An offline AI application for phones and Macs that supports chat, image generation, vision, Whisper speech-to-text, tool calling and local-network servers. It runs on CPU, GPU or NPU, requires no account or API key, and keeps data on the device. A paid Pro tier adds voice mode, custom personas and draft-and-approve actions.
Directory
Search results
Published directory entries matching your search.
Pattern is a web mining module for Python with tools for data mining, natural language processing, machine learning, and network analysis and visualization. The repository is archived and no longer maintained, receiving no further updates, bug fixes or security patches.
Release Insights is the code behind the whattrainisitnow.com dashboard, which shows the status of Firefox Desktop releases, including upcoming release timing, future milestones and main data points for past releases. It parses sources such as hg log, APIs and crashes to derive insights like uplifts per beta and top crash signatures per nightly. It requires PHP and Composer and needs no database or framework.
A Python implementation of Restricted Boltzmann Machines. It lets users initialize an RBM with a chosen number of visible and hidden units, train it on a matrix of training examples, run visible or hidden data, and let the network run freely. It is released under an MIT license.
Spider Suite is an open source web scraping or crawling project for collecting website data.
Telegram-focused OSINT toolbox with resources for researching accounts, channels, and public data.
User Scanner is a two-in-one email and username OSINT suite with native MCP support. It performs deep data extraction from a single email or username, analyzing over 1080 maintained scan vectors, including more than 200 email and 880 username sources. It is intended for security research, investigations, and digital footprinting.
Vega is an AutoML algorithm tool chain developed by Noah's Ark Laboratory. It covers hyperparameter optimization, data augmentation, network architecture search, model compression and fully train functions, and supports PyTorch, TensorFlow and MindSpore backends.
WiFi-Direct-File-Transfer-App is an experimental Android application that enables data sharing between Android 4.0 or higher devices using WiFi Direct connections, without requiring a WiFi access point or existing network infrastructure, hosted as a public repository on GitHub.