📦 espargos/esp-sdr

Turn a $3 Chip Into a Radio

Take a cheap ESP32 chip and turn it into a real software defined radio without buying extra hardware. This project, ESP-SDR, digs into undocumented debug paths inside the chip to bypass the standard Wi-Fi modem. That bypass lets the processor grab raw radio signals directly from the antenna. You can then analyze the spectrum of anything near two point four gigahertz on your computer. It is wild that you can do this with a microcontroller costing less than five dollars. No expensive spectrum analyzer required. Just a little bit of clever code and a USB cable.

📰 https://news.ycombinator.com/item?id=49893735

🆔 @hackernewsgithubprojects

📦 llmmanorg/llmman

Llmman: The Model Manager That Treats AI Like Docker

Llmman is the model manager that finally treats artificial intelligence models just like your software packages. Instead of using a messy, proprietary folder structure, it stores every model as a standard container image you already know how to handle. This means you can pull, push, and sign models using the exact same tools you use for your Docker containers, completely bypassing any specific hub or gatekeeper. It takes the complex business of moving heavy AI files and turns it into simple, standard supply chain logistics. If you want to run local models without the usual headache, this is the clean way to do it.

🆔 @hackernewsgithubprojects

📦 github/gh-actions-lock

GitHub Just Locked Your Workflows

GitHub just made it impossible for a single malicious update to hijack your entire build pipeline. The new tool called gh-actions-lock works like a digital safety seal for your automation scripts. Instead of trusting a vague version number, it records the exact, unchangeable fingerprint of every code snippet your workflows download. If anyone tries to swap in a fake or broken update, the system instantly blocks it. This turns your automated checks from a hopeful guess into a guaranteed, verified process. It is a quiet, powerful shift toward treating your build steps as critical security infrastructure rather than simple scripts.

🆔 @hackernewsgithubprojects

📦 fazlerocks/jevmail

Jevmail: The AI Inbox Sorter

Jevmail is the email triage tool that finally sorts your inbox without touching it. Instead of using a chatbot to guess, this app uses a specialized decision model to instantly categorize your Gmail messages into simple trays like Needs Reply or Spam. It is strictly read-only, meaning it can only look at your mail and never change a single label or mark anything as read. The coolest part is how it actually works: it processes a thousand emails in about a minute for just three cents, letting you see exactly which mail needs your attention while keeping everything else out of the way.

🆔 @hackernewsgithubprojects

📦 murray17/rovai-ai

Rovai AI: Turn Your AI Agents Into A Real Team

Stop treating your AI agents like disposable chatbots that forget everything the moment you close the tab. Rovai AI fixes that by giving your digital workers a shared Camp where they keep lasting roles and build a memory that actually sticks. It is less about running one-off prompts and more about creating a persistent environment where these agents can coordinate, share context, and grow into a cohesive unit. Think of it as giving your software team a real office instead of just sending them individual tasks. This is the rare setup where the agents do not just execute, but they actually develop a shared history and team dynamic over time.

🆔 @hackernewsgithubprojects

📦 basecamp/hotcell

HotCell: Securing Rails from Malicious Files

Basecamp's new project, HotCell, moves dangerous file processing out of your main web server and into a locked-down sidecar container. When users upload files, your Rails app usually trusts libraries like libvips to handle them, but those tools often contain bugs that hackers can exploit to steal data or crash your server. HotCell fixes this by running that work in a separate, unprivileged container with no network access and no sensitive credentials. If a malicious file triggers a bug, the damage is contained entirely within that isolated box, keeping your main application safe.

🆔 @hackernewsgithubprojects

📦 1jehuang/mermaid-rs-renderer

MMDR renders Mermaid diagrams without a browser

MMDR is the Rust renderer that finally kills the browser overhead for Mermaid diagrams. The official tool spawns a whole headless Chromium instance just to draw a picture, which means waiting seconds for every single chart. MMDR skips the browser entirely, parsing and drawing the diagram natively in a tiny binary instead. This means a flowchart that used to take two seconds now appears in milliseconds, making it perfect for fast previews or bulk documentation generation. It supports the standard diagram types you already know, so your existing code still works.

🆔 @hackernewsgithubprojects

📦 ikora128/stop-ai-slop-jp

Stop AI Slop (Japanese Edition)

Strip the robotic hum from your Japanese writing by handing a specific editing task to your AI assistant. Stop AI Slop (Japanese Edition) acts as a specialized guide that detects and removes the invisible tells that make text feel hollow and generated. The project targets the subtle structural habits of machine writing, such as uniform sentence rhythms, vague subjectless actions, and inflated abstract concepts. It forces the text to ground itself in specific human experience and concrete facts, pushing the language back toward a clear, visible voice. If you draft in Japanese with AI, this tool helps you reclaim the writer's identity from the template.

🆔 @hackernewsgithubprojects

📦 artemtsitronov/glacex

Glacex: The Rust UI Library Drawing Your Own Pixels

Build native desktop apps that skip the browser engine entirely. Glacex is a new Rust library that lets you draw every single pixel yourself directly on the graphics card. Instead of wrapping slow web tech or native toolkits, it uses a clever math trick to turn smooth shapes into tiny squares that your GPU can paint at lightning speed. This means crisp, anti-aliased buttons and text without the usual overhead. It is built for developers who want total control over their interface while keeping code clean and fast. If you like owning your rendering pipeline, this is the one to watch.

📰 https://news.ycombinator.com/item?id=49911322

🆔 @hackernewsgithubprojects

📦 deejanuz/frametop

Frametop VR Desktop

Put a customizable multi-monitor desktop right inside your virtual reality headset with Frametop. Built specifically for the Valve Steam Frame running SteamVR, this clever tool lets you run a full KDE Plasma desktop directly on your hardware without needing a separate computer. You can arrange, resize, curve, and roll multiple virtual monitors in three dimensional space, even pinning a screen to your wrist. Best of all, it includes a smart driver that turns any standard Bluetooth mouse into a three dimensional pointer, making it incredibly easy to navigate your workspace and the SteamVR dashboard without ever touching a controller.

🆔 @hackernewsgithubprojects

📦 unjs/upm

UPM Package Manager

UPM is the ultra-light package manager that delivers Rust-level install speeds using pure TypeScript. While other modern package managers require massive native binaries that bloat your disk and slow down continuous integration, this project fits entirely in about two hundred and fifty kilobytes by smartly reusing the tools already built into Node.js. It supports your existing lockfiles from npm, pnpm, and Bun right out of the box, and works securely by skipping risky postinstall scripts. Best of all, every command is a standard JavaScript function you can import, meaning you can easily bundle it directly into your own developer tools.

🆔 @hackernewsgithubprojects

📦 lightsifter/sift-light

Sift Light: The Search Tool That Actually Thinks

Sift Light is the search plugin that finally gives AI agents a reliable librarian instead of a blind guesser. When your code assistant needs to hunt for a specific error log or a forgotten config file, it usually just grabs every file and wastes your time. Sift Light fixes that by finding the exact passage you need and handing it over immediately, so the agent works with facts, not guesses. It even understands when you remember a word wrong, using local models to find the right file without sending your data to the cloud.

🆔 @hackernewsgithubprojects

📦 avinash-jetwani/jevmem

jevmem: The AI Memory That Remembers Your Dead Ends

JeVMem is the project memory tool that remembers every dead end your coding assistant hits. Instead of letting an AI forget a failed approach, it saves the specific reason why something broke, so it never tries that same mistake again. It automatically watches your chat sessions to capture decisions and constraints, storing them in a simple file that feeds directly back into the next prompt. This means your AI assistant actually learns from your past failures, saving you time and preventing repetitive errors. It works right inside Claude Code, making your daily coding sessions smarter and more efficient. Give your AI a real memory that actually sticks to the facts.

📰 https://news.ycombinator.com/item?id=49846391

🆔 @hackernewsgithubprojects

📦 symfony/reprise

Symfony Reprise

Reprise is the Symfony integration layer that finally brings Webpack Encore's best asset management features to modern bundlers like Vite and Rsbuild. If you love building PHP applications with Symfony but want the blazing-fast speed of modern front-end build tools, this project is the perfect bridge. It handles all the messy glue code that bundlers leave out by generating your asset entry points and manifest files automatically. This means your PHP templates can easily render script tags, manage cache-busting, and wire up live hot module reloading. It is the ultimate way to keep your modern front-end workflow and your back-end framework in perfect harmony.

🆔 @hackernewsgithubprojects

📦 misakazentai/world-execute-me-dsh-pv

Code-Rendered Music Video

A single Python command renders a full music video where every frame is a pure function of the song's timeline. This repository, named world.execute.me.dsh.pv, recreates a fan visual for the track world.execute.me by Mili using a split-screen approach. On the left, it simulates a live chat interface by generating HTML pages and screenshotting them with Playwright to mimic a real conversation. On the right, a custom engine draws a terminal-style visualization of the AI model itself. You bring your own audio file, and the system handles the rest, syncing lyrics and graphics perfectly.

🆔 @hackernewsgithubprojects

📦 cinderline/northcinder

NorthCinder: The AI Shopper That Actually Works For You

NorthCinder is the open-source shopping agent that forces AI to work for you, not for a marketplace. It plugs into your AI app to compare products across stores like Shopify, eBay, and Amazon, then shows you exactly why it picked a winner. The coolest part is that it refuses to just guess or let a store pay to be first. Instead, it gives you a short, honest list with reasons you can check yourself. And before it spends a single penny, it stops and asks your permission. It is a private, local tool that keeps your data and your money under your control.

🆔 @hackernewsgithubprojects

📦 zacharyzhang-ny/ely-gpui-components

Ely GPUI Components: Live Browser Testing

Ely GPUI Components is the Rust component library that renders every single interface element live in your browser. Most UI toolkits force you to launch a heavy desktop app just to see if a button works. This project changes that workflow completely by compiling the native Rust interface directly into the web. You can click, type, and interact with every widget exactly as it will appear in the final software. It covers everything from simple toggles to complex data grids and chat windows. The single most useful feature is that instant visual feedback. You stop guessing if your code works and start seeing it run immediately.

🆔 @hackernewsgithubprojects

📦 vectorize-io/agent-memory-benchmark

Agent Memory Benchmark: The Honest Test for AI Memory

Agent Memory Benchmark is the open evaluation harness that finally exposes whether an AI agent actually remembers or just guesses. Built by Vectorize, it solves the problem that older tests were too easy for modern models to pass by accident. Instead of just checking if an answer is correct, it measures the real cost and speed of finding that information. The most surprising part is that it treats memory like a strict exam where returning wrong details is just as bad as forgetting them entirely. If you are building agents that need to hold knowledge over time, this is the tool that tells you the truth.

🆔 @hackernewsgithubprojects

📦 ninjahawk/livenerf

livenerf: The Nerf Detector

Track whether a frontier AI model gets quietly worse right after it launches. Months of online reports claimed that major AI companies degrade their tools days after release, but without a fixed starting point, everyone was just guessing. This project, called livenerf, fixes that problem by running the exact same set of difficult math and science questions every single day for thirty days. It locks down the software version and the questions so nothing else can change. By comparing every daily result against the first week, it uses simple statistics to spot a real drop in performance.

📰 https://news.ycombinator.com/item?id=49809555

🆔 @hackernewsgithubprojects

📦 makson179/bello

bello

AI software developers are great until they wander off and make mistakes on long tasks. Bello is a local tool that acts as a manager for your AI coding agents, keeping them on track and preventing them from running unsafe commands. It wraps your existing coder in up to four specialized roles, including a runtime supervisor to stop logical drift, an independent reviewer to catch bugs, and even an adversary that tries to break the code with edge cases. Best of all, it includes a local model that shrinks command logs so your AI reads less text, saving you up to sixty-six percent on model subscription limits.

🆔 @hackernewsgithubprojects