📦 sahil-shubham/bhatti

Run AI Agents Safely with Self-Hostable MicroVMs

Are you tired of worrying about the security of your AI coding agents? Meet Bhatti, an open-source orchestrator that lets you run secure, self-hosted microVMs for your agents with ease. Instead of risking your main system, Bhatti creates isolated Linux environments in seconds, providing full kernel and filesystem protection. It is incredibly efficient, allowing you to pause sandboxes to save resources and resume them in mere microseconds for lightning-fast execution. With features like diff snapshots and multi-tenant isolation, it is the perfect sandbox for your development workflow. Give your AI agents a safe, dedicated home today by trying it out.

📰 https://news.ycombinator.com/item?id=47819407

🆔 @hackernewsgithubprojects

📦 varnan-tech/opendirectory

Supercharge Your AI Agents with OpenDirectory

Want to give your AI agents superpowers without teaching them complex tasks from scratch? Meet OpenDirectory, a powerful registry designed for growth automation, technical marketing, and go-to-market workflows. Instead of starting from zero, you can simply download pre-built skills like SEO keyword research tools, LinkedIn post generators, or even automated pull request explainers. It integrates seamlessly with agents like Claude Code, allowing you to instantly install and run these specialized capabilities via your terminal. It is the perfect way to automate your daily grind and boost productivity, so start exploring the catalog and supercharge your AI workflows today.

📰 https://news.ycombinator.com/item?id=47847832

🆔 @hackernewsgithubprojects

📦 zilliztech/vector-graph-rag

Build Faster Graph RAG with Pure Vector Search

Tired of RAG systems that struggle with complex multi-hop questions? This project offers a breakthrough by using pure vector search to perform graph-based reasoning without needing a separate, heavy graph database. It works by encoding entities and relations as vectors in Milvus, enabling efficient subgraph expansion for your data. By replacing slow, iterative agent loops with a single-pass LLM reranking process, it significantly cuts down on both computation and operational costs. It is an ideal tool for anyone looking to achieve state-of-the-art performance on knowledge-intensive tasks, helping you build smarter, faster, and more efficient AI applications today.

📰 https://news.ycombinator.com/item?id=47684290

🆔 @hackernewsgithubprojects

📦 nimaoth/nev

Why You Should Try the Nev Text Editor

If you are tired of switching between terminal and desktop editors, check out Nev. It is a powerful, keyboard-focused text editor written in Nim that runs seamlessly in both your terminal and as a native GUI. By pulling inspiration from popular tools like Neovim and Zed, it brings heavy hitters like Tree-sitter for syntax highlighting, full LSP support, and even WASM plugin capabilities right to your fingertips. Whether you need integrated debugging or built-in Git tools, Nev streamlines your workflow into one fast, efficient environment. Give it a try if you want a modern, unified coding experience.

📰 https://news.ycombinator.com/item?id=47884872

🆔 @hackernewsgithubprojects

📦 facepunch/sbox-public

Is This The Future of Game Development?

Ever wanted to build your own game without wrestling with complex, outdated tools? Meet this powerful open-source game engine that is changing the game for creators everywhere. Built on the advanced technology of Valve's Source 2, it leverages the speed of modern C sharp and a smart, component-based workflow. You can take advantage of lightning-fast hot reloading to see your code changes instantly in the editor, or use visual scripting to craft complex logic without typing a single line. It is a fresh, intuitive sandbox designed to make professional-level game development accessible. Dive in today and start creating your masterpiece.

📰 https://news.ycombinator.com/item?id=47885456

🆔 @hackernewsgithubprojects

📦 highflame-ai/zeroid

Stop Impersonation: Secure Your AI Agents with ZeroID

Ever wonder how to truly identify and govern autonomous AI agents in production? Today, most agents impersonate users through shared service accounts, creating massive security gaps. ZeroID solves this by treating every AI agent as a first-class entity with a unique, cryptographically verifiable identity URI. It enforces delegated authority, allowing agents to perform tasks on behalf of users or other agents while maintaining a clear, auditable delegation chain. With support for real-time revocation and policy-based scope attenuation, it keeps your automated workflows secure and accountable. Stop relying on shared secrets and start building trust into your agentic systems with ZeroID today.

📰 https://news.ycombinator.com/item?id=47674346

🆔 @hackernewsgithubprojects

📦 google-labs-code/design.md

Give Your Coding Agents a Design System with DESIGN.md

Struggling to keep your AI coding agents consistent with your visual brand? Meet the DESIGN.md format, a powerful way to define a persistent design system for your agents. By combining machine-readable tokens with human-readable rationale, this tool ensures your AI understands exactly how to apply your typography, colors, and layout rules. You can even use the included CLI to lint your design files, catch contrast errors, or export configurations directly into Tailwind CSS. It is the perfect bridge for creating high-quality, brand-accurate code automatically. Start using this structured approach today to give your AI agents a professional visual identity.

📰 https://news.ycombinator.com/item?id=47887123

🆔 @hackernewsgithubprojects

📦 droid-vm/droidvm

Run Desktop Linux Directly on Your Android Phone

Have you ever wanted to turn your smartphone into a fully functional desktop computer? DroidVM makes this possible by allowing you to run a virtual machine directly on your Android device. It leverages virtualization technology to create a complete Linux environment right in your pocket without needing a secondary computer. Whether you want to run desktop applications or experiment with new operating systems, this tool bridges the gap between mobile convenience and desktop power. It is an incredibly efficient way to supercharge your device for productivity or development tasks. Try it out to transform your phone into a portable workstation today.

📰 https://news.ycombinator.com/item?id=47887171

🆔 @hackernewsgithubprojects

📦 zimengxiong/winmux

Supercharge Your Mac Workflow with WinMux

Are you tired of managing messy windows on your Mac and want a more efficient way to work? Meet WinMux, an intuitive, batteries-included window manager built on top of Aerospace to help you take full control of your desktop workspace. This tool streamlines your productivity by offering powerful features like tab groups that organize multiple windows into a single footprint and a persistent sidebar for better spatial awareness. Whether you are using its managed tiling mode or simple corner snapping, WinMux provides a cleaner, faster experience that makes navigating your apps effortless. Give your productivity a massive boost today.

📰 https://news.ycombinator.com/item?id=47666590

🆔 @hackernewsgithubprojects

📦 russellromney/honker

Supercharge SQLite with Honker

Ever wish your SQLite database had the powerful real-time capabilities of Postgres? Meet Honker, a clever extension that brings Postgres-style notifications, durable work queues, and event streams directly into your SQLite workflow. Instead of setting up complex external brokers like Redis or Celery, Honker lets you handle pub/sub and task scheduling right where your data lives. It uses smart file-based monitoring to deliver cross-process updates with sub-millisecond latency. You can even keep your business logic and task enqueueing perfectly atomic within a single transaction. It is an incredibly efficient way to keep your architecture simple and your project fast.

📰 https://news.ycombinator.com/item?id=47874647

🆔 @hackernewsgithubprojects

📦 higangssh/homebutler

Manage Your Homelab Instantly from Chat!

Stop wasting time SSHing into your servers every time something goes wrong. This incredible tool brings your entire homelab into your terminal, web browser, or even your favorite AI chat assistant. As a single, zero-dependency binary, it lets you monitor service health, manage Docker containers, and even run network scans with just a few simple commands. It tracks process restarts and captures logs, making it easy to diagnose crashes immediately. Whether you need to deploy new apps or wake up sleeping machines, it simplifies everything into one efficient, powerful interface. Upgrade your workflow and start managing your infrastructure smarter today.

📰 https://news.ycombinator.com/item?id=47676030

🆔 @hackernewsgithubprojects

📦 nv404/gova

Build Native Desktop Apps with Gova

Tired of bulky desktop apps? Meet Gova, a powerful new framework that lets you build native, high-performance desktop applications using only the Go programming language. Gova simplifies your workflow by treating UI components as plain Go structs, removing the need for complex web runtimes or extra assets. It provides explicit, reactive state management and integrates directly with system native dialogs, allowing you to compile your entire project into one clean, static binary. Whether you are targeting Windows, macOS, or Linux, Gova offers a smooth, typed, and efficient path to desktop development. Give your next project the speed it deserves.

📰 https://news.ycombinator.com/item?id=47886272

🆔 @hackernewsgithubprojects

📦 matz/spinel

Supercharge Your Ruby: Meet Spinel

Ever wondered if you could run your Ruby code as a lightning-fast native executable? Spinel is an experimental ahead-of-time compiler that transforms your Ruby source into standalone native binaries, leaving traditional interpretation behind. By performing whole-program type inference and generating optimized C code, it delivers massive performance boosts for compute-heavy tasks. It is even self-hosting, meaning the compiler backend is written in Ruby and compiles itself. With features like value-type promotion that eliminate garbage collection overhead, this project is a bold step toward ultra-efficient Ruby. Experience the future of high-performance Ruby development and start compiling today.

📰 https://news.ycombinator.com/item?id=47887334

🆔 @hackernewsgithubprojects

📦 trycua/cua

Build AI Agents That Control Your Desktop

Have you ever wanted to build an AI that can actually use your computer just like a human? Meet Cua, the open-source infrastructure designed specifically for computer-use agents. It solves the fragmentation problem by providing a unified SDK to train and evaluate agents across macOS, Linux, and Windows desktops. With Cua, you get ephemeral sandboxes, native virtualization, and rigorous benchmarks to test your agent's ability to click buttons, type, and navigate workflows autonomously. Whether you are running complex GUI tasks or training for OSWorld benchmarks, Cua gives you the control you need to level up your automation projects today.

📰 https://news.ycombinator.com/item?id=47891384

🆔 @hackernewsgithubprojects

📦 arc1011/kerneluno

Run a Unix Shell on Your Arduino UNO!

Ever wondered if your Arduino UNO could do more than just blink an LED? Meet KernelUNO, an incredibly lightweight, Unix-like shell that brings a functional command-line interface directly to your microcontroller. It solves the problem of needing a dedicated interface for hardware interaction by providing twenty-two built-in commands for file management and real-time GPIO control. You can navigate a virtual filesystem, read memory statistics, and even toggle pins using standard shell commands. It is a fantastic way to experiment with kernel-level concepts on limited hardware. Dive into the code, explore the system, and transform your Arduino today.

📰 https://news.ycombinator.com/item?id=47851630

🆔 @hackernewsgithubprojects

📦 nickcirv/engram

Stop Wasting Tokens! Meet EngramX

Are you tired of your AI coding agent burning through tokens by repeatedly re-reading the same files? Meet EngramX, the smart context spine designed to stop that waste. By acting as an intelligent layer between your agent and the filesystem, it intercepts file reads and injects pre-assembled, compact context packets based on a local knowledge graph. It handles everything from mistake tracking to library documentation, delivering massive, measured token savings of nearly ninety percent. It works locally with no cloud data, so you can slash your AI bills while keeping your codebase secure and efficient.

📰 https://news.ycombinator.com/item?id=47803155

🆔 @hackernewsgithubprojects

📦 veeso/termscp

Master Your Files from the Terminal with Termscp

Are you tired of jumping between different apps just to manage files on remote servers? Meet Termscp, a powerful terminal user interface designed to streamline your file transfers and exploration. Written in Rust for maximum performance, this tool acts as your all-in-one hub for connecting to remote systems using protocols like SFTP, SCP, FTP, and even S3 or SMB. You can easily view, edit, and synchronize files directly from your terminal with a highly customizable interface that fits your workflow perfectly. Whether you are a developer or a sysadmin, Termscp makes managing remote data feel fast, native, and incredibly efficient.

📰 https://news.ycombinator.com/item?id=47893021

🆔 @hackernewsgithubprojects

📦 nellavio/nellavio

Build Dashboards Faster with This Next.js Starter

Are you tired of building your admin dashboard from scratch every single time? Stop wasting hours on repetitive setup and check out this powerful open source starter instead. It gives you a massive head start by providing over ninety reusable UI components and sixty different chart variations right out of the box. Built with modern tools like Next.js and Tailwind, it handles complex features like authentication and internationalization seamlessly. Whether you are developing internal tools or a new SaaS product, this project lets you focus on your unique features. Grab this solid foundation today and accelerate your development workflow.

📰 https://news.ycombinator.com/item?id=47893422

🆔 @hackernewsgithubprojects

📦 sbarex/qlmarkdown

Make Your Mac Markdown Magic

Stop guessing what is inside your text files before you open them. If you work with code or notes on a Mac, you know that missing previews for Markdown files can be a real productivity killer. This clever tool brings native Quick Look support to your system, letting you see perfectly rendered previews directly in the Finder with a single tap of the spacebar. It even handles syntax highlighting for code blocks and renders mathematical expressions beautifully. It is a seamless way to streamline your workflow and keep your workspace clean. Install it today to finally preview your documents instantly.

📰 https://news.ycombinator.com/item?id=47894050

🆔 @hackernewsgithubprojects

📦 alexzhang13/rlm

Stop hitting context limits with Recursive Language Models!

Ever feel like your AI gets lost when you throw massive documents at it? Meet the Recursive Language Models library, a game-changing tool that lets models handle near-infinite context by letting them think like programmers. Instead of trying to process everything in one massive, messy pass, this library allows the AI to act as an orchestrator that decomposes complex tasks into smaller, manageable sub-queries. By using sandboxed Python environments, the model can programmatically inspect, slice, and recursively call itself to find specific details. It is a powerful, plug-and-play way to make your AI smarter, more modular, and truly scalable.

📰 https://news.ycombinator.com/item?id=47894669

🆔 @hackernewsgithubprojects

📦 parallem-ai/parallem

Slash Your LLM Costs in Half with ParaLLeM

Are you tired of skyrocketing token costs while building AI agents? Meet ParaLLeM, an expressive library designed to revolutionize how you orchestrate complex agentic workflows. By leveraging the Batch API, this tool enables you to parallelize thousands of requests while keeping perfectly reproducible traces for every single run. The best part is the simplicity, as you can switch between sequential and batch execution by changing just one line of code. It is a lightweight, developer-focused solution that can save you fifty percent on all token costs. Give your agents a serious performance boost and optimize your development workflow today.

📰 https://news.ycombinator.com/item?id=47747516

🆔 @hackernewsgithubprojects