Top Finds

Automatic analyzer for logs generated by OBS Studio

ClawBlink : No‑code AI agent builder from chat. Describe an agent in plain English; ClawBlink builds and runs it.

🤖 Automate document indexing and enable intelligent Q&A with this real-time Telegram bot using OpenAI GPT-4 and Pinecone for enhanced user interaction.

🌐 Translate text locally in 55 languages with TranslateGemma CLI, offering flexible models and easy usage across macOS, Linux, and Windows.

Jerry The Customer Service Bot — AI customer service for Shopify. Semantic product search, voice chat, order tracking, revenue attribution. Protected by WonderwallAi.

📝 Extract high-quality Arabic text from PDFs and images with Manazir OCR, a layout-aware framework using multiple models for seamless results.

📊 Detect market regimes by clustering probability distributions using Wasserstein K-means for more accurate financial analysis and insights.

🛠️ Enhance reasoning efficiency in LLMs using AdvPrompt, an iterative framework that optimizes black-box adversarial prompting for better performance.

🚀 Optimize your Diffusion Transformers with Hetu-DiT, a dynamic parallel serving system that reduces latency and enhances GPU utilization.

Empowering Agriculture through smart farm for data visualization, farm management and AI/ML for productivity

🎤 Transform speech to text on Windows with fast, local AI processing. Enjoy seamless recording and automatic integration for effective communication.

🧬 Predict drug interactions with the open-source CYP3A4 system, essential for research, education, and enhancing patient safety in medication management.

🛠️ Refine product specs through multi-model debate, ensuring comprehensive reviews that catch gaps and enhance clarity with Claude Code's active participation.

Real-time SL detection system featuring WebSocket streaming, VideoMAE fine-tuned on WLASL, and LLM-driven semantic disambiguation. Includes a full pipeline for 3D motion capture (JSON/Three.js) and optimized inference for CUDA and DirectML.

🏥 Enhance healthcare with an AI-driven chatbot that provides reliable medical information through advanced Retrieval-Augmented Generation technology.

🎤 Build real-time multimodal conversational AI agents with this open-source framework, enabling seamless interaction and enhancing user experiences.

🌟 Align diffusion processes with detailed human preferences to improve machine learning models for richer, more accurate outputs.

A general-purpose programming language that reads like English

🚛 Detect trucks, classify types, and measure dimensions in images with this intuitive computer vision system using YOLOv8 and OpenCV.

Builds an autonomous AI robot with vision, voice, and decision-making capabilities using Python, PyTorch, and CUDA technology.

DSA-for-ML is a complete repository designed to teach Data Structures and Algorithms from scratch, with a focus on how these concepts are applied in Machine Learning. It includes detailed explanations, step-by-step code examples, complexity analysis, and practical ML applications, making it ideal for beginners and aspiring AI/ML engineers.

🎤 Transform voice questions into SQL queries, executing them directly on PostgreSQL to streamline data retrieval and insights.

🦆 Blazing Fast and highly customizable Github Action to setup a DuckDb runtime

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

A PyTorch image classifier that identifies 5 white blood cell types from microscopy images using a fine-tuned DenseNet-121 model.