📦 jaylfc/taos

Run a Private AI Operating System on Your Own Hardware

Manage your AI agents, files, and conversations using a self-hosted operating system that runs entirely on hardware you already own. This platform turns your spare devices like laptops, Raspberry Pis, or gaming PCs into a unified, distributed AI compute cluster. It features a complete web-based desktop interface, an app store, and an offline-first memory system that ensures your data stays private. Because it is framework-agnostic, you can switch between different agent engines without losing your history or configurations. Transform your existing collection of consumer hardware into a powerful, sovereign AI environment that you fully control.

🆔 @hackernewsgithubprojects

📦 railly/agentfiles

Manage All Your AI Agent Skills Inside Obsidian

Organize your AI workflows by managing skills, commands, and agents directly within Obsidian. This plugin streamlines your productivity by allowing you to browse, create, and edit files for over thirteen different coding assistants, including Claude Code and Cursor, from a centralized interface. You can search across your tools, install new capabilities via a marketplace, and track usage metrics like burn rate and health through a dedicated dashboard. It is an essential utility for developers looking to unify their fragmented agent configurations and keep everything accessible in one place while you code your next big project.

🆔 @hackernewsgithubprojects

📦 pierridotite/stonks-dashboard

Stonks Dashboard: Terminal-Based Financial Tracking

Stonks Dashboard is the minimalist financial monitor that brings real-time market tracking directly into your terminal. This tool allows you to keep a close eye on your crypto, stocks, and ETFs in a single, sleek cyberpunk-style interface. It visualizes data using dynamic ASCII charts and color-coded metrics, making it easy to spot trends across various time periods. With built-in support for caching and rate-limited API calls, it provides smooth updates without overloading your data sources. Whether you are managing personal investments or just love data in your command line, it offers a fast, efficient way to stay updated.

🆔 @hackernewsgithubprojects

📦 reinehonoka/voice-design-cloner

Build AI Voices Instantly with VoiceDesignCloner

This graphical interface eliminates the need for manual recording by automating the creation of high-quality AI training data from scratch. It streamlines the entire pipeline for voice synthesis, allowing users to design unique voices through text prompts, generate bulk audio corpora, and prepare datasets for fine-tuning models like Style-Bert-VITS2 or Irodori-TTS. By handling complex preprocessing tasks such as resampling and list generation automatically, this tool removes significant technical barriers for developers and creators. Whether building virtual characters or narrators, this software provides a unified workspace to design, clone, and train custom voices with ease.

🆔 @hackernewsgithubprojects

📦 digitranslab/allama

Automate Security Triage with AI Agents

Build automated security workflows using an open-source platform designed to replace legacy SOAR tools. This project enables security teams to deploy autonomous AI agents that analyze threats and execute responses through over eighty different integrations. You can design complex playbooks with a visual drag-and-drop editor that handles logic and loops without writing code, while running custom scripts in isolated sandboxes for added safety. By centralizing incident management and automating routine triage, the platform helps security analysts focus on critical tasks rather than manual alerts. Adopt this self-hosted solution to modernize your security operations and gain full data sovereignty.

🆔 @hackernewsgithubprojects

📦 zstud/reef

Stop struggling with Bash in Fish Shell

Reef is the Bash compatibility layer that makes legacy shell syntax run seamlessly inside the Fish shell. By utilizing a zero-copy Rust parser, it translates common Bash commands into native Fish equivalents on the fly with no configuration required. For more complex operations, it handles seamless passthrough to Bash while maintaining environment state. It also offers optional modern tool wrappers that replace legacy commands like grep or ls with faster alternatives like ripgrep and eza. Install it to gain the speed and features of Fish without sacrificing your existing Bash knowledge or script compatibility.

📰 https://news.ycombinator.com/item?id=48701585

🆔 @hackernewsgithubprojects

📦 almeidazs/better-drizzle

Drizzle ORM, but better

Simplify your database interactions by wrapping your Drizzle ORM client in a repository-style API that eliminates repetitive query code. This project provides a consistent, type-safe interface for common CRUD operations like finding, creating, updating, and deleting records, while also handling complex tasks like pagination and relation loading without hiding the underlying SQL power. By using these helpers, you can maintain clean service logic and implement features like lifecycle hooks or soft deletes through a plugin system. Use this approach to keep your code readable and high-performing while staying close to the metal. Give it a try for cleaner database queries.

🆔 @hackernewsgithubprojects

📦 runtypelabs/persona

Build Agentic Web Experiences with Vanilla JS

Persona is the themeable AI chat widget that brings agentic front-end experiences to any website using pure TypeScript and Vanilla JS. It removes framework complexity, allowing you to easily drop a powerful, multi-modal assistant into existing React, Vue, or static projects. With built-in support for streaming responses, voice input, tool call visualization, and artifact rendering, it offers a highly extensible plugin system to customize every layer of your UI. Whether you need a floating launcher, a docked side panel, or a full-page interface, this lightweight toolkit helps you build sophisticated AI features quickly without being tied to specific frameworks.

📰 https://news.ycombinator.com/item?id=48612231

🆔 @hackernewsgithubprojects

📦 automataia/graphrag-rs

Build Knowledge Graphs with Rust

This project provides a high-performance implementation of Graph-based Retrieval Augmented Generation written entirely in Rust. It functions by transforming documents into structured knowledge graphs, which allows for more nuanced natural language querying than standard search methods. The repository includes a command-line interface, a modular core library compatible with WebAssembly, and support for local model integration through Ollama. By utilizing parallel processing and configurable entity extraction, it enables developers to build scalable document analysis pipelines that run efficiently on local hardware. These tools ultimately provide a robust framework for advanced data retrieval and structured knowledge discovery.

🆔 @hackernewsgithubprojects

📦 alexandrosgounis/pdfx

Store Multiple Documents in One PDF with PDFx

PDFx enables users to bundle multiple documents into a single, standard PDF file while remaining fully compatible with any traditional PDF viewer. By embedding a lightweight JSON manifest directly into the PDF metadata, the software allows for the logical grouping of files that stay organized as a collection. Users can drag and drop documents into the interface, where they are rendered as distinct, reorderable stacks before being exported as a single unified file. This project effectively solves the issue of managing scattered document sets by turning collections into portable, self-contained units for easier sharing and storage.

📰 https://news.ycombinator.com/item?id=48696503

🆔 @hackernewsgithubprojects

📦 copilotkit/opentag

Build Your Own AI Agent for Slack and Beyond with OpenTag

OpenTag is the open-source bot framework that lets you deploy your own AI agents directly into Slack, Discord, Telegram, and WhatsApp. By keeping the runtime on your own infrastructure, you maintain total control over your data, tools, and chosen AI models without worrying about per-seat pricing or vendor lock-in. It supports advanced features like generative UI for inline charts and tables, and includes built-in human-in-the-loop gates for secure actions like filing Linear tickets or managing Notion documents. Clone the repository, connect your preferred chat platform, and start building custom, self-hosted AI assistants today to automate your team's workflow.

📰 https://news.ycombinator.com/item?id=48697420

🆔 @hackernewsgithubprojects

📦 eliasoulkadi/shokunin

Shokunin: 62 AI Agent Skills with Persistent Memory

Shokunin provides sixty-two specialized engineering skills and persistent AI memory for coding environments like OpenCode, Cursor, and Windsurf. This project bridges the gap between generic prompts and professional workflows by offering structured domain expertise—ranging from Docker and Kubernetes to frontend architecture and database management—directly within your editor. By integrating ChromaDB for local vector memory and declarative self-updates, it allows AI agents to recall previous sessions and maintain consistent project context without relying on cloud services. It is a completely open-source toolkit designed to help developers standardize complex engineering tasks and improve overall coding precision.

📰 https://news.ycombinator.com/item?id=48159744

🆔 @hackernewsgithubprojects

📦 magenta/the-infinite-crate

Build Live Music with The Infinite Crate

The Infinite Crate is the experimental digital audio workstation plugin that lets you steer live music generation through real-time text prompts. By combining a C++ JUCE engine with a responsive React interface, this project streams audio directly into your music software to create a dynamic practice partner or performance tool. You can manipulate musical output on the fly using intuitive text controls, making it easy to sample or jam in the moment. It is an impressive demonstration of integrating advanced AI models into standard audio production workflows for creative experimentation. Dive into this open-source project to start shaping your own sound.

📰 https://news.ycombinator.com/item?id=47316378

🆔 @hackernewsgithubprojects

📦 yuxumin/viq

ViQ: Unified Visual Representation Learning

Transform images into efficient, discrete codes with ViQ, a framework designed to bridge the gap between continuous visual encoders and text-based multimodal modeling. By utilizing a SigLIP2 vision tower paired with position-aware, head-wise Finite Scalar Quantization, this project enables images at any resolution to be represented as compact token sequences. This approach balances semantic richness with fine-grained detail, allowing you to feed visual data directly into language models like Qwen2.5 or reconstruct high-fidelity images. Because these codes can be extracted offline, you can significantly accelerate training pipelines, making ViQ a powerful tool for building more efficient and unified multimodal AI systems.

🆔 @hackernewsgithubprojects

📦 drjacky/claude-android-ninja

Master Android Development with AI Agent Skills

This repository provides a comprehensive collection of structured instructions and templates designed to help AI agents build professional-grade Android applications using Kotlin and Jetpack Compose. By adopting the open Agent Skills format, it supplies developers with standardized guidance on modular architecture, Navigation3 routing, and Material 3 theming. It includes practical support for offline-first data synchronization, performance benchmarking, and rigorous testing practices using fakes and Hilt. Integrating this skill set allows development agents to generate clean, maintainable code across complex domains like media playback and secure networking, ensuring high-quality, scalable results that align with modern Android development standards.

🆔 @hackernewsgithubprojects

📦 xlang-ai/osworld-v2

OSWorld 2.0: Testing AI Agents on Real Desktop Tasks

OSWorld 2.0 provides a scalable framework to evaluate how well multimodal AI agents perform complex, long-horizon tasks across real-world computer environments. The repository serves as a unified benchmark where agents are tested on their ability to navigate desktop interfaces, manage files, and execute multi-application workflows as a human would. By supporting various infrastructure providers like Docker and AWS, it enables researchers to deploy consistent, reproducible testing environments. Developers can use the provided setup tools and task classes to measure an agent's success rate, helping to bridge the gap between simple model reasoning and practical, reliable desktop automation.

🆔 @hackernewsgithubprojects

📦 fengdu2077/x-search-filters

Master X Search with this Simple Filter Tool

X Search Filters is the handy browser extension that helps you effortlessly build complex search queries on X without needing to memorize technical syntax. By adding a clean visual panel directly to the search bar, it allows you to toggle specific operators like date ranges, minimum engagement counts, and media types with ease. You can save your favorite searches, manage your history locally, and apply complex filters with a single click while keeping the native search bar fully functional. It is an essential tool for power users who want to find exactly what they need on the platform faster.

🆔 @hackernewsgithubprojects

📦 yaojingang/yao-meta-skill

Yao Meta Skill: Building Governed AI Agent Skills

Yao Meta Skill is the engineering framework that finally brings rigorous governance and portability to your AI agent skills. This system transforms messy operational workflows, prompts, and transcripts into highly structured, reusable packages. By utilizing an intermediate representation and target-specific compilers, it ensures your skills perform reliably across platforms like OpenAI and Claude. With built-in tools for output evaluation, release gates, and permission probes, it prevents common failures and tracks adoption drift through a managed lifecycle. Use this system to turn your internal AI experiments into professional-grade, team-ready assets that are built to last.

🆔 @hackernewsgithubprojects

📦 yaojingang/geoflow

GEOFlow: AI-Powered Multi-Site Content Engineering

GEOFlow is an open-source system designed to automate content engineering and distribution across multiple websites. It streamlines the entire workflow from AI-driven content generation and RAG-based semantic chunking to multi-platform publishing. By integrating knowledge bases, prompt management, and analytics into a centralized dashboard, it enables teams to manage and synchronize high-quality, SEO-optimized content across WordPress sites or custom GEOFlow agents. This platform simplifies complex tasks like automated scheduling, task monitoring, and cross-site theme replication. It provides a robust architecture for teams looking to manage scalable digital assets with reliable AI integration and real-time performance tracking.

🆔 @hackernewsgithubprojects

📦 yaojingang/yao-open-prompts

Master AI with Yao Open Prompts

Yao Open Prompts is the curated library that finally organizes high-quality AI instructions into actionable, professional workflows. This repository provides over one hundred tested Chinese and English prompts specifically designed for content creation, marketing strategy, learning methodologies, and everyday productivity. Instead of scattered advice, you get structured tools for tasks like generating PPTs, performing reverse engineering, or optimizing content for search visibility. By offering a clean, copy-paste format focused on real-world utility, it streamlines how you interact with AI models to achieve better results. Explore these refined templates to elevate your daily AI usage and save valuable time.

🆔 @hackernewsgithubprojects

📦 yaojingang/yao-geo-skills

Master Generative Engine Optimization with These Reusable Skill Packages

This repository provides twenty open-source skill packages designed to standardize workflows for Generative Engine Optimization. Instead of relying on scattered prompts, the project offers structured, verifiable execution assets that cover everything from strategic diagnosis and page technical audits to content production and performance tracking. Each skill includes clear input templates, evaluation rubrics, and reproducible examples to ensure quality and consistency in professional tasks. It serves as a practical toolkit for teams aiming to automate complex operations and maintain reliable results in generative search environments, ultimately turning repetitive optimization tasks into reusable and scalable professional workflows.

🆔 @hackernewsgithubprojects