📦 wangjiangshan0725/elastic-dit

Elastic Diffusion Transformer

Make massive AI image generators run twice as fast without making them look worse. That is exactly what Elastic Diffusion Transformer does. Usually, these heavy models waste time crunching the same math for every single picture. This new method adds a tiny smart switch to each step. It watches the specific image being made and decides if that step is even needed. If it is, it shrinks the workload just enough to save power. The result is a huge speed boost for tools like Qwen-Image, with almost zero drop in quality. It is not just a trick; it is a smarter way to build the future of creative AI.

🆔 @hackernewsgithubprojects

📦 blueforcer/comfyui-dlss5-enhancer

ComfyUI DLSS5 Enhancer

NVIDIA's newest neural renderer, designed to reconstruct skin and lighting details in video games, now runs directly inside ComfyUI. This project bridges a gap by feeding your image batches or video files through the exact same native renderer used in gaming engines, rather than relying on generic filters. It recovers material responses like skin texture and hair structure that standard processing simply misses. Because it uses the genuine rendering engine, it delivers a level of realism that is difficult to achieve with typical software tools. It is not a simple sharpening filter, but a reconstruction of physical light behavior.

🆔 @hackernewsgithubprojects

📦 inclusionai/llada-image

LLaDA-Image: One Model, Two Jobs

LLaDA-Image is the open-source image generator that finally stops forcing you to pick between creating art and editing it. Most tools force you to download one model for drawing from scratch and a totally different one for touching up that drawing, which is messy and confusing. This project solves that by using a single, unified brain to handle both jobs perfectly. You can type a description to get a photorealistic photo, or hand it a picture and ask for changes like making it look like a watercolor painting, all without switching tools.

🆔 @hackernewsgithubprojects

📦 saganaki22/comfyui-breeze-tts-2

Breeze TTS 2: The Voice Actor Node for ComfyUI

Breeze TTS 2 is the ComfyUI node pack that turns text prompts into actual character performances. It solves the problem of robotic narration by letting you clone specific voices or design new ones from scratch, right inside your existing workflow. The coolest part is the multi-speaker dialogue feature, which lets you wire up to eight distinct characters into a single script and generate a full conversation in one go. You can even add inline vocal events like sighs or laughs directly in the text to make the delivery feel natural.

🆔 @hackernewsgithubprojects

📦 atlascloudai/awesome-gpt-image-2-prompts

The Global Library for AI Image Prompts

A single GitHub repository now hosts a living, multilingual library of text prompts that tell artificial intelligence exactly what to draw. This project, called Awesome GPT Image 2 Prompts, solves the problem of guessing how to get the best results from image generators by collecting proven, high-quality instructions from creators around the world. The most surprising fact is that the collection is not static; it updates automatically every four hours, pulling fresh, vetted entries from a global community that speaks seventeen different languages. You can submit your own creations through a simple form, and if they meet the quality standards, they join the main list and a searchable web gallery.

🆔 @hackernewsgithubprojects

📦 agjs/gb10-clock-cap

GB10 Clock Cap: Cooler, Quieter, Smarter

The GB10 clock cap is the tuning tool that turns your hot inference server into a cool, efficient workhorse. It solves the problem of excessive heat and power draw by lowering your graphics chip speed, which surprisingly costs almost nothing in real performance. The project runs a smart test that checks your system, measures the difference, and even installs the setting automatically so it sticks after a restart. You get a cooler machine that uses far less energy while still serving your requests quickly. It is the perfect fix for anyone running large language models on dedicated hardware.

🆔 @hackernewsgithubprojects

📦 plannotator/artifact-server

Artifact Server: Where AI Agents Publish Work

Artifact Server is the self-hosted hub that keeps your AI-generated designs and code organized and under your control. It solves the messy problem of scattered digital assets by giving developers and AI agents one secure place to publish, review, and version their work. The standout feature is its built-in connection tool, which allows AI agents to upload files and share review links directly within your own infrastructure. You are no longer locked into a third-party platform; instead, you host the server yourself to keep full ownership of your data.

📰 https://news.ycombinator.com/item?id=49554724

🆔 @hackernewsgithubprojects

📦 arahim3/kaggle-tpu-lab

kaggle-tpu-lab

A free cloud platform can now host a massive artificial intelligence model that responds nearly as fast as you can type. The project called kaggle-tpu-lab turns Kaggle's complimentary hardware into a private, high-speed server for a top-tier language model. It delivers a public connection that coding tools can use directly without expensive cloud bills or complex setup. The system handles huge amounts of text at once, making it practical for long conversations and complex tasks. You can launch it with a single command and let the software handle the heavy lifting in the background. This setup proves that powerful, fast AI does not require a big budget or specialized knowledge.

🆔 @hackernewsgithubprojects

📦 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