Models & systems, shipped.
RAG assistants that turn chats into leads, an AI editor that turns raw footage into YouTube Shorts, open-source image editing, autonomous agents and vision models — each measured by what it does in production.
RAG Lead Assistant — AI chat that answers & captures leads
Retrieval-augmented chat assistant grounded in business knowledge. It answers visitor questions accurately from real documents and captures qualified leads — name, contact and intent — naturally inside the conversation.
AI Shorts Editor — Raw footage to YouTube Shorts
Upload raw clips and a script; the AI understands the video and audio, transcribes the speech, chooses the cuts, and renders vertical YouTube Shorts with animated captions and highlighted keywords.
AI Image Editor — Prompt-driven editing on open-source models
Carvona — an image editing pipeline built entirely on open-source diffusion and segmentation models. Select, remove, replace and restyle parts of an image with plain-language prompts, including professional automotive photo editing.
Nami Agent — Autonomous multi-agent loop
Autonomous workflow engine with dynamic tool-calling, calendar orchestration, and self-correcting agent execution loops.
Buzz Card — Multimodal VLM document parser
Vision-Language pipeline extracting business cards and unstructured documents into CRM entities zero-shot.
Face Anti-Spoofing — Real-time liveness detection
Production biometric security model distinguishing live human faces from 2D photos, masks, and screen replays in real time.
Diffusion Vehicle Studio — Segmentation-guided inpainting
Generative AI pipeline combining YOLOv8 segmentation with ControlNet to generate studio-grade vehicle visual presentations.
Legal AI & RAG Engine — Grounded legal intelligence
Legal intelligence platform indexing Constitution & IPC legal documents with dense vector search for zero-hallucination answers.
Neural Voice Cloning — Speech synthesis
Deep audio synthesis pipeline implementing speaker embeddings and neural vocoders for natural conversational speech.
AI repositories
- 01AI RAG chatbotRetrieval-augmented AI chat assistant that answers from business knowledge and captures leads in the conversation.Python★ 0
- 02CarvonaProfessional AI tools for automotive image editing.TypeScript★ 0
- 03Nami agentNami_agent is an calendar bot for development ai agent any user can access but this testing cases now still working on this Python★ 0
- 04Real Time Face Anti spoofing DetectionReal-Time Face Anti-Spoofing System: A YOLO-based real-time face anti-spoofing and image quality assessment solution with a Streamlit interface. Ideal for biometric authentication and surveillance applications.Python★ 7
- 05Car front Side DetectionIts an Yolov8 Car Front and Car Side detection it uses for production ready live code for bank side car front and car side validation collecting all Python★ 0
- 06jump height estimatorThis project is a real-time jump height estimator built with MediaPipe Pose and OpenCV. It uses a webcam feed to detect and track a person’s movement and estimates how high they jump based on the vertical displacement of their hip landmarks.Python★ 1
- 07Computer Vision Task Defective Product DetectorA Computer Vision-based Defective Product Detector automatically identifies flaws or anomalies in products using image processing and machine learning. It enhances quality control by analyzing visual data in real-time for faster and more accurate defect detection.Jupyter Notebook★ 0
- 08EduPDF Chatbot Ask Your LessonEduPDF Chatbot is an AI-powered app that lets users upload educational PDFs and ask questions about the content. Using RAG with LangChain, FAISS, and LLMs like Gemini, it retrieves relevant text chunks and generates accurate answers through a simple Streamlit UI.Python★ 0