📦 mikehasa/golive-skill

GoLive Skill: Put Your AI App Live

Your AI coding assistant can build a whole app in minutes, but getting it to real users still means juggling hosting, databases, domains, emails, and payments. GoLive Skill is an open-source tool that solves this by inspecting your app, planning the exact changes needed, and asking for your approval before it touches anything. It uses your own existing logins to deploy everything on your own accounts, then verifies that it actually works. No hidden backend, no extra subscriptions, and no telemetry. If you want to take an agent-built product live without the usual setup headache, this is the tool to watch.

🆔 @hackernewsgithubprojects

📦 jkudish/jev-browser

Jev Browser: The $0.001 Web Agent

Jev Browser is the web automation tool that drives a real browser for less than two cents. It works by asking a specialized AI model to choose one single action from the elements on a page, rather than generating entire page structures from scratch. This approach allows the software to complete complex tasks, like finding a specific price or filling out a form, in just a few seconds. The result is a fully functional web agent that is fast, incredibly cheap, and easy to audit. It turns a difficult programming problem into a simple, low-cost utility.

🆔 @hackernewsgithubprojects

📦 qwenlm/qwen-live-harness

Qwen Live Harness: Your Realtime AI Sidekick

Qwen Live Harness lets you talk to your computer while it watches and listens. It acts as a realtime bridge that sees your screen, hears your voice, and delegates heavy lifting to background tools like code assistants. The coolest part? It remembers. It keeps long-term memory of your preferences and context, so you don’t have to repeat yourself. Imagine saying, "Watch this code and tell me if it breaks," and having it actually do that while you keep chatting. It’s like having a very attentive, slightly caffeinated intern who never forgets a detail.

🆔 @hackernewsgithubprojects

📦 nvlabs/skill2env

How Skill2Env Automates AI Training Tasks

A single command can turn a simple text description of a skill into a fully automated computer test that AI agents can solve. This project is called Skill2Env, and it solves a major bottleneck in training artificial intelligence. Usually, researchers have to hand-code complex scenarios to practice a new ability. Skill2Env uses an AI helper to automatically build those scenarios, complete with the instructions, the testing code, and even the correct answer key. It generates these practice problems in a standard format that other AI systems are built to understand. You can feed it a list of skills and it will churn out hundreds of training exercises overnight.

🆔 @hackernewsgithubprojects

📦 lakeday-org/perch

Perch: The Linter That Understands Code

Perch is the linter that actually reads your code to find bugs. While standard tools check your syntax, this tool uses an AI to understand what your functions are supposed to do, spotting logical errors like flipped conditions or missing null checks that regular linters completely miss. It parses your project structure, asks specific questions about how methods interact, and flags issues based on confidence scores. It is not just a spell checker for code, but a semantic scanner that understands context. If you want to catch logic bugs before they hit production, this is the tool you need to try.

📰 https://news.ycombinator.com/item?id=49840204

🆔 @hackernewsgithubprojects

📦 huiliyi37/tianshu-harness

Tianshu harness: The AI that remembers like you

Your coding bot suddenly stops acting like a dumb tool and starts acting like a partner who actually remembers your project. That is the core promise of Tianshu harness. Most AI assistants forget everything the moment you close the tab, but this project builds a memory system that decays naturally, just like a human brain. It uses a clever trick called pheromone decay to keep important context fresh while letting old noise fade away. This means the AI gets smarter over time without getting confused by irrelevant data. It is not just a chatbot; it is a cognitive framework for building AI that truly understands context.

🆔 @hackernewsgithubprojects

📦 han-1413141/dsh-cost-meter

The AI Cost Meter You Need

The DSH cost meter tracks every cent of your AI spending right inside your chat window. This plugin plugs into the DeepSeek Harness interface to show live costs per conversation, token usage, and account balances. It solves the problem of hidden AI bills by displaying exactly what each model costs, including peak and off-peak pricing windows. You can set budgets, see provider quotas, and get alerts before expensive peak hours start. The interface is bilingual, supporting both English and Chinese. If you use AI coding tools, this tool tells you what you are actually paying, so you can manage costs effectively without guessing.

🆔 @hackernewsgithubprojects

📦 mars-sea/dsh-commandcode-provider

dsh-commandcode-provider

Plug Command Code directly into your DeepSeek Harness terminal with the dsh-commandcode-provider. It drops into your local setup to give you instant access to a live catalog of models, complete with image support and built-in web search. But the real magic is how it handles multiple subscriptions. When one of your accounts hits its usage limit, the plugin automatically rotates to the next available key so your workflow never stops. You get a dedicated settings panel to manage these accounts and track your quota in real time, all without leaving your terminal. It is a clever way to keep your AI tools running smoothly even when your credits run dry.

🆔 @hackernewsgithubprojects

📦 abracadabra50/open-supermarkets

Let AI Shop Groceries: Open Supermarkets

Automate your entire grocery run. Open Supermarkets lets an AI agent search live stock, compare prices, and build a basket across ten retailers in seven countries without you touching a keyboard. The coolest part? In places like Spain and the Netherlands, no account is needed. Just query the real catalogue instantly. It handles the messy retail plumbing, so you can focus on the food. Your agent picks the best milk or the cheapest olive oil, and the system keeps the checkout safe by default. It is a clever bridge between smart assistants and real-world shopping. Stop copying and pasting shopping lists. Let the machine handle the mundane.

🆔 @hackernewsgithubprojects

📦 general-instinct/instinctflash

InstinctFlash: 33x Faster Robot Brains

InstinctFlash is the serving runtime that makes heavy robotics models run fast on cheap hardware. It takes massive AI brains that usually need data centers and shrinks their response time without dumbing them down. The coolest part is how it picks the fastest math trick for each model automatically, giving you thirty times the speed on a single chip. No more waiting for your robot to think. Your arm moves as fast as you can watch it. It’s the missing piece for real-time robotics.

📰 https://news.ycombinator.com/item?id=49802789

🆔 @hackernewsgithubprojects

📦 haplollc/thinkingorbs

ThinkingOrbs: 3D Loading Dots for AI

A single line of Swift code can now render genuinely three-dimensional loading indicators built entirely from grayscale dots. This project, called ThinkingOrbs, solves the visual monotony of artificial intelligence interfaces by offering nine distinct animated designs. Each orb represents a specific action, such as searching, solving, or listening, allowing users to see exactly what their agent is doing. The animations are mathematically precise ports of a famous web library, ensuring they look identical on any Apple device. Because they are drawn with simple dots rather than heavy graphics, they remain lightweight and respect accessibility settings like reduce motion.

🆔 @hackernewsgithubprojects

📦 awss1i/assay

How Assay Tests Your Code Without Tests

assay is the browser checker that actually runs your generated web pages. It solves the annoying gap where you have code that compiles but might still be broken in the browser. Instead of writing test suites or guessing with an AI, it opens your page in a real browser, finds every button and input, and presses them all to see if anything breaks. It tells you exactly what failed, like a button that does nothing on the first click. No API keys, no flaky tests, just a quick, mechanical check that works even if the code was written seconds ago.

📰 https://news.ycombinator.com/item?id=49787853

🆔 @hackernewsgithubprojects

📦 thinking-space/one-shot-opd

One Training Example: One-shot-opd

A single math problem can teach a large language model almost as much as seventeen thousand examples. This repository, called One-shot-opd, proves it by training a student model on just one query. Researchers found that while the algorithm gets slower over time, the initial data covers nearly all the necessary thinking states. In other words, the model is data-saturated but algorithm-starved. This shifts the focus from needing massive datasets to optimizing the training process itself. The key takeaway? You might need far fewer examples than you think to get a smart result.

🆔 @hackernewsgithubprojects

📦 vsitzmann/deckwerk

DeckWerk: The Local Slide Editor for Creators

Build a presentation where the video is just as easy to handle as a word document. DeckWerk is a desktop app that treats your slides as real files on your computer, meaning no cloud uploads and no login required. It is built specifically for researchers and developers who need to show off video and image-heavy demos without the friction of traditional software. The coolest part is that you can edit the actual code while watching the changes appear in real time. It feels like a bridge between writing a website and dragging a slide.

🆔 @hackernewsgithubprojects

📦 852wa/jizura

JIZURA: Turn Lyrics Into Motion Videos

Turn raw song lyrics into fully animated motion videos directly in your browser. JIZURA automatically designs the layout, text movement, backgrounds, and effects for every line of a song. The surprising part is how it works: you paste in your lyrics, load an audio file, and simply press a button to generate a completely unique visual style for the whole track. It detects the beat to sync the text with the music, then lets you randomize the design until you find a look you like. Everything runs locally in your browser, meaning your music and lyrics never leave your computer.

🆔 @hackernewsgithubprojects

📦 ybouane/videoflow

Code Your Videos: The VideoFlow Script

VideoFlow turns writing code into making actual video files. Instead of dragging clips around in a heavy editor, you write simple TypeScript instructions to place text, drop in images, and set up animations. The system compiles your script into a portable format that can render an MP4 directly in your browser or on a server. The coolest part is the resolution independence. You design your layout using relative units, so a composition built for a massive forty k monitor scales down perfectly to a standard phone screen without breaking the layout.

🆔 @hackernewsgithubprojects

📦 zhijiewong/openharness

OpenHarness

Your terminal can now run a full AI coding agent that actually lives inside your shell, and it does not force you to pick a single cloud provider. OpenHarness is an open source command line tool that connects to any large language model, whether that is a free local model on your own computer or a paid API. The coolest part is that it treats your codebase like a safe space. Every change the AI makes gets wrapped in a git commit automatically, so if the bot writes something terrible, you can just undo it with one command.

📰 https://news.ycombinator.com/item?id=47600371

🆔 @hackernewsgithubprojects

📦 ektogamat/threejs-conference

Threejs-Conference: Rain That Actually Collides

A browser scene renders a rainy cyberpunk alley where thousands of raindrops physically bounce off rooftops and car roofs without crashing the computer. This project, called Threejs-Conference, solves a common problem: making digital weather look real while keeping it fast enough to run on your phone. Instead of checking every drop against every wall, which is slow and messy, it uses a clever shortcut. The graphics card creates a simple height map of the street, then lets the rain calculate its own bounces directly on the hardware. This means the water behaves correctly without the main processor getting stuck.

🆔 @hackernewsgithubprojects

📦 wladimiravila/esp32s3-distributed-ai

ESP32-S3 Distributed AI

Three tiny circuit boards, each no larger than a coin, can work together to generate human-like text without touching the internet. This project, called ESP32-S3 Distributed AI, splits a massive language model across these three microchips, allowing them to chat over a direct wireless link to complete complex tasks. By dividing the heavy lifting among them, the system solves the problem of running powerful artificial intelligence on hardware that usually lacks the brain power for such jobs. You simply connect to the local network, type a prompt, and watch the boards collaborate to stream text back to your screen.

📰 https://news.ycombinator.com/item?id=49111137

🆔 @hackernewsgithubprojects

📦 xrip/cmp50hx-unlock

CMP 50HX Unlock

The CMP 50HX mining card has been artificially limited to a fraction of its true speed, but a new project called CMP 50HX Unlock reverses that restriction. It works by installing a special firmware patch during the early computer startup phase, which tells the graphics processor to run at its full factory speed instead of the throttled mining rate. This single change boosts the card's raw calculation power by over thirty times, making it perform like a high-end RTX 2080 Ti graphics card. The solution is simple to apply with a single installer for both Linux and Windows, and it also fixes slow data transfer speeds.

🆔 @hackernewsgithubprojects

📦 agentsea/nautilo

Nautilo: Your Own AI Workspace

Nautilo is the self-hosted workspace that puts you in total control of your AI partners. Think of it as a digital room where you bring in your own people and their digital assistants. You give each assistant a unique personality, memory, and voice, then you all write and plan together. Because you run the server and choose the models, your data stays yours. It is not just a chatbot; it is a shared creative space where humans and machines work side by side on real projects. You get the power of AI without giving up your privacy.

🆔 @hackernewsgithubprojects