📦 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

📦 iapp-technology/openthai-systemone

OpenThai-SystemOne: The Tiny AI Brain

Classify customer complaints, score news topics, and control video games in real-time without generating a single word of text. That is the core promise of OpenThai-SystemOne, a tiny open-source model that answers specific questions about a situation in a single lightning-fast pass. It is built on a Qwen base but replaces the standard text-generation part with a specialized decision head that reads a situation and immediately outputs calibrated probabilities for your specific options. It handles Thai and English natively, making it incredibly useful for routing tickets, checking content safety, or even playing Doom by reading the game state.

🆔 @hackernewsgithubprojects

📦 frontiercs/frontiersmith

FrontierSmith: AI-Generated Coding Problems

An AI system is now inventing brand new algorithmic puzzles that human programmers have never seen before. The project called Frontier Smith solves a major bottleneck in software training by synthesizing open-ended coding problems at scale. Instead of relying on a fixed collection of old textbook exercises, this pipeline uses large language models to create fresh, complex challenges and even writes the test scripts needed to verify if your code works. This is useful because it allows developers to practice on novel scenarios that mirror real-world engineering, rather than just memorizing standard solutions.

🆔 @hackernewsgithubprojects

📦 nokia-applied-research/anyjev

AnyJev Makes LLMs Tell the Truth

A standard language model will change its answer just because you rearranged the list of options. AnyJev from Nokia Applied Research fixes that by turning any open model into a decision maker that gives you a real probability you can actually trust. It works without training, using a clever trick to average out the model’s bias so the confidence score means what it says. This lets you automatically handle a huge chunk of traffic safely instead of sending everything to a human. It is a neat way to make AI decisions reliable without touching the model weights, which is pretty clever for a tool that needs zero labels to start.

🆔 @hackernewsgithubprojects

📦 beniedev/moonbite

Moonbite: The Memory Layer for AI Agents

Moonbite is the continuity layer that gives long-running AI agents a real sense of time. Most AI systems forget everything the moment a chat session ends, which makes them useless for work that spans days or weeks. Moonbite fixes this by adding a structured memory system that remembers past events, tracks current context, and decides when an action actually matters. It does not replace your AI assistant but sits quietly behind it, ensuring the model knows what happened yesterday before it speaks today. If you are building agents that need to stick around, this is the missing piece that keeps them coherent.

🆔 @hackernewsgithubprojects

📦 pinto0309/ocec

OCEC: The 112 KB Eye Detector

The tiniest eye detector in the wild is a mere one hundred and twelve kilobytes, yet it judges if eyes are open or closed in less than a millisecond. Named OCEC, this ultra-lightweight model solves a specific problem: most computer vision tools are too heavy for real-time tracking on low-power devices. By analyzing tiny twenty-four by forty pixel crops, the project provides a training pipeline and several model sizes that balance speed and accuracy. This is useful for anyone building responsive interfaces or accessibility tools where processing power is limited.

🆔 @hackernewsgithubprojects

📦 pulse-energy-eu/slopshape

SlopShape: How to Spot AI Writing

SlopShape lets you spot AI-written business articles without reading a single word. Instead of looking for specific keywords or grammar errors, this research project measures the hidden structural habits of text. The team compared thousands of real human blogs against AI versions written by five different models. They found that AI posts follow predictable patterns in how they organize ideas, which remain visible even if you rewrite the sentences. This tool creates a reliable way to verify content authenticity on the web. If you rely on online articles for business decisions, knowing how to filter out machine-generated filler is becoming an essential skill for staying informed.

🆔 @hackernewsgithubprojects