🔥 discordo | Go
🎯 Primary Use Case:
Accessing and interacting with Discord through a terminal interface.
✨ Key Features:
• Lightweight
• Configurable
• Mouse & clipboard support
• Attachments
• Notifications
📖 Summary:
Discordo is a lightweight, secure, and feature-rich terminal-based Discord client. It aims to provide a configurable and efficient way to access Discord through a terminal user interface, supporting features like attachments, notifications, and 2-Factor authentication.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Accessing and interacting with Discord through a terminal interface.
✨ Key Features:
• Lightweight
• Configurable
• Mouse & clipboard support
• Attachments
• Notifications
📖 Summary:
Discordo is a lightweight, secure, and feature-rich terminal-based Discord client. It aims to provide a configurable and efficient way to access Discord through a terminal user interface, supporting features like attachments, notifications, and 2-Factor authentication.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 blurr | Kotlin
🎯 Primary Use Case:
Automating tasks on Android devices using natural language commands.
✨ Key Features:
• Intelligent UI Automation using Android Accessibility Service
• High-quality voice using GCS's Chirp
• Multi-agent system architecture written in Kotlin
• LLM-powered reasoning and planning
📖 Summary:
The repository provides an AI agent named Panda for Android that can autonomously understand natural language commands and operate a phone's UI. It uses the Android Accessibility Service to interact with the device and LLMs for high-level reasoning and planning, enabling automation of complex, multi-step tasks across different applications.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Automating tasks on Android devices using natural language commands.
✨ Key Features:
• Intelligent UI Automation using Android Accessibility Service
• High-quality voice using GCS's Chirp
• Multi-agent system architecture written in Kotlin
• LLM-powered reasoning and planning
📖 Summary:
The repository provides an AI agent named Panda for Android that can autonomously understand natural language commands and operate a phone's UI. It uses the Android Accessibility Service to interact with the device and LLMs for high-level reasoning and planning, enabling automation of complex, multi-step tasks across different applications.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 protector | Python
🎯 Primary Use Case:
Real-time privacy protection for smart glasses applications.
✨ Key Features:
• Anonymizes faces (blur or solid ellipse masking)
• Manages consent (voice detection)
• Real-time processing (720p 30fps)
• 100% offline operation
• Recording
📖 Summary:
The repository provides a real-time privacy protection layer for smart glasses applications. It filters camera input, anonymizes faces, manages consent through voice detection, and outputs a compliant video stream. This allows developers to build privacy-conscious AI, social, and enterprise applications using smart glasses.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Real-time privacy protection for smart glasses applications.
✨ Key Features:
• Anonymizes faces (blur or solid ellipse masking)
• Manages consent (voice detection)
• Real-time processing (720p 30fps)
• 100% offline operation
• Recording
📖 Summary:
The repository provides a real-time privacy protection layer for smart glasses applications. It filters camera input, anonymizes faces, manages consent through voice detection, and outputs a compliant video stream. This allows developers to build privacy-conscious AI, social, and enterprise applications using smart glasses.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 tiktokenizer | TypeScript
🎯 Primary Use Case:
Calculating the number of tokens for a given prompt to optimize usage of OpenAI models.
✨ Key Features:
• Online playground
• Token calculation for prompts
• Integration with openai/tiktoken
• Built with T3 Stack
📖 Summary:
The Tiktokenizer repository is an online playground for the `openai/tiktoken` library. It allows users to calculate the number of tokens required for a given prompt, which is crucial for working with OpenAI models and managing API costs. The project is built using the T3 Stack and is sponsored by Diagram.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Calculating the number of tokens for a given prompt to optimize usage of OpenAI models.
✨ Key Features:
• Online playground
• Token calculation for prompts
• Integration with openai/tiktoken
• Built with T3 Stack
📖 Summary:
The Tiktokenizer repository is an online playground for the `openai/tiktoken` library. It allows users to calculate the number of tokens required for a given prompt, which is crucial for working with OpenAI models and managing API costs. The project is built using the T3 Stack and is sponsored by Diagram.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 noisedash | JavaScript
🎯 Primary Use Case:
Creating and customizing ambient noise soundscapes for relaxation, focus, or other purposes.
✨ Key Features:
• Generate and customize ambient noises using Tone.js
• Save, import, and export noise profiles
• Fine-tune noises with audio processing tools (filters, LFOs, effects)
• Upload and edit audio samples
📖 Summary:
Noisedash is a self-hostable web application designed for generating and customizing ambient noises. It allows users to create personalized soundscapes by combining generated noises with uploaded audio samples, applying audio processing effects, and saving noise profiles for easy access and sharing. The application also includes admin tools for managing multiple users and is designed to be mobile-friendly.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Creating and customizing ambient noise soundscapes for relaxation, focus, or other purposes.
✨ Key Features:
• Generate and customize ambient noises using Tone.js
• Save, import, and export noise profiles
• Fine-tune noises with audio processing tools (filters, LFOs, effects)
• Upload and edit audio samples
📖 Summary:
Noisedash is a self-hostable web application designed for generating and customizing ambient noises. It allows users to create personalized soundscapes by combining generated noises with uploaded audio samples, applying audio processing effects, and saving noise profiles for easy access and sharing. The application also includes admin tools for managing multiple users and is designed to be mobile-friendly.
🔗 Links:
• View Project
================
🔓 Open Source
🌟 receipthero | TypeScript
🎯 Primary Use Case:
Organizing and managing receipts with AI-powered data extraction and categorization.
✨ Key Features:
• AI-powered OCR using Together AI
• Data extraction (vendor, date, amount, items, currency, payment method)
• Automatic expense categorization
• Local data storage for privacy
• Spending breakdown visualization
📖 Summary:
ReceiptHero is an open-source receipt management application that uses AI-powered OCR to extract data from receipt images. It allows users to upload receipts, automatically categorize expenses, and view spending breakdowns, storing data locally for privacy.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Organizing and managing receipts with AI-powered data extraction and categorization.
✨ Key Features:
• AI-powered OCR using Together AI
• Data extraction (vendor, date, amount, items, currency, payment method)
• Automatic expense categorization
• Local data storage for privacy
• Spending breakdown visualization
📖 Summary:
ReceiptHero is an open-source receipt management application that uses AI-powered OCR to extract data from receipt images. It allows users to upload receipts, automatically categorize expenses, and view spending breakdowns, storing data locally for privacy.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
✨ Code2Video | Python
🎯 Primary Use Case:
Generating educational videos based on code execution and logic.
✨ Key Features:
• Video generation from code
• Educational video creation
• Code-centric paradigm
• Multi-agent system utilization (implied)
📖 Summary:
Code2Video is a project focused on generating educational videos from code. It presents a code-centric paradigm for creating teaching videos, potentially leveraging multi-agent systems to automate the video creation process. The project provides resources such as a paper, dataset, and project website for further exploration.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Generating educational videos based on code execution and logic.
✨ Key Features:
• Video generation from code
• Educational video creation
• Code-centric paradigm
• Multi-agent system utilization (implied)
📖 Summary:
Code2Video is a project focused on generating educational videos from code. It presents a code-centric paradigm for creating teaching videos, potentially leveraging multi-agent systems to automate the video creation process. The project provides resources such as a paper, dataset, and project website for further exploration.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 doomscroll-detector | Python
🎯 Primary Use Case:
Detecting and discouraging doomscrolling behavior.
✨ Key Features:
• YOLOv11 pose estimation for keypoint tracking
• YOLO object detection for phone detection
• Heuristics for detecting reclined posture based on hip/shoulder alignment
• Heuristics for detecting phone holding based on wrist proximity
• Overlay of results on webcam feed with a spoofed penalty counter
📖 Summary:
The Doomscrolling Detector is a computer vision pipeline that identifies when a user is reclined and using their phone, indicative of doomscrolling behavior. It uses pose estimation and object detection to flag these instances, and includes a spoofed penalty counter as a humorous deterrent.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Detecting and discouraging doomscrolling behavior.
✨ Key Features:
• YOLOv11 pose estimation for keypoint tracking
• YOLO object detection for phone detection
• Heuristics for detecting reclined posture based on hip/shoulder alignment
• Heuristics for detecting phone holding based on wrist proximity
• Overlay of results on webcam feed with a spoofed penalty counter
📖 Summary:
The Doomscrolling Detector is a computer vision pipeline that identifies when a user is reclined and using their phone, indicative of doomscrolling behavior. It uses pose estimation and object detection to flag these instances, and includes a spoofed penalty counter as a humorous deterrent.
🔗 Links:
• View Project
================
🔓 Open Source
💡 WZML-X | Python
🎯 Primary Use Case:
Mirroring and cloning files from various online sources to different cloud storage platforms or Telegram.
✨ Key Features:
• qBittorrent support with file selection and seeding options
• Aria2c integration with file selection, netrc support, and authentication
• Telegram upload/download with file splitting, thumbnail support, and leech options
• Support for uploading files to specific Telegram supergroups
📖 Summary:
WZML-X is a Telegram bot built with Pyrogram that enhances file mirroring and cloning capabilities. It supports downloading from various sources like torrents, Mega, Google Drive, and direct links, then uploading to Google Drive, Telegram, Rclone clouds, or DDL servers.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Mirroring and cloning files from various online sources to different cloud storage platforms or Telegram.
✨ Key Features:
• qBittorrent support with file selection and seeding options
• Aria2c integration with file selection, netrc support, and authentication
• Telegram upload/download with file splitting, thumbnail support, and leech options
• Support for uploading files to specific Telegram supergroups
📖 Summary:
WZML-X is a Telegram bot built with Pyrogram that enhances file mirroring and cloning capabilities. It supports downloading from various sources like torrents, Mega, Google Drive, and direct links, then uploading to Google Drive, Telegram, Rclone clouds, or DDL servers.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🌟 UpUp | JavaScript
🎯 Primary Use Case:
Providing offline access to website content for users with intermittent or no internet connectivity.
✨ Key Features:
• Offline functionality using service workers
• Simple JavaScript API for configuration
• Control over offline content
• Browser support for Chrome, Opera, and Firefox (with service worker support)
📖 Summary:
UpUp is a JavaScript library that enables offline functionality for websites by utilizing service workers. It allows developers to specify content to be displayed when users are offline, ensuring a consistent user experience even without an internet connection. The library is designed to be easy to implement, requiring only a few lines of JavaScript to configure.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Providing offline access to website content for users with intermittent or no internet connectivity.
✨ Key Features:
• Offline functionality using service workers
• Simple JavaScript API for configuration
• Control over offline content
• Browser support for Chrome, Opera, and Firefox (with service worker support)
📖 Summary:
UpUp is a JavaScript library that enables offline functionality for websites by utilizing service workers. It allows developers to specify content to be displayed when users are offline, ensuring a consistent user experience even without an internet connection. The library is designed to be easy to implement, requiring only a few lines of JavaScript to configure.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 duplicati | C#
🎯 Primary Use Case:
Securely backing up data to cloud storage services.
✨ Key Features:
• AES-256 encryption
• Incremental backups
• Built-in scheduler
• Support for multiple cloud storage services (Amazon S3, Google Drive, WebDAV, etc.)
• Command-line and GUI interface
📖 Summary:
Duplicati is a free, open-source backup client written in C# that securely stores encrypted, incremental, and compressed backups on cloud storage services and remote file servers. It supports various destinations like Amazon S3, Google Drive, and WebDAV, and offers features like AES-256 encryption, a built-in scheduler, and flexible backup options.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Securely backing up data to cloud storage services.
✨ Key Features:
• AES-256 encryption
• Incremental backups
• Built-in scheduler
• Support for multiple cloud storage services (Amazon S3, Google Drive, WebDAV, etc.)
• Command-line and GUI interface
📖 Summary:
Duplicati is a free, open-source backup client written in C# that securely stores encrypted, incremental, and compressed backups on cloud storage services and remote file servers. It supports various destinations like Amazon S3, Google Drive, and WebDAV, and offers features like AES-256 encryption, a built-in scheduler, and flexible backup options.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 lmms | C++
🎯 Primary Use Case:
Music production, including composing, arranging, and mixing audio tracks.
✨ Key Features:
• Song-Editor for arranging melodies, samples, patterns, and automation
• Pattern-Editor for creating beats and patterns
• Piano-Roll for editing patterns and melodies
• Mixer with unlimited mixer channels and arbitrary number of effects
• Many powerful instrument and effect-plugins out of the box
📖 Summary:
LMMS is a free, open-source, cross-platform digital audio workstation (DAW) software. It provides tools for music production, including composing, arranging, and mixing, with features like a Song Editor, Pattern Editor, Piano Roll, and Mixer, along with support for various plugins and standards.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Music production, including composing, arranging, and mixing audio tracks.
✨ Key Features:
• Song-Editor for arranging melodies, samples, patterns, and automation
• Pattern-Editor for creating beats and patterns
• Piano-Roll for editing patterns and melodies
• Mixer with unlimited mixer channels and arbitrary number of effects
• Many powerful instrument and effect-plugins out of the box
📖 Summary:
LMMS is a free, open-source, cross-platform digital audio workstation (DAW) software. It provides tools for music production, including composing, arranging, and mixing, with features like a Song Editor, Pattern Editor, Piano Roll, and Mixer, along with support for various plugins and standards.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source