📦 hm-runninghub/comfyui_rh_minmaxh3

Generate Video and Audio Simultaneously with MiniMax-H3

MiniMax-H3 generates synchronized video and audio at the same time instead of adding sound after the video is already done. This ComfyUI plugin brings that joint generation process into your workflow, letting you create content where the visuals and the soundtrack are built together from the start. You can drive the generation with simple text prompts, use a starting image to animate a scene, or chain together video and audio references for precise control. The best part is that it runs smoothly on a single twenty-four-gigabyte graphics card by using smaller, optimized model weights.

🆔 @hackernewsgithubprojects

📦 ucsc-vlaa/visualclaw

VisualClaw: The AI Agent That Evolves Its Own Brain

VisualClaw is the modular agent system that finally gives AI a way to learn from its own mistakes in real time. Most AI tools just guess when they fail, but VisualClaw actually keeps score. It watches what the AI does, spots the exact moment it messes up, and then writes a new, better set of instructions for next time. Think of it as a robot that gets smarter every time it drops a tray. It handles video, remembers past conversations, and even works with smart glasses. It turns a dumb, one-trick AI into a self-improving assistant that gets better the more you use it.

🆔 @hackernewsgithubprojects

📦 mikeluu99/searxng-rust

Searxng Rust: Multi-Engine Search Aggregator

Searxng Rust lets you build a private search engine that checks multiple sources like DuckDuckGo and Brave at once, then blends the results into a single clean list. It solves the annoyance of searching multiple sites individually by automating the comparison process. The cool part is its ranking system, which gives higher scores to pages that show up in several engines, proving their relevance. It strips out tracking links to keep results clean and returns everything as simple JSON, making it a perfect tool for developers who want a fast, customizable search experience without relying on big tech.

📰 https://news.ycombinator.com/item?id=49158141

🆔 @hackernewsgithubprojects

📦 poxk/falco

Falco: A Tiny Browser Engine in Rust

Falco is a tiny browser engine written from scratch in Rust that renders web pages to PNG images or live interactive windows without relying on Chromium or WebKit. It builds every component including the HTML parser, CSS engine, layout system, and JavaScript virtual machine from the ground up. The project supports modern features like CSS Grid and Flexbox while keeping the binary size remarkably small. You can feed it a URL or local file and get a high-quality screenshot, or open a live window to scroll, click links, and fill out forms. It is a fascinating look at how a browser actually works under the hood.

📰 https://news.ycombinator.com/item?id=49146759

🆔 @hackernewsgithubprojects

📦 cursor/mixture-of-kittens

Mixture of Kittens: The MoE Megakernel

Mixture of Kittens is a custom training megakernel for Cursor that squeezes up to two and a third times more speed out of NVIDIA Blackwell chips by merging all expert computations into one single block of code. It completely removes the usual bottleneck of talking back and forth between your processor and graphics cards, letting the GPUs chat directly with each other while crunching numbers at lightning speed. This means you can train massive language models without wasting time waiting for slow data transfers, effectively turning a chaotic assembly line into a silent, synchronized dance of pure computation.

🆔 @hackernewsgithubprojects

📦 codegraph-ai/codegraph

CodeGraph: Your Codebase as a Searchable Map

CodeGraph turns your sprawling codebase into a living map that AI agents can actually read. Instead of blindly scanning files, it builds a detailed graph of functions, classes, and connections, then serves that structure through forty-two tools. Think of it as giving your coding assistant a complete overhead view of the project, highlighting exactly how pieces relate. It tracks which functions call others, spots unused imports, and even checks if your documentation matches the actual code. You can even save debugging notes for future sessions so the agent remembers past fixes.

🆔 @hackernewsgithubprojects

📦 xmarre/comfyui-spectrum-minimax-h3

ComfyUI Spectrum MiniMax H3

Speed up your MiniMax H3 video and audio projects by skipping expensive steps. This tool predicts the next phase of your generation instead of recalculating it from scratch. It learns from past steps to forecast the outcome, cutting generation time by over a third. You might notice small shifts in fast motion or fleeting details, but the speed gain is real. Try it when speed matters more than perfect pixel accuracy.

🆔 @hackernewsgithubprojects

📦 nihalashetty/forge

Build AI Agents Visually with Forge

Build, test, and ship AI agents visually without writing code or handing over your data. Forge lets you drag and drop agents, tools, and logic onto a canvas to wire them together, then deploy them anywhere you choose like an API, email, or a website widget. The coolest part is it stays entirely on your own infrastructure, so you keep full control without vendor lock-in. You can even watch the AI build itself in real time. It’s perfect for developers who want the power of custom AI workflows without the messy backend plumbing. Grab it, host it, and start building smarter automations today.

🆔 @hackernewsgithubprojects

📦 hermannbjorgvin/clawdmeter

Clawdmeter: Your Desk Dashboard for AI Usage

Watch your Claude Code usage climb right on your desk. Clawdmeter is a tiny ESP32 dashboard that connects over Bluetooth to your computer and displays your session and weekly API limits. The coolest part is the pixel art mascot, Clawd, which gets busier and more frantic as you burn through your quota, giving you a funny visual cue when you are getting heavy. It even doubles as a keyboard, sending space and tab shortcuts directly to your app so you can control voice mode without touching the mouse.

🆔 @hackernewsgithubprojects

📦 neelm0906/mference

Run Huge AI Models on 8GB Macs

Mference lets you run massive artificial intelligence models on small Apple computers by keeping only the active parts in memory while streaming the rest from your hard drive. It uses Swift and Metal to pull data directly from your solid-state drive, allowing huge systems with billions of parameters to work on just eight gigabytes of random access memory. You get a simple app to chat with large language models or a server you can connect to locally without uploading your data to the cloud. It is a clever way to keep your private conversations private while enjoying powerful computing on everyday hardware.

🆔 @hackernewsgithubprojects

📦 makazhanalpamys/soup

Train an 8B Model on a 4GB Laptop

You can actually fine-tune a massive eight billion parameter AI model on a laptop with just four gigabytes of graphics memory. That sounds impossible until you see how this tool called Soup works. Instead of trying to load the entire model into your video memory all at once, which usually crashes your machine, Soup uses a clever technique called layer streaming. It feeds the AI model to the GPU one piece at a time while keeping the heavy frozen parts sitting in your regular system RAM. This means you can train powerful models right on your own hardware without needing expensive cloud servers or specialized data center cards.

📰 https://news.ycombinator.com/item?id=49166984

🆔 @hackernewsgithubprojects

📦 yhfgyyf/vllm-deepseek-v4-sm89

Run DeepSeek V4 Flash on RTX 4090 with vLLM

This is the vllm-deepseek-v4-sm89 project, the hardware bridge that finally lets you run the massive DeepSeek V4 Flash model on standard RTX 4090 graphics cards using vLLM. Most people think this powerful AI requires expensive enterprise server chips, but this repository patches the underlying code to translate complex neural network operations into instructions your consumer GPU can actually understand. It effectively unlocks the full speed of this advanced language model on hardware you can buy today. By bridging the gap between high-end model architecture and accessible hardware, it proves you do not need a data center to experiment with state-of-the-art artificial intelligence.

🆔 @hackernewsgithubprojects

📦 neuroaihub/brainpilotbench

BrainPilotBench

BrainPilotBench turns scientific research into a fair test. It gives artificial intelligence agents four real neuroscience jobs, like analyzing brain scans or decoding neural signals, then grades them on the actual code and figures they produce instead of just how they behave. This removes guesswork by using strict, pre-set rules to score every submission, ensuring that only systems that truly understand the science get top marks. It is the first benchmark where you can trust the results because the scoring is handled by maintainers who protect the test data from leaks.

🆔 @hackernewsgithubprojects

📦 leonickson1/swiftlet

Swiftlet: Run Giant AI on Your iPhone

Swiftlet is the open-source runtime that lets you run massive, billion-parameter artificial intelligence models on ordinary Apple devices, including standard iPhones. Most large language models require gigabytes of RAM to stay active, but Swiftlet takes a clever shortcut by keeping only a small, essential part of the model in memory and streaming the rest directly from your storage chip just in time. This means you can chat with huge language models on your phone without needing a powerful computer or an internet connection. It is a brilliant example of optimizing code to run beautifully on everyday hardware.

📰 https://news.ycombinator.com/item?id=49158333

🆔 @hackernewsgithubprojects

📦 atlascloudai/awesome-seedance-2.5-prompts-skills

Awesome Seedance 2.5 Prompts Skills

This repository packs over a hundred carefully chosen video prompts for Seedance 2.5, each paired with a real video preview so you actually see what works. It goes further by offering an installable agent skill that helps you plan, optimize, and build storyboards before the video even starts, turning vague ideas into clear shots. You get reliable workflows for everything from simple single clips to complex sequences with consistent characters and products. The project explains how to stitch scenes together, handle transitions, and fix common drift without guessing. It is a practical guide that saves hours of trial and error.

🆔 @hackernewsgithubprojects

📦 mingti-org/phyai

PhyAI: Fast AI for Robots

PhyAI lets robots think and react in real time by running heavy AI models directly on tiny edge devices like NVIDIA Jetson boards. It solves the frustrating lag that usually makes robotic controls feel clumsy or unresponsive. Instead of waiting for slow cloud servers, this framework squeezes out maximum speed using specialized coding tricks and smart memory management. It even supports fancy data compression techniques to keep things fast without losing accuracy. Whether you are testing on a single chip or scaling to huge server clusters, it handles both smoothly. This is a game changer for building robots that feel truly responsive.

🆔 @hackernewsgithubprojects

📦 osilly/vision-deepresearch

Vision-DeepResearch: AI That Actually Looks Around

Teach an AI to actually look around before answering by letting it search the web dozens of times instead of just guessing. This project trains multimodal models to treat images as starting points for long, iterative investigations. It combines visual understanding with hundreds of search engine queries to solve tricky questions that simple chatbots miss. The researchers also provide a benchmark to test how well these models handle this extended reasoning process. It is fascinating to see how adding search turns transforms a dumb image viewer into a curious investigator.

🆔 @hackernewsgithubprojects

📦 prism-shadow/gdpevo

GDP Evo: Testing AI Self-Evolution on Real Tasks

GDP Evo lets artificial intelligence agents learn and improve themselves by tackling actual business problems instead of just solving math puzzles. Think of it as a practice ground where AI gets handed real-world memos about things like warehouse shipments or monthly accounting closings. It watches how these digital assistants figure out the right steps to handle the paperwork and then measures whether they actually got better at the job over time. This is a big deal because most tests are too abstract to tell us if AI can truly handle the messy, complicated tasks we deal with every day.

🆔 @hackernewsgithubprojects

📦 jd-opensource/joyai-video-edit

Edit Live Video with JoyAI Video Edit

Watch JoyAI Video Edit transform a live video stream in real time using just a text instruction. Instead of waiting for an entire clip to finish or processing it in slow batches, this system edits frames the moment they arrive. It combines a large language model to understand your request with a diffusion engine that paints new pixels on the fly. The result feels like magic, letting you swap backgrounds, change clothing styles, or remove objects as you watch the screen. It achieves thirty frames per second, turning video editing from a tedious, offline chore into an instant, interactive experience that feels surprisingly natural.

🆔 @hackernewsgithubprojects

📦 xiaobin-rong/unipase

UniPASE Speech Enhancement

UniPASE transforms noisy audio into crystal-clear speech without adding weird robotic artifacts, a rare feat in generative models. This repository offers the official implementation of a state-of-the-art system designed to clean up voice recordings while keeping them sounding natural and authentic. It works by stripping away background noise and intelligently reconstructing missing sound details rather than just deleting bad parts. You get ready-to-use checkpoints that handle everything from basic clarity to fixing dropped audio packets. The setup is straightforward, requiring only standard Python libraries like PyTorch and SciPy to run inference on your own files.

🆔 @hackernewsgithubprojects

📦 fzkuji/gui-agent-harness

GUI Agent Harness

Give it a simple task and watch it operate your entire desktop. This project turns any AI into a GUI automation agent. You type a request like 'open the settings menu,' and it autonomously takes screenshots, spots buttons, and clicks for you. The cool part is its visual memory. It learns what interfaces look like after one look and remembers them later, so it gets faster every time. It even zooms in repeatedly to find tiny buttons you’d normally miss. It works on Mac, Windows, and Linux, using local or remote machines. It’s basically a digital assistant that can actually use a computer instead of just talking about it.

🆔 @hackernewsgithubprojects