📦 debpalash/voicestudio

VoiceStudio: Your Local Voice Lab

VoiceStudio is the local voice studio that lets you clone, dub, and create audio entirely on your own hardware. While most voice tools require cloud servers and subscriptions, this open-source app keeps your data private by running sixteen text-to-speech engines and eleven transcription engines locally. You can clone a voice from a short clip, dub videos in hundreds of languages, or generate audiobooks without sending a single byte to the internet. It works on macOS, Windows, and Linux, offering a private, offline alternative to hosted services that gives you full control over your creative output.

🆔 @hackernewsgithubprojects

📦 molbal/comfyui-gguf

ComfyUI GGUF: Run Huge AI Models on Small GPUs

ComfyUI GGUF lets you shrink massive AI image models so they actually fit on your modest graphics card. Without this tool, those heavy transformer models would crash your computer or crawl at a snail’s pace. The project compresses the data into a special format, keeping quality high while slashing memory usage. It even includes a handy tool to convert your existing files in one go. This means you can test expensive AI models without buying a new workstation. It is a clever workaround that saves both money and space. Give it a try if you want to experiment with big models on a budget.

🆔 @hackernewsgithubprojects

📦 ogulcancelik/herdr-browser

Herdr Browser: Watch Your Agents Browse

Herdr Browser is the terminal plugin that finally lets you see what your AI agents are actually doing in the browser. Usually, browser automation is a blind spot where you just guess if it worked or stare at static screenshots later. This tool renders a live, interactive Chrome view directly inside your terminal layout. The best part is that while an agent drives the browser, you can grab the mouse and type right over its shoulder without stopping the process. It is like having a co-pilot who can take the wheel at any moment. No more detached windows or invisible headless runs.

🆔 @hackernewsgithubprojects

📦 shy3130/tickflow-stock-panel

The Self-Hosted Stock Analyzer

TickFlow Stock Panel runs a full quant desk on your own computer, handling stock picking, live monitoring, and backtesting without any cloud dependency. The standout feature is its AI-powered strategy builder, which lets you describe a trading idea in plain language and generates a testable rule instantly. It then scans the entire A-share market in milliseconds to find matches. You can run this locally via Docker, making it a private, zero-maintenance tool for serious hobbyists. It is not a stock picker, but a playground to test your own logic safely. If you want to understand how quant tools actually work, this open-source project is the perfect place to start.

🆔 @hackernewsgithubprojects

📦 anthropics/claude-plugins-community

Claude Plugins Community Marketplace

Anthropic maintains a strict gatekeeper for its new AI agents, ensuring every community-submitted tool passes automated security scans before hitting your terminal. This read-only mirror, called Claude Plugins Community, acts as the public registry for those vetted extensions. Instead of hunting for scattered add-ons, developers can now install trusted skills like simple explainer tools or complex video generators directly into Claude Code with a single command. It turns the chaotic world of third-party AI extensions into a curated, safe library that updates nightly. You don't need to worry about unverified code breaking your workflow, making it the safest way to supercharge your AI development stack today.

🆔 @hackernewsgithubprojects

📦 fzakaria/nixpkgs-multiverse

Get Any Version of Any Nix Package in One Command

Nixpkgs-multiverse lets you grab any version of any package from the entire thirteen-year history of Nix, all from a single flake input. Instead of juggling pinned commits or hunting through old build logs, this tool acts as a massive archive of every package version that has ever existed. It solves the annoying problem of needing a specific older version without downloading and evaluating a massive code tree every time. The coolest part is the speed; it uses a clever shortcut to pull pre-built binaries directly from the cache, so you can run old software in seconds. It’s like having a time machine for your dependencies, but without the heavy lifting.

🆔 @hackernewsgithubprojects

📦 chirpz-ai/pandaprobe

PandaProbe: Debug Your AI Agents Like a Pro

PandaProbe is the open-source tool that finally lets you see exactly what your AI agents are doing inside. It records every step your agent takes, letting you trace decisions, test performance, and fix issues before they reach your users. This is huge because debugging AI usually feels like guessing in the dark, but PandaProbe gives you the controls you need. Whether you are building on LangGraph or CrewAI, it plugs in easily to make your AI reliable and easy to manage. Stop guessing, start debugging with confidence.

🆔 @hackernewsgithubprojects

📦 adnanakil/nobuzz

NoBuzz Fixes Claude's Clickbait Voice

NoBuzz stops your code assistant from sounding like a hyped-up influencer. You know that annoying habit where it calls simple bugs load-bearing assumptions and ends every answer with a dramatic kicker? This skill fixes it. It takes the text and sends it to a different AI model just to translate the drama back into plain English. You can even pick who you're talking to, like a peer or a boss, and get the right level of detail without the fluff. It is a clever way to keep the smart answers but ditch the annoying voice. Your code stays clean, and your eyes stay open.

🆔 @hackernewsgithubprojects

📦 sergiiob/intel-arc-pro-b70-inference-cookbook

Battlemage GPU Hacks: 160 Tokens Per Second

A single Intel Arc Pro B70 graphics card is pushing a massive thirty-five billion parameter AI model at one hundred sixty tokens per second, which sounds impossible for a discrete GPU with that price tag. This open cookbook gives you the exact recipes, engine patches, and benchmark harnesses needed to get those numbers on Intel's Battlemage hardware. It solves the problem of opaque performance data by proving exactly how to configure inference engines for maximum speed on these specific chips. If you are looking to run large language models locally on Intel graphics, this is your definitive guide to making it actually fly.

🆔 @hackernewsgithubprojects

📦 xmanrui/dsh-im

Turn Any Chat App Into Your AI Agent

Turn any chat app into a direct line to your local AI agent. DSH-IM lets you scan a QR code or enter a simple token to connect nine different platforms, like Telegram, Discord, and Slack, to a private AI harness on your computer. You can talk, share images, and manage tasks right inside your favorite chat window without needing any complex server setup or public IP addresses. It bridges the gap between casual messaging and serious coding work, keeping your data local while giving you instant access to powerful tools. It is the cleanest way to bring smart automation into your daily conversations.

🆔 @hackernewsgithubprojects

📦 nari-labs/nari-qwen3-tts

Nari Qwen3-TTS: Instant Speech Generation

Turn text into human-sounding speech in under fifty milliseconds, all running on just one high-end graphics card. Nari Qwen3-TTS is a specialized tool built specifically to run the Qwen3 speech model at incredible speed. The problem it solves is simple: most text-to-speech systems feel sluggish, forcing you to wait seconds for audio to appear, which makes building real-time voice apps frustrating. This project crushes that delay, delivering sound almost instantly even when handling many requests at once. It’s incredibly useful if you need fast, responsive voice features without managing a massive server cluster, proving that heavy AI models can be made to fly.

🆔 @hackernewsgithubprojects

📦 musoyangrigor/gitx-skill

GitX: The AI Skill That Cleans Up Your Messy Commits

GitX is the portable AI skill that turns chaotic agent edits into clean, logical Git history. If you have ever stared at a wall of code changes from an AI tool and panicked about how to commit them properly, this is your fix. GitX plugs into agents like Claude or Cursor to automatically group your work, write smart conventional commit messages, and even handle branch creation and pull requests for you. It handles the boring, risky parts of Git so you do not have to think about merge conflicts or secret scanning.

📰 https://news.ycombinator.com/item?id=49401487

🆔 @hackernewsgithubprojects

📦 westpoint-io/mimik

Record Your Workflow as You Click with Mimik

Hit record, perform your browser task, and watch a polished step-by-step guide assemble itself in real-time. Mimik is a local browser extension that captures every click and keypress to instantly create annotated screenshots, eliminating the tedious work of manual documentation. The standout feature is its Guide Me mode, which allows you to replay your recorded steps directly on the live webpage, highlighting the next element and guiding the viewer through the process without needing to leave the site. Because everything runs locally, your sensitive data never leaves your device, making it a secure way to document internal tools or create tutorials.

📰 https://news.ycombinator.com/item?id=48098187

🆔 @hackernewsgithubprojects

📦 neeeophytee/agent-stylebooks

Agent Stylebooks: Why AI Needs Editorial Rules

Agent Stylebooks is the collection of writing guides that stops AI from guessing at tone. Instead of asking a model to just sound human, you install a specific editorial system, like the one from the Centers for Disease Control or the government of the United Kingdom. The project takes proven public style guides and turns them into simple files that tell your coding assistant exactly how to structure a sentence. It turns vague instructions into clear, repeatable rules. This is useful because it means the error message in your app can sound exactly how a real support team would write it.

🆔 @hackernewsgithubprojects

📦 zackb/tether

Tether: iPhone Messages on Linux

Tether is the Linux bridge that finally brings your iPhone text messages to your desktop without needing a Mac. If you have switched to a Wayland-based system like Fedora or Arch but still rely on an iPhone, this project handles the heavy lifting for you. Instead of just syncing the clipboard, it pairs your phone over Bluetooth so you can read and reply to iMessage and SMS directly from your computer. It also mirrors notifications from any app, letting your Linux setup feel as connected as it used to.

📰 https://news.ycombinator.com/item?id=49370499

🆔 @hackernewsgithubprojects

📦 pgrundev/pgbot

pgbot: Your Database's Instant Health Check

pgbot is the one-shot health checker that turns your noisy Postgres database into a clear, readable report without installing a single agent. It connects with strict read-only permissions, scans the system statistics, and gives you a graded score with specific findings like slow queries or missing indexes. The coolest part is that it remembers the last check, so it tells you exactly what changed since your previous run, like a query that just got twice as slow. It is one static binary that works everywhere, making it perfect for quick triage or letting an AI agent get structured data. No servers, no setup, just answers.

🆔 @hackernewsgithubprojects

📦 smontlouis/bible-strong-avatar-lab

Build Animated Avatars Right In Your Browser

Drop a character into a browser and watch it come alive with expressive animations, all without touching a backend. Bible Strong Avatar Lab is a studio where you build procedural 2D avatars using simple shapes, define their facial expressions, and string them together into loops or one-shot clips. The coolest part is that once you design your character, you export a single portable file that works directly in React or plain JavaScript, completely detached from the editor. It runs entirely locally, meaning no accounts, no servers, and full control over your creative assets.

🆔 @hackernewsgithubprojects

📦 sapphiretoucan/diskgenius-shift

Diskgenius Shift: A Windows Workspace

Diskgenius Shift bundles a full team workspace into a single Windows download that requires zero installation. The project offers a calendar for scheduling, a document editor with markdown support, and an analytics dashboard to track team progress, all wrapped in a lightweight package that runs directly from your disk without needing extra dependencies. It is designed for simple, resource-light daily use, making it an interesting alternative for those who prefer a self-contained tool over complex cloud suites. The main takeaway is that this specific build provides a complete, offline-ready productivity stack for Windows users who want straightforward control over their workflow without the overhead of traditional software installs.

🆔 @hackernewsgithubprojects

📦 samukashvili/lumen-ps

Lumen PS: Turning a Flatbed Scanner into a 3D Texture Maker

Lumen PS is the texture-scanning software that turns ordinary flatbed scanner captures into professional 3D material maps. By rotating a subject like a leaf or circuit board four times, it uses the scanner's built-in light and sensor offset to calculate surface depth and color without any special camera rigs. The most surprising part is that it recovers detailed relief, such as individual veins or drilled holes, from just four simple scans. This solves the problem of needing expensive equipment to create realistic, relightable textures for digital art. It gives you normal, height, and color maps ready for game engines.

📰 https://news.ycombinator.com/item?id=49247297

🆔 @hackernewsgithubprojects

📦 cristianolivera1/aura

Aura: The Gradient Tool That Makes Backgrounds Feel Like Light

Aura is a web app that turns simple color layers into backgrounds that actually feel like glowing light. It ships over two hundred preset gradients built with CSS blend modes, so instead of flat fills you get soft, atmospheric washes that look like light bleeding through glass. The standout feature is the in-browser generator: stack layers, tweak blur, opacity, and blend modes in real time, add a grain overlay for a filmic finish, and even generate a prompt to rebuild the exact gradient in AI tools.

🆔 @hackernewsgithubprojects

📦 tgo-app-dev/vpipe

Vpipe Runs Massive AI Video Models on a 16GB MacBook

Generate video with sound locally on a standard sixteen-gigabyte MacBook Air. This is the surprising part. Vpipe is a local runtime built specifically for Apple Silicon that runs massive AI models, like the thirty-three billion parameter MiniMax H3, without needing a high-end graphics card or cloud server. It achieves this through custom Metal inference kernels and clever weight streaming, allowing you to create videos and their matching soundtracks entirely on your laptop. The entire runtime is incredibly compact, weighing in under thirty megabytes, which means it fits easily on your machine while handling heavy multimodal tasks like image editing, real-time chat, and video generation.

📰 https://news.ycombinator.com/item?id=49397410

🆔 @hackernewsgithubprojects