Top Finds

A powerful FastAPI-based multi-modal ingestion system that processes PDFs, scanned documents, images, videos, YouTube links, and text files — then optionally performs semantic retrieval using FAISS + HuggingFace embeddings and refines answers using an LLM (Ollama via NPMAI).

Trying to train agents to play Liar's dice with DDQN and masking.

Production-ready framework for training robust computer vision models. Features multi-GPU support, EMA tracking, label smoothing, and comprehensive robustness evaluation across 4 noise types. Includes scalable TF.Data pipeline, automated testing, Docker support, and CLI tools. Install: pip install robust-vision

NvAPI functionality for talking to Nvidia GPUs in vvvv gamma

A small collection of mini-projects for viewers to learn from.

🛠️ Generate AI framework prompts effortlessly with `ai-prompt-ppt`, using 20 case studies to enhance accuracy and relevance for your projects.

🔄 Build dynamic programs with the WHEN Language, a unique loop-based language that simplifies execution through implicit loops and conditional logic.

Professional project by Gabriel Demetrios Lafis

🕰️ Analyze Hacker News from a decade ago to uncover predictions and insights, evaluating comments with an LLM for deeper understanding and context.

A Python based frontend Ai chat interface powered by the Sarvam AI API

🤖 Transform natural language into cron expressions effortlessly with AI, ensuring privacy and flexibility through local and cloud model support.

Google Gemini API integration showcase — multimodal inference (text, image, audio), function calling, system prompt engineering, streaming output, and multi-turn demos.

🎮 Enhance your gaming skills with an AI chatbot that delivers real-time strategies and coaching for 9+ popular competitive games.

🗺️ Map and document your codebase effortlessly with Cartographer, a Claude Code plugin that uses parallel AI to analyze and synthesize code insights.

Global Power Plant Database Analysis is a Streamlit-based interactive web app designed to explore and analyze worldwide energy generation data

AI-powered resume analyzer that evaluates resumes against job descriptions with ATS scoring, skill detection, and improvement suggestions.

An interactive reinforcement learning project where agents trained using Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) play Atari's classic Space Invaders. The project includes a Streamlit app to visualize and compare the performance of both agents.

Visual speech recognition using deep learning — lip reading without audio

A curated collection of advanced computer vision projects built using OpenCV, Python, and modern CV techniques. This repository serves as a growing hub for experimental, research-oriented, and real‑world computer vision applications.

🔍 Enhance reasoning in Large Language Models with DeepRWKV-Reasoning, using advanced Monte Carlo Tree Search for robust solutions.

🔬 Enhance your experiments with SciAgent, an AI-powered tool for automatic tracking, intelligent analysis, and local storage—all without altering your code.

🛡️ Detect phishing emails in Gmail using machine learning for real-time protection, ensuring your inbox stays safe and secure.

🚀 Automate SEO article creation and publishing in WordPress with tools for research, content generation, optimization, and quality control.

Automated financial prediction tracking & verification using Korean macro data and LLM analysis

An AI powered Bash Shell that is perfect for people who are using it for the first time.