📦 vizart-vj/comfyui-aetherscale

AetherScale: Native DLSS 5 Video Enhancement for ComfyUI

Upscale your video clips using next generation neural rendering directly inside ComfyUI. AetherScale is a custom node pack that brings experimental DLSS 5 capabilities to your local machine. Instead of processing frames sequentially, it analyzes motion across the entire timeline to intelligently reconstruct details and remove artifacts. This is particularly useful for creators who want high quality output without uploading private footage to the cloud. It handles large video batches efficiently by streaming data through your graphics card, ensuring your memory doesn't get overwhelmed.

🆔 @hackernewsgithubprojects

📦 nvidia/personal-ai-router

Personal AI Router: Your Local AI Cluster

Personal AI Router is the local inference tool that finally lets your home computers work together. It turns a group of connected machines into a shared pool of processing power without any cloud connection. When you send a request, the router automatically picks the best available device to handle the task. This keeps your data private while giving you more computing muscle than a single laptop could provide. It is a clever way to maximize the hardware you already own. If you want faster local AI without renting a server, this is a fascinating tool to watch.

🆔 @hackernewsgithubprojects

📦 miuuyy/chatgpt-persona-voice

ChatGPT Persona Voice

A desktop app called ChatGPT Persona Voice swaps the assistant's default speech for any voice you pick, running entirely on your own computer without sending audio to the cloud. It works by quietly intercepting the sound from ChatGPT or Codex, converting it into your chosen character's voice in near real time, and then playing that new voice back through your speakers while muting the original. This means you can have the AI speak with a distinct, personalized identity, like a specific anime character or a custom recording, while keeping the conversation inside the standard interface.

🆔 @hackernewsgithubprojects

📦 aws-bench/aws-bench

aws-bench: Testing AI on Real Clouds

aws-bench puts AI coding agents to work in live, disposable AWS environments, forcing them to diagnose misconfigurations and provision infrastructure rather than solving static puzzles. This matters because it measures how these models handle the messy, dynamic reality of cloud operations. The framework spins up isolated accounts, deploys real infrastructure, and lets an agent attempt tasks like fixing a broken server or creating a new database. It then uses automated checks to see if the agent actually succeeded. This gives developers a clear, reproducible way to judge if an AI can truly do real cloud work.

📰 https://news.ycombinator.com/item?id=49570089

🆔 @hackernewsgithubprojects

📦 v4c38/spectacles-dimensional-os

Drive a Robot with AR Glasses

Steer a real robot with your eyes. Spectacles Dimensional OS turns Snap Spectacles into a controller for Unitree robots. You see the robot’s path and sensors right in front of you. No joystick needed. Just look where you want it to go. It even lets you talk to it. This is a cool look at the future of human robot interaction.

🆔 @hackernewsgithubprojects

📦 busabase/busabase

Busabase: The Database for AI Agents

Busabase gives AI agents a real database, not just a chat log. It solves the problem of scattered agent output by storing structured data, knowledge, and skills in one local workspace. The coolest part is the review layer: when an agent wants to change something, it sends a specific request that you can inspect and approve before it becomes permanent. It’s like giving your AI tools a safety net so they can actually do useful work without breaking your data. If you want your AI assistants to be helpful without being chaotic, this is the system to check out.

📰 https://news.ycombinator.com/item?id=48734021

🆔 @hackernewsgithubprojects

📦 gioblu/npc-forge

NPC-Forge

npc-forge builds chatbots that run entirely on your computer's basic processor without using any heavy artificial intelligence. It works by matching your words to a pre-written list of commands, so it responds in milliseconds and never hallucinates. The built-in helper, TERMy, even turns simple sentences like 'list files' into real terminal actions. No cloud, no training, just fast, predictable results. If you want a terminal assistant that actually respects your privacy and hardware, this is the way to go.

📰 https://news.ycombinator.com/item?id=49552623

🆔 @hackernewsgithubprojects

📦 stubbb/c-shop

C-Shop: The Image Editor That Edits Itself

Cutting out a dog from a photo used to mean lassoing pixels by hand, but C-Shop changes that with a simple script. This is not a web app in a wrapper or a bloated suite; it is a fast, single Rust binary that runs directly on your graphics card. The coolest part? It has a brain. You can ask it to find objects, clean up grainy skies, or even relight a shadowy scene, all without touching a mouse. It runs these smart tools in the background so your editor stays snappy. If you want a tool that does the thinking for you, this is the one to watch.

📰 https://news.ycombinator.com/item?id=49485024

🆔 @hackernewsgithubprojects

📦 yasirm0/loupe

Loupe: The Citation Checker That Runs Entirely In Your Browser

Loupe is a free, open-source tool that actually reads your research paper and checks if its citations truly back up the claims being made. You upload your draft and your source documents, and it runs entirely in your browser using your own AI provider, meaning no data ever touches a third-party server. The real kicker is that it doesn't just check if a source supports a claim, but also runs a dedicated pass to hunt for outright contradictions where a source says the opposite of what your paper claims. It even flags factual statements that have no citation at all, which is a classic sneaky mistake in academic writing.

🆔 @hackernewsgithubprojects

📦 yasirm0/scilene

Scilene: The Honest Guide to Journal Publishing

Scilene is the journal finder that actually tells you why it picked each journal. It solves the confusing, black-box problem of academic publishing by using simple, readable logic instead of opaque algorithms. The coolest part is its semantic search, which understands the meaning of your manuscript, not just keywords, so it finds journals that truly fit your work. You get a clear explanation for every recommendation, making the decision process transparent and stress-free. It is a smart, honest tool for researchers who want clarity, not just a list. It turns a frustrating guess into a confident choice. Give it a try and see the difference.

🆔 @hackernewsgithubprojects

📦 natpate/ninfer-windows

Ninfer Windows: Run Big AI Locally

Run massive artificial intelligence models directly on your single graphics card without any cloud connection. That is exactly what ninfer windows provides. It is a specialized engine built specifically for Windows users who want serious performance. Instead of relying on generic, slow software, this project includes hand crafted code that squeezes maximum speed out of your specific hardware. It supports popular, large language models and handles the complex math in a way that is incredibly efficient. If you have been waiting for a way to run heavy AI locally without a data center, this is the tool you need.

🆔 @hackernewsgithubprojects

📦 agentsafelabs/safelabs-eval

Safelabs Eval: How To Stress Test Your AI Agent

Safelabs Eval lets you stress test your AI agent to find hidden weaknesses before they cause real problems. It works by firing thirty specific adversarial prompts at your system to see if it leaks data or obeys malicious commands. The coolest part is that it scores the answers using simple pattern matching instead of calling expensive AI models, so it runs fast and costs you nothing. You get a clear report on exactly where your agent failed, without needing to rewrite your code. It is a straightforward way to check if your bot is actually safe. Try it out to see if your agent can handle a bit of pressure.

📰 https://news.ycombinator.com/item?id=48297782

🆔 @hackernewsgithubprojects

📦 danialkhilji/homeos

HomeOS: The Kitchen Screen That Runs Your House

Turn an old laptop into the brain of your house with HomeOS. It runs on a Linux mini PC and gives every family member a shared touchscreen to manage chores, shopping, and prayer times without pulling out a phone. The coolest part is how it handles weekly task rotation; it automatically resets chores every Monday so nobody has to remember to clear the board. You get a calendar, live weather, and a store-based grocery list that actually looks like a real app. Since it is self-hosted, your family data stays on your own machine, not in some cloud.

📰 https://news.ycombinator.com/item?id=49535594

🆔 @hackernewsgithubprojects

📦 ryzqi/learn-agent

Learn-Agent: Build Real AI Agents

Learn-agent is the Chinese tutorial series that actually teaches you to build production-grade AI agents. Instead of just reading about theory, you get twenty chapters of runnable TypeScript code that shows you exactly how to wire up tools, permissions, and memory systems. It solves the common problem of agents getting stuck or making mistakes by giving you a clear, step-by-step architecture that you can run on your own machine. Whether you want to understand how to keep an agent safe or how to make it work on complex tasks, this repo gives you the practical skills to do it.

🆔 @hackernewsgithubprojects

📦 haohervchb/sglang-v100

Run Qwen 3.8 on Four V100s

SGLang for V100 lets you run massive AI models on four aging graphics cards from 2017. Most people assume you need brand-new, expensive hardware to handle large language models, but this project proves otherwise. It takes a powerful inference engine and tweaks it specifically for the unique architecture of these older V100 chips. By using clever memory tricks and optimized code paths, you can actually serve modern models like Qwen 3.8 Flash on this legacy hardware. It is a fascinating look at how software engineering can bridge the gap between old hardware and new AI capabilities.

🆔 @hackernewsgithubprojects

📦 bradgroux/veritas-kanban

Veritas Kanban: The AI Truth Teller

Your AI agents are lying to you about progress, and Veritas Kanban is the antidote. It’s a local-first task board where every agent action is bound to a verifiable audit trail, meaning you get the unfiltered truth about where your project actually stands instead of just a cheerful status update. This lightweight orchestration harness gives you a visual board to track work while letting you plug in agents as optional layers, so you can see exactly what they did without trusting their word. It’s a clever way to keep AI honest while staying in control. If you’re running agents, this is the reality check you need.

🆔 @hackernewsgithubprojects

📦 ningbainb/deepseek-harness-desktop

DeepSeek Harness Desktop: The Zero-Setup AI Workspace

Install a fully functional artificial intelligence workspace on your Windows PC without touching a single command line. DeepSeek Harness Desktop bundles the entire coding environment, including terminal access and mobile remote controls, into a single installer that requires no prior setup. It solves the tedious problem of manually configuring complex AI agents by handing you a ready-to-run application with built-in plugins and visual themes. This means you can start building with advanced language models immediately, bypassing the usual technical hurdles. If you want to test powerful AI tools without the configuration headache, this is the straightforward way to begin your next project.

🆔 @hackernewsgithubprojects

📦 omdsh-dev/dsh-mnemon

DSH Mnemon: The Missing Memory Layer

DSH Mnemon gives your coding agent a proper long-term brain so it actually remembers what it learned. Instead of forgetting everything between sessions, it splits knowledge into three clear buckets: quick notes for right now, full documents for deep dives, and persistent facts for everything else. The coolest part is that it lets you plug in almost any memory backend you like, so you are never locked into one specific database. It turns a chatbot that keeps losing context into a reliable partner that recalls decisions you made months ago. If you are tired of repeating yourself to your AI, this is the layer that finally fixes it.

🆔 @hackernewsgithubprojects

📦 saurabhav88/enviouswispr

EnviousWispr: Private AI Dictation for Mac

EnviousWispr turns your Mac into a private dictation machine that never sends your voice to the cloud. It runs entirely on your Apple Silicon chip, using local models to transcribe speech in under a second. The standout feature is their custom AI polish model, which cleans up grammar and filler words right on your device, so your audio never leaves your computer. It’s free, open source, and works fully offline. If you want to type faster without sacrificing your privacy, this is the tool to watch.

📰 https://news.ycombinator.com/item?id=48963964

🆔 @hackernewsgithubprojects

📦 kunchenguid/vision

Vision: The AI Skill That Finds Your Project's Soul

Vision is the coding assistant that finally writes down what your project actually stands for by reading your past work. Instead of asking you to list vague values, it studies your real history of accepted and rejected code to draft a concrete vision document. The surprising part is how it tests that draft by throwing tough, hypothetical scenarios at you on a simple review board. You decide whether a new idea fits your project, and the tool updates the writing based on your answers. This creates a clear rulebook that helps humans and machines agree on what the project is and is not.

🆔 @hackernewsgithubprojects

📦 sylvinus/agent-vm

agent-vm

agent-vm lets you run autonomous A.I. coding agents inside a safe, isolated Linux virtual machine while keeping your actual computer completely untouched. The tool creates a lightweight Debian environment that mounts only your current project folder, meaning the A.I. can execute any command, install dependencies, or run containers without ever exposing your personal files, cloud credentials, or system keys to potential supply-chain attacks. You get a fully equipped workspace with Docker and a headless browser ready to go, so you can let the agent work with full permission without worrying about accidental damage or malicious code.

📰 https://news.ycombinator.com/item?id=47301380

🆔 @hackernewsgithubprojects