files and directories exist as interconnected nodes, while content is chunked and embedded for semantic querying.

Features

• Graph-Based Storage — Files and directories stored as Neo4j nodes with CONTAINS relationships
• Hierarchical Structure — Traditional filesystem operations (create, read, write, move, delete)
• Semantic Search — LanceDB stores embeddings for content-based querying
• Hybrid Queries — Combine graph traversal with vector similarity
• Text Optimization — Cleans HTML, normalizes formatting, semantic chunking

Technical Highlights

• Neo4j for graph structure and relationship queries
• LanceDB for vector storage and similarity search
• Cohere embed-english-v3.0 for embeddings
• chonkie for semantic text chunking
• FastAPI web framework

Tech Stack

Architecture

Filesystem (Neo4j)          Embeddings (LanceDB)
├── /projects              → chunk_1 → [embedding]
│   └── /notes             → chunk_2 → [embedding]
└── /docs                  → chunk_3 → [embedding]

Query: "show me files about AI projects"
→ Vector search in LanceDB
→ Returns matching chunks with file paths from Neo4j

Pet Face Recognition

A local-first pet registration and identification system using face recognition. No cloud AI dependencies — all processing happens locally with deterministic embeddings.

Features

• Local-Only Architecture — No external cloud APIs; all processing done locally
• Facial Embedding Pipeline — Extracts 256-dimensional feature vectors using classical computer vision:
  • Local Binary Patterns (LBP)
  • Histogram of Oriented Gradients (HOG)
  • Discrete Cosine Transform (DCT)
  • Color histograms (HSV)
  • Multi-scale grid pooling
• pgvector Similarity Search — Efficient vector storage and retrieval in PostgreSQL
• Pet Registration — Upload multiple images per pet with name and location
• Identification — Find matching pets from uploaded images with similarity scoring

Technical Highlights

• Deterministic embeddings — Same image always produces identical features
• Multi-criteria matching — Similarity score + margin between matches + minimum images
• YOLO11 for classification, segmentation, and pose estimation
• Docker Compose for easy local development
• FastAPI backend with React frontend

Tech Stack

Why Local-First?

Running AI locally means no API costs, no privacy concerns, and deterministic results. The system extracts facial features using classical computer vision techniques that are reproducible and don’t depend on external services.

Dynamic RAG

A sophisticated Retrieval-Augmented Generation system with multi-agent architecture for intelligent question-answering over custom knowledge bases.

Features

• Multi-Agent Architecture — Specialized agents working together:
  • QA Agent — Main agent for answering questions using the knowledge base
  • Personal Agent — For personal/general questions not requiring RAG
  • Validation Agent — Classifies queries as on-context, personal, bad, or unknown
  • Prompt Agent — Generates diverse query perspectives for comprehensive retrieval
  • Reranking Agent — Reorders retrieved chunks for better relevance
• Hybrid Search — Combines FAISS vector similarity with keyword matching
• Streaming Responses — Token-by-token streaming of LLM outputs
• Multi-language Support — Uses multilingual embeddings via Cohere
• Document Processing — PDF parsing with OCR support via Mistral

Technical Highlights

• LangChain + LangGraph for orchestrating the RAG pipeline
• FAISS vector store for similarity search
• Cohere embeddings for multilingual support
• SQLite for session persistence and analytics
• Configurable agents via JSON configuration files

Tech Stack

Architecture

ValidationAgent → classifies query type
       ↓
PromptAgent → generates specialized prompts
       ↓
QA Agent → retrieves chunks, reranks, generates answer
       ↓
StreamingResponse