📦 jpezzulli/sglang-rtxpro6000

sglang-rtxpro6000

sglang-rtxpro6000 is a personal, optimized runtime that lets you run large Qwen language models on a single RTX Pro 6000 Blackwell graphics card. This is not a toy project; it is a specialized build of the SGLang inference engine, tuned specifically for the SM 120 architecture found in that specific professional-grade GPU. The reason this matters is that running these heavy models usually demands expensive multi-GPU clusters or massive cloud bills, but this configuration squeezes serious performance out of one piece of hardware. It solves the problem of high inference costs by leveraging the specific strengths of Blackwell silicon.

🆔 @hackernewsgithubprojects

📦 sapientinc/hrm-text

HRM-Text: Train an AI for $1000

Sapient Inc just proved you can build a billion parameter language model for under one thousand dollars, which completely breaks the usual rules for AI development. This project uses a specialized architecture that repeats its internal logic to squeeze more intelligence out of fewer chips, cutting the required compute power by hundreds of times compared to standard methods. Instead of buying expensive hardware, you get a full training framework that runs on just a few high-end graphics cards to produce a model that handles math and reading comprehension surprisingly well. It is not just a theoretical idea but a complete toolkit with data processing and testing built in.

🆔 @hackernewsgithubprojects

📦 shengsheng90/dsh-taskboard

How AI Agents Manage Real Tasks

DSH Taskboard is the local plugin that gives AI agents a real job board. While most AI tools just chat, this project lets coding agents actually claim tasks, do the work, and submit results for your approval. It runs locally on your machine using a simple database, so your data stays private. The coolest part is that agents can't mark their own work as finished. They have to send it to you, a human, for final sign-off. It turns your AI assistant into a productive coworker that you can actually trust with real projects.

🆔 @hackernewsgithubprojects

📦 dachev/plan-review

Plan Review for Claude Code

Catch design mistakes before they become code. Plan Review for Claude Code sends your implementation plan to an independent A.I. reviewer, like Codex, before you start building. This catches logical errors while they are still cheap to fix, rather than discovering them in a messy code review later. The killer feature is that you stay in control. The system presents every finding as a simple choice. You decide whether to investigate a potential issue or dismiss it entirely. This ensures the A.I. doesn't just blindly apply changes, but works with you to refine the plan. It is a smart way to keep your coding workflow intentional and precise.

📰 https://news.ycombinator.com/item?id=49204661

🆔 @hackernewsgithubprojects

📦 edoardolunardi/kugiri

kugiri: Perfect Text Animations

kugiri cuts web text into lines, words, and characters exactly where your browser painted them, solving the age-old problem of broken text animations. Most libraries guess where words wrap, but this one reads the actual screen, ensuring right-to-left text, hyphenation, and special layouts stay perfect. You get simple data attributes to target each piece, letting you animate every letter or word with pure CSS or JavaScript. It is tiny, fast, and handles complex layouts without breaking your design. If you want text that moves exactly as it looks, this tool gives you the precision you need for polished web effects.

🆔 @hackernewsgithubprojects

📦 v1ki/dsh-plugin-subscriptions

dsh-plugin-subscriptions: Use your existing AI subscriptions in DSH without API keys

dsh-plugin-subscriptions is the DeepSeek Harness plugin that lets you use your existing ChatGPT, Claude, Grok, and GitHub Copilot subscriptions as direct LLM providers without ever generating or managing an API key. It solves the problem of juggling separate developer credentials and billing endpoints for every model you want to test, by handling the entire OAuth login flow directly inside the DSH web interface. You simply connect your accounts, and the plugin automatically discovers the available models, tracks your live subscription usage limits, and even pools multiple accounts to intelligently fail over when one hits a rate limit.

🆔 @hackernewsgithubprojects

📦 rion-wu-tech/wechat-intelligence-hub

WeChat Intelligence Hub

WeChat Intelligence Hub turns thousands of scattered chat messages into a single, searchable intelligence base that runs entirely on your own computer. It reads your local chat data without touching the cloud or sending anything, so you can finally find that one specific promise a client made last winter. The system tracks follow-ups, flags potential opportunities, and builds daily briefings so you never miss a beat. It is strictly read-only, meaning it analyzes your history rather than automating your replies. If you live in group chats, this is the missing layer that turns noise into actionable clarity, giving you a private, local dashboard for your most important conversations.

🆔 @hackernewsgithubprojects

📦 trentorch/trentorch

TrenTorch: Build Your Own PyTorch

TrenTorch is the coding curriculum that forces you to build your own machine learning framework instead of just importing one. Most people treat neural networks like a black box, but this project makes you write every single line of code on plain NumPy to recreate the actual machinery of PyTorch. It breaks the work into twenty progressive steps, guiding you from basic math all the way to building a real language model from scratch. The coolest part is that you are not just playing with toy problems. You are actually recreating historic milestones, like the original perceptron and the modern transformer architecture.

🆔 @hackernewsgithubprojects

📦 elliothux/open-compute

open-compute: The Self-Hosted Cloud

open-compute is the self-hosted platform that finally lets you run your Cloudflare Workers code on your own hardware without the usual infrastructure headache. It bundles the entire execution environment, database, and scheduling system into a single binary file, meaning you skip the need for Kubernetes or complex server clusters entirely. The standout feature is its perfect compatibility; your existing code runs unchanged with millisecond startup times, giving you full control over your data while maintaining the speed you expect from the cloud. If you want the power of edge computing without the vendor lock-in or the monthly bill, this is the tool to try.

🆔 @hackernewsgithubprojects

📦 tonyd2wild/qwen3.8-flash-next-nvfp4-dgx-spark

Running a 125B Model on One Box

A 125 billion parameter model now runs on a single, desktop-sized computer. The trick is that this repo keeps a massive lookup table on the hard drive, only pulling the specific pieces it needs for each word as it goes. It fits the rest of the brain into the machine’s memory without any compression tricks, serving text at speeds that rival much larger systems. This proves you can run the latest heavy language models on consumer hardware if you handle the memory smartly. It is a practical, measured guide for developers who want to test these big models without buying a data center.

🆔 @hackernewsgithubprojects

📦 vortrix5/sifty

Sifty: The Windows Cleaner That Actually Cares About Your Files

Sifty is the Windows maintenance tool that refuses to delete anything you cannot get back. While most cleaners send files to the void, this project routes every single removal through the Recycle Bin, meaning you can instantly undo your last cleanup if you change your mind. It also defaults to a dry-run mode, showing you exactly what it plans to touch before you give the go-ahead. This makes it the safest way to reclaim space from browser caches, old build files, and forgotten startup items. The interface is built for people who want control, not surprises, ensuring your system stays tidy without the risk of accidental data loss.

📰 https://news.ycombinator.com/item?id=48506948

🆔 @hackernewsgithubprojects

📦 amarnath3003/iot-claw

IoT-Claw: Your AI Smart Home

IoT-Claw is the local-first smart home platform that lets an AI agent actually fix your own devices. Most smart home setups break when a sensor goes offline or a network hiccups, but IoT-Claw has a built-in sandbox where the AI writes, tests, and debugs its own code to solve problems without you touching a wire. It connects to your cheap microcontrollers over Wi-Fi, so if your light stops working, the system figures out why, patches the script, and pushes the fix directly to the hardware. It’s basically a self-healing smart home that runs entirely on your own network, keeping your data private while it handles the tedious troubleshooting for you.

🆔 @hackernewsgithubprojects

📦 amarnath3003/dataset-creator-app

Dataset Creator App: Your All-In-One AI Lab

Dataset Creator App is the local workspace that finally puts dataset creation, model training, and testing under one roof. Most developers feel scattered across different tools for every step of the AI pipeline, but this project solves that by connecting the whole workflow in a single place. You feed it documents, and it automatically builds the training data, runs the fine-tuning on your own hardware, and then lets you chat with the result to see if it actually works. It even runs completely offline so your data stays private. If you want to build custom AI without touching the cloud, this is your all-in-one starter kit.

🆔 @hackernewsgithubprojects

📦 mcpfyy/mcpfy

mcpfy: One Line for Your AI Tools

Turn your AI models into powerful apps with a single line of code. mcpfy is a developer kit that takes the messy setup of connecting artificial intelligence to your data and makes it simple. Instead of writing hundreds of lines of boilerplate just to get started, you define your tools in plain TypeScript and run a single command to see them working. It handles the hard networking parts automatically, so you can focus on building the actual features your users need. If you have ever wanted to give ChatGPT or Claude hands that can fetch live weather or draw diagrams, this is the fastest way to do it.

🆔 @hackernewsgithubprojects

📦 liangmianya/dsh-synapse

Synapse: Your AI Chat Map

Synapse is the visual workspace that turns tangled AI chats into a navigable map. Instead of scrolling through endless text, you see every conversation, follow-up, and branch as a card on a single, draggable canvas. It plugs directly into DeepSeek Harness, syncing in real-time so your history stays perfect while you explore new ideas. You can even copy specific parts of a reply to spawn a new branch instantly. It’s like a whiteboard for your AI, helping you see how your thoughts connect without losing track. If you get lost in long chats, this is your shortcut back to clarity.

🆔 @hackernewsgithubprojects

📦 beamivalice/ponyexl3

Run 27B LLMs on Your Mac

Run a twenty-seven billion parameter language model directly on your Mac without a dedicated graphics card. PonyExl3 squeezes massive models into low bit formats that your Apple chip can process natively. The surprising part is that it does not just store these compressed weights; it decodes them on the fly inside the math engine. This means you get near full quality answers while using a fraction of the memory, fitting huge models into standard laptop hardware. It turns your everyday computer into a capable local inference station. If you want to test large language models locally without buying extra hardware, this is the tool to try.

🆔 @hackernewsgithubprojects

📦 hannay001/lockkeeper

Lockkeeper: The Firewall for Your AI Agents

Lockkeeper is the capability router that stops your AI coding agents from drowning in unnecessary tools. The problem is simple: modern agents install hundreds of skills and plugins, but most of that context is just noise that slows them down. Lockkeeper solves this by acting like a bouncer for your agent’s brain, picking only the eight or ten specific tools actually needed for your current task. The truly surprising part is its built-in firewall. It scans every new skill you install to catch hidden malicious instructions before they ever touch your code. It’s the security layer you didn’t know you needed for your AI toolbox.

🆔 @hackernewsgithubprojects

📦 amarnath3003/quickliquid

QuickLiquid: Real Glass for the Web

QuickLiquid calculates real optical refraction to bend the actual pixels behind your interface elements, creating genuine Apple-style liquid glass on the web. Instead of using a flat translucent layer that just looks fake, this library uses math to simulate how light physically bends through a curved surface. It handles everything from dynamic rim lighting to chromatic aberration, making buttons and cards feel like tangible objects made of solid material. Because it is heavily optimized with a smart caching system, you get this premium depth without sacrificing speed.

🆔 @hackernewsgithubprojects

📦 seeed-studio/kicad-mcp-server

KiCad MCP Server

Hand your AI assistant direct access to your KiCad hardware designs. This project connects your local circuit schematics and printed circuit boards to large language models through the Model Context Protocol. Instead of manually digging through files or guessing how parts connect, you can simply ask your chatbot to trace pin level connections or run design rule checks. It parses your files directly to find errors and validate your work. It is the perfect bridge between human creativity and machine precision. You draw the board, the AI does the heavy lifting.

🆔 @hackernewsgithubprojects

📦 vinzdg/codenotch

Codenotch: See Your AI Limits

Stop guessing if your AI is about to cut you off. Codenotch pins a tiny, sleek black bar to the edge of your Mac screen that instantly shows exactly how much of your usage limit you have burned for Claude, Cursor, and other coding tools. It works in the background without you needing to sign in again, just reading the data your apps already have. The coolest part is that it tells you if your AI is still working or if it’s stuck waiting for your input, so you never stare at a frozen screen wondering what went wrong.

🆔 @hackernewsgithubprojects