Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Offline-first synchronization engine for SQLite and PostgreSQL, built in Rust with column-level CRDTs, authoritative partial replicas, and secure multi- tenancy.

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Open-source Legal AI workspace for evidence-grounded legal drafting, matter analysis and verifiable answers.

Ultra-lightweight, edge-native API Gateway for Go

Memory as state, not search — deterministic, dependency-free memory for AI agents. The memory lives in a Markdown file.

Turn any MCP server into a CLI in one command.

Wiredigg is a comprehensive network analysis tool with advanced security features designed for network administrators, security professionals, and IT enthusiasts. It provides real-time packet capture, protocol analysis, anomaly detection, and threat identification capabilities in a modern, user-friendly interface.

Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and provenance.

Open-source middleware for AI agents — catches mid-run failures,compresses stale context, and grows a reasoning library across runs. Any model, any framework.

An MCP server for dataset generation, fine-tuning, RL, and evaluation of LLMs — directly from your coding agent.

A lightweight and fast C++ library for building MQTT clients and brokers, with support for QoS, authentication, security, persistence, and user/session management.

Lightweight, agent-optimized database CLI with one-shot schema introspection, column profiling, and ERD generation.

MCP-powered memory, policy, and experience layer for safer AI agents.

Sandboxed code execution daemon with enforced memory, CPU, and output limits. JSON API for humans and AI agents.

Open-source Durable Objects for live applications.

No description.

A lightweight desktop application that checks your system's compatibility with Windows 11. Provides detailed analysis of hardware requirements including CPU, RAM, storage, TPM, Secure Boot, and more. Features a user-friendly dark mode interface with comprehensive recommendations to fix compatibility issues.

Face recognition with deep neural networks.

TensorFlow tutorials and code examples for beginners

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (PyTorch) - We released the testing code!

How to use autocomplete on a site created in Flask

DuffyDiff is a modern, user-friendly text comparison tool built with Python and Tkinter. It allows users to easily compare two text files, navigate between differences, and merge content between files.

Fast BPE tokenizer with guaranteed perfect text reconstruction. 2x faster than tiktoken at encoding/decoding while preserving all whitespace and formatting.

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

使用opencv部署DBNet文字检测，包含C++和Python两种版本的实现

A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization

My pytorch implementation of spatial transformer network for deskewing of license plate image dataset

🔥Char detection base on crnn 字符（单字）检测基于CRNN

This repo explains how to train an Object Detector for multiple objects using Tensorflow Object Detection API on Ubuntu 16.04 (GPU)

Transform ONNX model to PyTorch representation

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.

This repository contains Image compression techniques employing various machine learning and deep learning techniques.

slices 3D models from STL files

Keras Implementation of faster-rcnn

ASTER in Pytorch

GitHub repo for my article at https://towardsdatascience.com/indian-car-license-plate-detection-using-yolo-v5-ae2574578175

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

An end-to-end implementation of the MobileNetv2+SSD architecture in Keras from sratch for learning purposes. The dataset is prepared using MNIST images: MNIST images are embedded into a box and the model detects bounding boxes for the numbers and the numbers.

View model summaries in PyTorch!

Programs/ Materials that don't belong to a particular domain and are built for future reference or just for practice

用opencv部署nanodet目标检测，包含C++和Python两种版本程序的实现

Deploy OcrLite in your web browser with ncnn and webassembly

QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.

A Python library for downloading YouTube videos

pytorch, ctpn ,text detection ,ocr,文本检测

Super Resolution of low resolution Images in PyTorch

Deep learning based image denoising using tensorflow/Keras combined with block matching

A simple tool for labeling object bounding boxes in images.

Object localization in images using simple CNNs and Keras

https://github.com/cstack/db_tutorial clone (parts 1-12) written in c++.

Writing a sqlite clone from scratch in C

⚡️ Using NNIE as simple as using ncnn ⚡️

RSA for flutter made with golang for fast performance with support for android, ios, macos, linux, web and hover

Cute library to implement SearchView in a Material Design Approach

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

Pytorch implementation of CRNN (CNN + RNN + CTCLoss) for all language OCR.

Training Convolutional Recurrent Neural Network (CRNN) using PyTorch

Project an image centroid to another image using OpenCV

Multidimensional RNN in Keras Tensorflow

Fast Object Detector for the Jetson Nano

Draft of the fastai book

This is a tool for transforming a model trained with Keras into a Tensorflow Protocol Buffers (.pb). And optimize it for using it with the module Dnn of OpenCV.

This a deep learning program for recognizing the captcha using keras with python.

A Keras implementation of MobileNetV3.

OCR with caffe deep learning framework -> Migrated to tensorflow

Kaggle猫狗大战caffe实现

using the VGG16 to extract the feature of photo and transfer to fit the style photo

No description.

keras-cnn-captcha

Python library for GPGPU on Raspberry Pi

How to train a Keras model to recognize variable length text | DLology

CRNN (CNN+RNN) for OCR using Keras / License Plate Recognition

使用CRNN识别广东移动固定长度四位验证码

Simple image search engine

yolo3 implement by tensorflow， including mobilenet_v1, mobilenet_v2

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

No description.

No description.

Minimal and formal résumé (CV) website template for print, mobile, and desktop. https://bit.ly/2kEzgt8

A Keras implementation of SSD

Face recognition usiong keras and tensorflow

Detours is a software package for monitoring and instrumenting API calls on Windows. It is distributed in source code form.

MobileNet-v2 experimental network description for caffe

Convert a model from TensorFlow to Caffe.

A tensorflow implemention of MobilenetV3

Detects license plate of car and recognizes its characters

How to train a TensorFlow Object Detection Classifier for multiple object detection on Windows

Models and examples built with TensorFlow

Six degrees of separation algorithm along with the PHP implementation

Con questo codice potrai convertire qualsiasi numero in una stringa.Con questo codice si arriva fino al trillione.Chiunque voglia può modificare e aumentare sempre più.

Con questo codice potrai convertire una stringa in morse o viceversa.

This code allows you to enter your equation into infix notation to transform this into postfix notation and calculate the result.

Cloudlets are universal server images for the cloud. They're lightweight, version-controlled, and you can export them to any bootable format known to man: Xen, KVM, Amazon EC2, or just a plain bootable CD.

No description.

Caffe: a fast open framework for deep learning.

Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

A recurrent neural network for generating little stories about images

Implementation of a few computer vision algorithms

These are the codes I used in my youtube videos

CSS library for Instagram filters

Bare bottom simplest example of machine learning in TensorFlow.

No description.

Master the command line, in one page

Socket.IO integration for Flask applications.

OpenCV Python Neural Network Autonomous RC Car

A curated list of awesome iOS ecosystem, including Objective-C and Swift Projects

A curated list of awesome Deep Learning tutorials, projects and communities.

A jQuery plugin to provide simple yet fully customisable pagination.

How search Youtube Video by query

Advanced javaScript color picker and color conversion / calculation (rgb, hsv, hsl, hex, cmyk, cmy, XYZ, Lab, alpha, WCAG 2.0, ...)

Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning

Audio fingerprinting and recognition in Python

Computation using data flow graphs for scalable machine learning

Docker - the open-source application container engine

Various slide menu