💡 alt-sendme | TypeScript
🎯 Primary Use Case:
Direct, secure, and private file transfer between users without relying on cloud services.
✨ Key Features:
• Send anywhere (local networks or across continents)
• Transfer anything (any size, any format, verified with BLAKE3)
• No accounts or personal info required
• Peer-to-peer direct transfer
• End-to-end encryption (QUIC + TLS 1.3)
📖 Summary:
Alt-Sendme is a free, open-source file transfer tool that enables direct peer-to-peer file and folder sharing of any size or format. It prioritizes privacy and security through end-to-end encryption and avoids cloud storage, accounts, or personal information requirements.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Direct, secure, and private file transfer between users without relying on cloud services.
✨ Key Features:
• Send anywhere (local networks or across continents)
• Transfer anything (any size, any format, verified with BLAKE3)
• No accounts or personal info required
• Peer-to-peer direct transfer
• End-to-end encryption (QUIC + TLS 1.3)
📖 Summary:
Alt-Sendme is a free, open-source file transfer tool that enables direct peer-to-peer file and folder sharing of any size or format. It prioritizes privacy and security through end-to-end encryption and avoids cloud storage, accounts, or personal information requirements.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
❤1
🌟 ODM | Python
🎯 Primary Use Case:
Processing aerial drone imagery to create detailed 2D and 3D geospatial products for applications such as mapping, surveying, and environmental monitoring.
✨ Key Features:
• Generates classified point clouds
• Creates 3D textured models
• Produces georeferenced orthorectified imagery
• Generates georeferenced digital elevation models
• Command-line interface for scripting and integration
📖 Summary:
ODM is an open-source command-line toolkit for processing aerial drone imagery. It converts 2D drone images into various geospatial products like classified point clouds, 3D textured models, orthorectified imagery, and digital elevation models.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Processing aerial drone imagery to create detailed 2D and 3D geospatial products for applications such as mapping, surveying, and environmental monitoring.
✨ Key Features:
• Generates classified point clouds
• Creates 3D textured models
• Produces georeferenced orthorectified imagery
• Generates georeferenced digital elevation models
• Command-line interface for scripting and integration
📖 Summary:
ODM is an open-source command-line toolkit for processing aerial drone imagery. It converts 2D drone images into various geospatial products like classified point clouds, 3D textured models, orthorectified imagery, and digital elevation models.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
❤1
🌟 AI-Text-Humanizer-App | Python
🎯 Primary Use Case:
To convert AI-generated text into human-like, academic writing that can bypass AI detection.
✨ Key Features:
• AI-Powered Text Refinement
• Expand Contractions
• Add Academic Transitions
• Passive Voice Conversion (Optional)
• Synonym Replacement (Optional)
📖 Summary:
This Python application, built with Streamlit, transforms AI-generated or informal text into formal, human-like, and academic writing. It offers features like expanding contractions, adding academic transitions, and optional synonym replacement to help bypass AI detectors and improve text quality.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To convert AI-generated text into human-like, academic writing that can bypass AI detection.
✨ Key Features:
• AI-Powered Text Refinement
• Expand Contractions
• Add Academic Transitions
• Passive Voice Conversion (Optional)
• Synonym Replacement (Optional)
📖 Summary:
This Python application, built with Streamlit, transforms AI-generated or informal text into formal, human-like, and academic writing. It offers features like expanding contractions, adding academic transitions, and optional synonym replacement to help bypass AI detectors and improve text quality.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 LongCat-Video | Python
🎯 Primary Use Case:
Generating high-quality, long videos from text, images, or by continuing existing video content.
✨ Key Features:
• Unified architecture for Text-to-Video, Image-to-Video, and Video-Continuation
• Natively pretrained for long video generation (minutes-long) without quality degradation
• Efficient inference for 720p, 30fps videos using coarse-to-fine strategy and Block Sparse Attention
• Strong performance achieved through multi-reward RLHF (GRPO)
📖 Summary:
LongCat-Video is a 13.6B parameter foundational video generation model capable of Text-to-Video, Image-to-Video, and Video-Continuation tasks. It is particularly optimized for efficient, high-quality generation of long videos, aiming to be a step towards world models.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Generating high-quality, long videos from text, images, or by continuing existing video content.
✨ Key Features:
• Unified architecture for Text-to-Video, Image-to-Video, and Video-Continuation
• Natively pretrained for long video generation (minutes-long) without quality degradation
• Efficient inference for 720p, 30fps videos using coarse-to-fine strategy and Block Sparse Attention
• Strong performance achieved through multi-reward RLHF (GRPO)
📖 Summary:
LongCat-Video is a 13.6B parameter foundational video generation model capable of Text-to-Video, Image-to-Video, and Video-Continuation tasks. It is particularly optimized for efficient, high-quality generation of long videos, aiming to be a step towards world models.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 claude-usage | Python
🎯 Primary Use Case:
To provide users with a local, detailed dashboard for monitoring and analyzing their Claude Code token usage and associated costs.
✨ Key Features:
• Tracks token usage (input, output, cache)
• Logs session history, models, and projects
• Estimates costs based on usage
• Provides a web-based dashboard with charts
• Works with API, Pro, and Max plans
📖 Summary:
This Python repository provides a local dashboard to visualize and track your Claude Code token usage, session history, and estimated costs. It works by parsing local log files generated by Claude Code, offering insights beyond what the official UI provides, and is compatible with API, Pro, and Max plans.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To provide users with a local, detailed dashboard for monitoring and analyzing their Claude Code token usage and associated costs.
✨ Key Features:
• Tracks token usage (input, output, cache)
• Logs session history, models, and projects
• Estimates costs based on usage
• Provides a web-based dashboard with charts
• Works with API, Pro, and Max plans
📖 Summary:
This Python repository provides a local dashboard to visualize and track your Claude Code token usage, session history, and estimated costs. It works by parsing local log files generated by Claude Code, offering insights beyond what the official UI provides, and is compatible with API, Pro, and Max plans.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 metrics | JavaScript
🎯 Primary Use Case:
To create and display personalized, visually appealing statistics about a GitHub user's activity and contributions directly within their profile README or other web content.
✨ Key Features:
• Infographics generator for GitHub statistics
• 30+ plugins and 335+ options for customization
• Supports users, organizations, and repositories
• Renders metrics as SVG, Markdown, PDF, or JSON
• Embeddable in GitHub profile readmes
📖 Summary:
Metrics is a JavaScript-based tool that generates customizable infographics displaying GitHub account statistics. It offers over 30 plugins and 300 options to visualize data such as contributions, languages, and stargazers, rendering them as SVG, Markdown, PDF, or JSON.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To create and display personalized, visually appealing statistics about a GitHub user's activity and contributions directly within their profile README or other web content.
✨ Key Features:
• Infographics generator for GitHub statistics
• 30+ plugins and 335+ options for customization
• Supports users, organizations, and repositories
• Renders metrics as SVG, Markdown, PDF, or JSON
• Embeddable in GitHub profile readmes
📖 Summary:
Metrics is a JavaScript-based tool that generates customizable infographics displaying GitHub account statistics. It offers over 30 plugins and 300 options to visualize data such as contributions, languages, and stargazers, rendering them as SVG, Markdown, PDF, or JSON.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 open-wearables | Python
🎯 Primary Use Case:
To provide a unified API and self-hosted platform for developers and individuals to aggregate, manage, and analyze health data from diverse wearable devices, enabling faster development of health applications and personalized health insights.
✨ Key Features:
• Unified API for multiple wearable providers
📖 Summary:
Open Wearables is an open-source, self-hosted platform designed to unify health data from various wearable devices into a single, AI-ready API. It simplifies the process for developers and individuals to access, manage, and derive insights from their health metrics, offering a unified interface instead of managing multiple device-specific integrations.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To provide a unified API and self-hosted platform for developers and individuals to aggregate, manage, and analyze health data from diverse wearable devices, enabling faster development of health applications and personalized health insights.
✨ Key Features:
• Unified API for multiple wearable providers
📖 Summary:
Open Wearables is an open-source, self-hosted platform designed to unify health data from various wearable devices into a single, AI-ready API. It simplifies the process for developers and individuals to access, manage, and derive insights from their health metrics, offering a unified interface instead of managing multiple device-specific integrations.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 nano11 | PowerShell
🎯 Primary Use Case:
Creating a minimal, static Windows 11 environment for testing, development, or embedded use in virtual machines.
✨ Key Features:
• Automates the build of a streamlined Windows 11 image using PowerShell.
• Utilizes only built-in DISM capabilities and oscdimg.exe.
• Creates a bootable ISO with no external binaries.
• Includes an unattended answer file to bypass Microsoft Account requirement and enable compact installation.
📖 Summary:
nano11 is a PowerShell script that automates the creation of a highly streamlined Windows 11 ISO image. It aggressively removes non-essential components, apps, and services to achieve a significantly smaller footprint, making it suitable for testing, development, or embedded use cases in virtual machines.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Creating a minimal, static Windows 11 environment for testing, development, or embedded use in virtual machines.
✨ Key Features:
• Automates the build of a streamlined Windows 11 image using PowerShell.
• Utilizes only built-in DISM capabilities and oscdimg.exe.
• Creates a bootable ISO with no external binaries.
• Includes an unattended answer file to bypass Microsoft Account requirement and enable compact installation.
📖 Summary:
nano11 is a PowerShell script that automates the creation of a highly streamlined Windows 11 ISO image. It aggressively removes non-essential components, apps, and services to achieve a significantly smaller footprint, making it suitable for testing, development, or embedded use cases in virtual machines.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 video2x | C++
🎯 Primary Use Case:
Upscaling low-resolution videos and increasing the frame rate of existing videos using AI for improved visual quality.
✨ Key Features:
• Machine learning-based video super resolution
• Machine learning-based frame interpolation
• Rewrite in C/C++ for speed and efficiency
• Cross-platform support (Windows, Linux)
• Support for Anime4K v4, Real-ESRGAN, Real-CUGAN, RIFE
📖 Summary:
Video2X is a C++ framework for enhancing video quality through machine learning. It offers super-resolution to upscale video resolution and frame interpolation to increase frame rates, utilizing advanced AI models and GPU acceleration.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Upscaling low-resolution videos and increasing the frame rate of existing videos using AI for improved visual quality.
✨ Key Features:
• Machine learning-based video super resolution
• Machine learning-based frame interpolation
• Rewrite in C/C++ for speed and efficiency
• Cross-platform support (Windows, Linux)
• Support for Anime4K v4, Real-ESRGAN, Real-CUGAN, RIFE
📖 Summary:
Video2X is a C++ framework for enhancing video quality through machine learning. It offers super-resolution to upscale video resolution and frame interpolation to increase frame rates, utilizing advanced AI models and GPU acceleration.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🌟 CloudPaste | JavaScript
🎯 Primary Use Case:
To provide a flexible, self-hosted, and serverless platform for managing and sharing files and text across various cloud storage providers, with integrated editing and preview capabilities.
✨ Key Features:
• Serverless architecture with Cloudflare Workers, Workflow, and D1
• Support for multiple storage backends including S3-compatible, WebDAV, OneDrive, Google Drive, Telegram, HuggingFace, and GitHub
📖 Summary:
CloudPaste is a serverless, self-hosted file management and text-sharing tool that aggregates multiple storage services. It offers a built-in Markdown editor, supports over 30 file format previews, and can be deployed via Cloudflare Workers or Docker.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To provide a flexible, self-hosted, and serverless platform for managing and sharing files and text across various cloud storage providers, with integrated editing and preview capabilities.
✨ Key Features:
• Serverless architecture with Cloudflare Workers, Workflow, and D1
• Support for multiple storage backends including S3-compatible, WebDAV, OneDrive, Google Drive, Telegram, HuggingFace, and GitHub
📖 Summary:
CloudPaste is a serverless, self-hosted file management and text-sharing tool that aggregates multiple storage services. It offers a built-in Markdown editor, supports over 30 file format previews, and can be deployed via Cloudflare Workers or Docker.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 logo-generator-skill | HTML
🎯 Primary Use Case:
Quickly generating professional, high-quality logos and presentation-ready showcase images for startups, developers, designers, and product teams.
✨ Key Features:
• SVG Logo Generation (dot matrix, line systems, mixed compositions)
• Design Variety (6+ distinct variants per request)
• Professional Showcase (12 curated background styles)
• Nano Banana Integration (Gemini 3.1 Flash Image Preview)
• Interactive HTML Previews
📖 Summary:
This repository provides a professional SVG logo generator that creates multiple design variants based on product characteristics. It also generates high-end showcase images with various professional background styles, leveraging Gemini 3.1 Flash Image Preview for refined presentations.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Quickly generating professional, high-quality logos and presentation-ready showcase images for startups, developers, designers, and product teams.
✨ Key Features:
• SVG Logo Generation (dot matrix, line systems, mixed compositions)
• Design Variety (6+ distinct variants per request)
• Professional Showcase (12 curated background styles)
• Nano Banana Integration (Gemini 3.1 Flash Image Preview)
• Interactive HTML Previews
📖 Summary:
This repository provides a professional SVG logo generator that creates multiple design variants based on product characteristics. It also generates high-end showcase images with various professional background styles, leveraging Gemini 3.1 Flash Image Preview for refined presentations.
🔗 Links:
• View Project
================
🔓 Open Source
🌟 mxFind | Rust
🎯 Primary Use Case:
Discovering and searching public Matrix chat rooms across different homeservers.
✨ Key Features:
• Search public Matrix rooms via `/_matrix/client/v3/publicRooms`
• Query multiple configured homeservers
• Store room metadata in a local SQLite index
• Use local search by default when the database exists
• Force live search when needed
📖 Summary:
mxfind is a Rust-based command-line and terminal UI tool designed to discover public Matrix chat rooms. It allows users to query multiple Matrix homeservers, build a local SQLite index for fast searching, and output results in both human-readable and machine-readable JSON formats.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Discovering and searching public Matrix chat rooms across different homeservers.
✨ Key Features:
• Search public Matrix rooms via `/_matrix/client/v3/publicRooms`
• Query multiple configured homeservers
• Store room metadata in a local SQLite index
• Use local search by default when the database exists
• Force live search when needed
📖 Summary:
mxfind is a Rust-based command-line and terminal UI tool designed to discover public Matrix chat rooms. It allows users to query multiple Matrix homeservers, build a local SQLite index for fast searching, and output results in both human-readable and machine-readable JSON formats.
🔗 Links:
• View Project
================
🔓 Open Source
✨ ccpocket | Dart
🎯 Primary Use Case:
Enabling developers to remotely control and interact with AI coding agents (like Codex and Claude) from their mobile devices or desktops, facilitating a more flexible and accessible development workflow.
✨ Key Features:
• Control Codex and Claude coding agents from mobile and desktop
• Remote session management and action approval
• Cross-device context persistence
📖 Summary:
CC Pocket is a mobile and desktop application that allows users to control coding agent sessions (Codex and Claude) remotely via a self-hosted WebSocket bridge server. It enables users to start, manage, and approve agent actions from their phone, tablet, or desktop, offering a seamless coding experience across devices.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Enabling developers to remotely control and interact with AI coding agents (like Codex and Claude) from their mobile devices or desktops, facilitating a more flexible and accessible development workflow.
✨ Key Features:
• Control Codex and Claude coding agents from mobile and desktop
• Remote session management and action approval
• Cross-device context persistence
📖 Summary:
CC Pocket is a mobile and desktop application that allows users to control coding agent sessions (Codex and Claude) remotely via a self-hosted WebSocket bridge server. It enables users to start, manage, and approve agent actions from their phone, tablet, or desktop, offering a seamless coding experience across devices.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🌟 docker-pi-hole | Shell
🎯 Primary Use Case:
To provide a simple and reliable way to deploy Pi-hole as a network-wide ad blocker using Docker.
✨ Key Features:
• Official Pi-hole Docker image
• Network-wide ad blocking
• DNS sinkhole functionality
• Easy deployment with Docker Compose
• Customizable environment variables for configuration
📖 Summary:
This repository provides the official Docker image for Pi-hole, a network-wide ad blocker and DNS sinkhole. It allows users to easily deploy Pi-hole in a containerized environment for efficient ad blocking across their entire network.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To provide a simple and reliable way to deploy Pi-hole as a network-wide ad blocker using Docker.
✨ Key Features:
• Official Pi-hole Docker image
• Network-wide ad blocking
• DNS sinkhole functionality
• Easy deployment with Docker Compose
• Customizable environment variables for configuration
📖 Summary:
This repository provides the official Docker image for Pi-hole, a network-wide ad blocker and DNS sinkhole. It allows users to easily deploy Pi-hole in a containerized environment for efficient ad blocking across their entire network.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🌟 mgrep | TypeScript
🎯 Primary Use Case:
To provide a natural language interface for searching and retrieving information from local files and the web, particularly useful for developers and AI agents.
✨ Key Features:
• Natural-language search
• Semantic, multilingual, and multimodal search capabilities
• Built-in web search (--web)
• Background indexing with `mgrep watch`
• Friendly device-login flow
📖 Summary:
mgrep is a command-line tool that enables semantic searching across various file types, including code, text, and PDFs, using natural language queries. It features background indexing, web search integration, and is designed for both human and agent use, aiming to reduce token usage for AI agents.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To provide a natural language interface for searching and retrieving information from local files and the web, particularly useful for developers and AI agents.
✨ Key Features:
• Natural-language search
• Semantic, multilingual, and multimodal search capabilities
• Built-in web search (--web)
• Background indexing with `mgrep watch`
• Friendly device-login flow
📖 Summary:
mgrep is a command-line tool that enables semantic searching across various file types, including code, text, and PDFs, using natural language queries. It features background indexing, web search integration, and is designed for both human and agent use, aiming to reduce token usage for AI agents.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 ESP32-Bit-Pirate | C++
🎯 Primary Use Case:
Hardware hacking and digital protocol analysis
✨ Key Features:
• Interactive CLI via USB Serial or WiFi Web
• Support for numerous protocols (I2C, SPI, UART, 1-Wire, CAN, Wi-Fi, Bluetooth, RFID, etc.)
• Protocol sniffers for I2C, UART, SPI, 1Wire, 2wire, CAN, Wi-Fi, Bluetooth, SubGhz
• EEPROM dump tools
• Scripting using Bus Pirate-style commands
📖 Summary:
ESP32 Bit Pirate is an open-source firmware that transforms an ESP32 device into a versatile hardware hacking tool. It supports a wide array of digital and radio protocols, offering features like sniffing, sending, scripting, and interactive control via a web-based CLI.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Hardware hacking and digital protocol analysis
✨ Key Features:
• Interactive CLI via USB Serial or WiFi Web
• Support for numerous protocols (I2C, SPI, UART, 1-Wire, CAN, Wi-Fi, Bluetooth, RFID, etc.)
• Protocol sniffers for I2C, UART, SPI, 1Wire, 2wire, CAN, Wi-Fi, Bluetooth, SubGhz
• EEPROM dump tools
• Scripting using Bus Pirate-style commands
📖 Summary:
ESP32 Bit Pirate is an open-source firmware that transforms an ESP32 device into a versatile hardware hacking tool. It supports a wide array of digital and radio protocols, offering features like sniffing, sending, scripting, and interactive control via a web-based CLI.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 app-store-screenshots | TypeScript
🎯 Primary Use Case:
Automating the creation of professional, marketing-ready App Store and Google Play screenshots using AI.
✨ Key Features:
• AI-powered screenshot generation for App Store and Google Play
• Connected canvas editor for seamless element spanning
• Real device frames for iOS, iPad, Android, and Play Store formats
📖 Summary:
This repository provides a Next.js-based editor for generating App Store and Google Play marketing screenshots. It leverages AI coding agents to automate the creation of visually appealing and store-ready screenshot decks, complete with device frames, captions, and connected canvas layouts.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Automating the creation of professional, marketing-ready App Store and Google Play screenshots using AI.
✨ Key Features:
• AI-powered screenshot generation for App Store and Google Play
• Connected canvas editor for seamless element spanning
• Real device frames for iOS, iPad, Android, and Play Store formats
📖 Summary:
This repository provides a Next.js-based editor for generating App Store and Google Play marketing screenshots. It leverages AI coding agents to automate the creation of visually appealing and store-ready screenshot decks, complete with device frames, captions, and connected canvas layouts.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 agent | Go
🎯 Primary Use Case:
To provide a flexible and scalable software agent for managing and processing video streams from various camera sources for surveillance purposes.
✨ Key Features:
• Open-source video surveillance management agent
• Scalable and isolated component of the Kerberos.io stack
• Supports IP cameras with RTSP H264/H265 streams
• Can process streams from USB cameras, Raspberry Pi cameras, etc. (via camera-to-rtsp)
📖 Summary:
The Kerberos Agent is an open-source, scalable video surveillance management system designed for IP cameras and other video sources. It allows for the processing and management of video streams, enabling features like motion detection and integration into larger surveillance setups.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
To provide a flexible and scalable software agent for managing and processing video streams from various camera sources for surveillance purposes.
✨ Key Features:
• Open-source video surveillance management agent
• Scalable and isolated component of the Kerberos.io stack
• Supports IP cameras with RTSP H264/H265 streams
• Can process streams from USB cameras, Raspberry Pi cameras, etc. (via camera-to-rtsp)
📖 Summary:
The Kerberos Agent is an open-source, scalable video surveillance management system designed for IP cameras and other video sources. It allows for the processing and management of video streams, enabling features like motion detection and integration into larger surveillance setups.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 MATRIXON-AGENTIC-BROWSER | HTML
🎯 Primary Use Case:
Smart web automation and AI-assisted browsing using a local, privacy-focused agent.
✨ Key Features:
• Local LLM (GGUF models via llama.cpp)
• AgentPanel sidebar AI assistant
• Web search, page reading, URL navigation tools
• Full-page AI chat with file attachments and LaTeX
• AI-summarized web search results
📖 Summary:
MATRIXON Agentic Browser is an open-source, privacy-focused desktop browser built with Electron. It integrates a fully local AI assistant powered by llama.cpp and GGUF models, enabling smart web automation and interaction without relying on cloud services or API keys.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Smart web automation and AI-assisted browsing using a local, privacy-focused agent.
✨ Key Features:
• Local LLM (GGUF models via llama.cpp)
• AgentPanel sidebar AI assistant
• Web search, page reading, URL navigation tools
• Full-page AI chat with file attachments and LaTeX
• AI-summarized web search results
📖 Summary:
MATRIXON Agentic Browser is an open-source, privacy-focused desktop browser built with Electron. It integrates a fully local AI assistant powered by llama.cpp and GGUF models, enabling smart web automation and interaction without relying on cloud services or API keys.
🔗 Links:
• View Project
================
🔓 Open Source
❤1🔥1🙏1
🔥 abtop | Rust
🎯 Primary Use Case:
Monitoring and managing the performance and resource utilization of multiple AI coding agent sessions in a terminal environment.
✨ Key Features:
• Real-time monitoring of AI coding agents (Claude Code, Codex CLI, OpenCode)
• Tracks token usage, context window percentage, and rate limits
• Detects open ports and child processes spawned by agents
• Supports multiple active agent sessions across macOS, Linux, and Windows
📖 Summary:
abtop is a terminal-based monitoring tool for AI coding agents, inspired by htop. It provides real-time insights into the performance and resource usage of agents like Claude Code, Codex CLI, and OpenCode, displaying token consumption, rate limits, context window status, and active network ports.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Monitoring and managing the performance and resource utilization of multiple AI coding agent sessions in a terminal environment.
✨ Key Features:
• Real-time monitoring of AI coding agents (Claude Code, Codex CLI, OpenCode)
• Tracks token usage, context window percentage, and rate limits
• Detects open ports and child processes spawned by agents
• Supports multiple active agent sessions across macOS, Linux, and Windows
📖 Summary:
abtop is a terminal-based monitoring tool for AI coding agents, inspired by htop. It provides real-time insights into the performance and resource usage of agents like Claude Code, Codex CLI, and OpenCode, displaying token consumption, rate limits, context window status, and active network ports.
🔗 Links:
• View Project
================
🔓 Open Source