📦 mihneaptu/opencode-fusion

opencode-fusion

Slash your AI coding costs by up to fifty-four percent by separating the brains from the brawn. This clever setup for opencode locks your expensive, high-intelligence main model out of editing files entirely, forcing it to focus only on planning, reviewing, and high-level strategy. When it is time to write code, the main agent hands precise specifications to a cheaper, lightning-fast sidekick model to do the actual typing. You get top-tier results and cross-vendor review for a fraction of the price. Give your budget a break and try opencode-fusion to experience smart, multi-model delegation today.

🆔 @hackernewsgithubprojects

📦 eps-acoustic-revolution-lab/ear_vae

ear_vae

Reconstruct studio-quality music with incredible spatial depth and crystal-clear high frequencies using a smart neural network designed to mimic how humans actually hear. While typical audio AI models struggle to keep stereo sound feeling wide and realistic, ear_vae solves this by introducing a brilliant perceptual filter and phase-aware training. This means it doesn't just look at raw math data; it optimizes for actual auditory perception, keeping your left and right channels in perfect sync. It is the ultimate tool for developers building next-gen audio generators who want their music to sound open, punchy, and alive.

🆔 @hackernewsgithubprojects

📦 kirakun0328/text-to-vrma

Text-To-VRMA

Text-to-vrma is the animation tool that finally lets you control 3D virtual avatars using plain text. Instead of spending hours manually editing keyframes, you just type a simple action like having a character happily jump or wave, and the app instantly generates a smooth movement file. By combining smart language models with a specialized motion engine, it automatically handles body physics, timing, and even natural facial expressions. You can drop in any virtual character, watch them move in real-time, and export the file instantly. It is a fantastic way to bring virtual characters to life without needing professional animation skills.

🆔 @hackernewsgithubprojects

📦 mysterypancake/houdini-opencl

Houdini OpenCL

Houdini artists can bypass standard vex programming and tap directly into their graphics card using the low-level power of OpenCL. The houdini-opencl repository provides much-needed documentation and examples for utilizing this incredibly fast but notoriously difficult language. While vex runs solely on the processor, OpenCL executes directly on the graphics card, making it ideal for heavy simulation tasks like feedback loops or neighbor calculations. However, it requires manual memory management and is highly prone to crashes. This project demystifies the setup, teaching developers how to bind data correctly and avoid memory leaks. It is the ultimate guide to unlocking maximum viewport performance.

🆔 @hackernewsgithubprojects

📦 shubhamj010/screenshotjanitor

ScreenshotJanitor

Keep your Android phone clutter-free by automatically sweeping away temporary screenshots you no longer need. This clever tool monitors your device in the background and intercepts every new screenshot you take, giving you a quick notification to archive, save, or delete it on the spot. If you do nothing, its built-in daily scheduler quietly runs in the background to clean up the leftovers and reclaim your storage space. It is completely local with no cloud integration, ensuring your personal photos stay private. It is the perfect, set-it-and-forget-it way to keep your gallery pristine without lifting a finger.

🆔 @hackernewsgithubprojects

📦 nesdev-org/mesence

mesence

Play classic console games across seven different retro systems using a single, high-performance application built for modern computers. The mesence project is a community-managed, multi-system emulator that lets you run games from iconic hardware like the NES, SNES, Game Boy Advance, and WonderSwan on Windows, Linux, and macOS. This community fork keeps the beloved emulator active, updating it to run on modern frameworks like dot net ten. It solves the hassle of managing separate emulators for every retro console by combining them into one fast, lightweight package that even runs on the Steam Deck, giving classic games a permanent home on modern hardware.

🆔 @hackernewsgithubprojects

📦 calesthio/generative-media-skills

Generative Media Skills

Equip your AI coding assistants with a massive library of specialized instructions to plan, direct, and refine professional-grade video, audio, and images. The generative-media-skills repository provides over one hundred and fifty research-backed agent skills covering everything from cinematography and sound design to automated quality checks. Instead of relying on generic prompts, your AI helper can consult deep operating knowledge of specific media tools, helping you coordinate complex workflows like syncing voiceovers, rendering 3D assets, and finishing videos with proper color grading. It is a brilliant way to turn standard language models into highly capable, detail-oriented digital media producers.

🆔 @hackernewsgithubprojects

📦 ruhan-wang/harness_handbook

Harness Handbook

Harness Handbook is the developer tool that turns entire codebases into structured, interactive maps to help AI coding assistants find where changes need to be made. Large software repositories can be completely overwhelming for a language model to digest, often causing it to miss critical files when planning updates. This project parses your source code and uses an AI to generate a highly organized, step-by-step handbook of your system architecture. When you feed this handbook to a code agent, it can easily navigate your files and pinpoint exactly where to make edits without drowning in context. Give it a try to build smarter, more precise coding assistants today.

🆔 @hackernewsgithubprojects

📦 bitpainter75/ferrumpix

FerrumPix

The desktop photo manager that actually bridges the gap between local files and your self-hosted cloud, FerrumPix is a free, open-source gallery and editor designed specifically for Linux and Windows. While it lets you browse local folders, crop images, and paint with brush tools, its real standout feature is a direct, built-in integration with Immich. You can view your cloud albums, download originals, and even edit your hosted photos, saving the polished results right back to your server. It is a surprisingly complete, lightweight tool built with modern tech that makes organizing your personal photo library feel incredibly simple.

🆔 @hackernewsgithubprojects

📦 tonyd2wild/glm-5.2-quanttrio-200k-4x-dgx-spark--36tok-s

glm-5.2-quanttrio-200k-4x-dgx-spark--36tok-s

The specialized cluster recipe that serving teams are using to run the massive GLM-5.2 model at full quality without deleting any of its two hundred fifty-six experts. Instead of surgically hacking the model down to fit on your hardware, this setup orchestrates four NVIDIA GB10 nodes to host the unpruned model at a massive two hundred thousand token context. It squeezes out up to thirty-six tokens per second using smart trickery like built-in speculative decoding and custom Triton kernels. It even includes an indexer patch to prevent multi-user crashes. If you want to deploy full-scale reasoning models across high-end hardware, grab this recipe, spin up your cluster, and start serving.

🆔 @hackernewsgithubprojects

📦 xang1234/stock-screener

Stock Screener

This multi-market stock scanner lets you run institutional-grade technical and fundamental scans across twelve global markets simultaneously, including the US, India, and Hong Kong, without paying for expensive data feeds. The platform orchestrates complex trading strategies like William O'Neil's CANSLIM and Mark Minervini's trend templates, combining eighty technical filters with an AI chatbot to research trending themes from live feeds. It solves the massive headache of managing scattered market data and high API costs by pulling information into a single, Docker-deployed system backed by PostgreSQL and Redis. Anyone looking to level up their trading workflow gets a self-hosted, industrial-strength screening pipeline that runs entirely on local hardware.

🆔 @hackernewsgithubprojects

📦 drsexo/frosty

Frosty

You can now reclaim your Android phone's battery life by freezing power-hungry background services with a single tap. Frosty is an advanced Magisk, KernelSU, and APatch module designed specifically to stop background battery drain and rein in persistent Google services. Through its clean web interface, it lets you disable unnecessary telemetry, automate screen-off power saving, and apply deep sleep optimizations without breaking your favorite features. It even auto-tunes system memory and block storage performance based on your device's actual hardware. It is the ultimate tool for anyone wanting complete, smart control over their phone's standby power.

🆔 @hackernewsgithubprojects

📦 open-compass/agentcompass

AgentCompass

Benchmark and evaluate your AI agents under realistic conditions using this unified testing suite. It runs parallel tests across over twenty major benchmarks to systematically grade how well your language models handle complex, multi-step operations like writing code, executing terminal commands, browsing the web, and navigating visual interfaces. By spinning up secure, isolated environments using Docker or Modal, it lets you safely watch your agents attempt real-world software engineering tasks and deep research assignments. You get back clear metrics and step-by-step trajectory graphs showing exactly where an agent succeeded or got stuck. Grab the repository to start stress-testing your agents today.

🆔 @hackernewsgithubprojects

📦 harahan/meanflownft

MeanFlowNFT

Train image and video generators to produce high-quality, aesthetic results in only four steps. This project introduces a clever way to apply reinforcement learning directly to fast, velocity-based AI generators without destroying their speed or efficiency. Usually, fine-tuning these models with human feedback rewards requires slow, complex calculations during training. This framework solves the problem by optimizing the model's trajectory in a simulated space while keeping the actual generator lightweight and fast. In practice, this means you can generate stunning media using Stable Diffusion and video models with incredible detail, beating older, slower methods. Give this repository a try to see how efficient AI generation can really be.

🆔 @hackernewsgithubprojects

📦 katipally/openlive

OpenLive

OpenLive is the open-source voice and vision layer that finally gives your favorite AI agents eyes and ears right on your own machine. Instead of renting an expensive, locked-in cloud pipeline, this clever tool runs your entire voice loop locally using WebGPU. It handles the listening, the speaking, and even screen sharing privately, letting you connect to almost any brain you want. You can voice-drive coding agents like Claude Code, answer permissions aloud, and even clone your own voice in seconds. It is the ultimate way to talk to your AI without paying extra audio fees.

🆔 @hackernewsgithubprojects

📦 siw00-lim/tango

tango

You can now edit 3D models with incredible precision without drawing a single manual mask. A clever new framework called tango makes 3D editing entirely training-free by steering the generative process in what mathematicians call tangent space. Instead of applying a clumsy global update that ruins the parts of your model you want to keep, it automatically targets only the areas that need to change. By amplifying guidance for tokens in the edit zone and softening it everywhere else, it keeps the original object's identity perfectly intact. It is a brilliant, math-driven shortcut to painless, localized 3D modifications.

🆔 @hackernewsgithubprojects

📦 pku-sec-lab/jetson-pi-edge

jetson-pi-edge

Run massive vision-language-action robot control models directly on low-power onboard hardware in real time. Running advanced artificial intelligence on a physical robot usually means dealing with painful lag that ruins smooth movement. This repository solves that by packing smart speedups like graph reuse and GPU-resident buffers into a lightweight runtime based on llama.cpp. It squeezes incredible performance out of compact devices like the NVIDIA Jetson, slashing latency by more than half so your robot can react instantly to visual feedback. Just spin up its persistent background server, feed in your camera feeds and robot states, and watch it generate lightning-fast physical actions.

🆔 @hackernewsgithubprojects

📦 internrobotics/real

Real

The robotics framework that finally bridges the gap between simulated training and real-world physical deployment. Real uses raw camera feeds and the Model Context Protocol to guide mobile robots through complex tasks like navigating rooms, finding objects, and opening doors. Instead of guessing, these robots can actually communicate with humans to clear up confusing instructions. It solves the classic simulation-to-reality bottleneck by matching virtual environments perfectly with physical hardware, achieving an incredible seventy-eight percent success rate in actual physical tests. If you want to see how robots are learning to interact with our open world, check out the Real repository.

🆔 @hackernewsgithubprojects

📦 michaelshimeles/adam

Adam

Adam is the clever port that takes Vercel's durable AI agent runtime, called Eve, and runs the entire execution engine directly inside Convex. Usually, running these complex, long-lived agents requires managing a heavy Node server, persistent databases, and message queues. Adam completely eliminates the server by compiling your agent loop and running it directly in Convex's serverless environment, keeping the workflow state, schedules, live streams, and UI together in one unified place. It is a fantastic project for developers because it simplifies deployment and ensures that even hours of complex AI steps run reliably without server maintenance. Check out Adam to see how serverless AI architecture is becoming incredibly simple.

🆔 @hackernewsgithubprojects

📦 qualtyco/api-doctor

api-doctor

The code linter that prevents AI-generated code from breaking your external integrations. While artificial intelligence is amazing at writing quick software drafts, it often hallucinates incorrect API structures, leaves out critical web verification steps, or hardcodes sensitive keys. To solve this, api-doctor uses deterministic structure-based rules rather than unpredictable AI models to scan your files. It instantly flags broken configurations for popular platforms like Supabase, Firebase, and OpenAI before they crash in production. Running this simple tool in your terminal ensures your third-party integrations stay secure, reliable, and functional without relying on another AI to double-check the first one.

📰 https://news.ycombinator.com/item?id=48762860

🆔 @hackernewsgithubprojects