📦 webpro-nl/unbash

unbash: The Fast Bash Parser

Inspecting bash scripts without running them sounds risky, but unbash changes that. This TypeScript tool parses shell commands instantly, giving you a clear, typed map of the structure without executing a single line. It is incredibly fast, handling massive files at speeds that make older parsers look like they are stuck in the past. The real magic is how it handles nested commands, letting you see exactly where variables and subshells live so you can audit your code safely. It even recovers from broken input, so your tools never crash on bad data.

📰 https://news.ycombinator.com/item?id=47333545

🆔 @hackernewsgithubprojects

📦 gluonfield/jaz

Jaz: Your AI Never Sleeps

Jaz lets your coding agents run loops overnight on your own machine. It is a personal AI setup that connects to Codex, Claude, and other tools so they can keep working while you sleep. The software uses a client and server split, meaning the heavy lifting happens on a backend you control. You can plug in your existing subscriptions, so you are not paying extra for a new platform. It adds memory that sticks around and lets you push code directly to git. The result is a powerful, always on assistant that lives on hardware you own, not in some closed cloud service.

🆔 @hackernewsgithubprojects

📦 small-tailqwq/dsh-deep-whale

Deep-Sea Maid Skins for DeepSeek

Your DeepSeek interface can now look like a deep-sea maid cafe, complete with chibi whale characters and lace accents. The DSH Deep Whale repository provides a visual skin that overlays your existing app without altering any code or performance. It adds dual maid backdrops and decorative frames, automatically switching between light and dark modes to match your preferences. All artwork is embedded directly into the package, so it works instantly without needing external servers. This project proves that even serious developer tools can have personality, letting you enjoy a cozy, anime-inspired workspace while keeping your code clean.

🆔 @hackernewsgithubprojects

📦 bigattichouse/llama-optimize

llama-optimize

llama-optimize uses a statistical trick to find your GPU’s best settings in hours instead of days. It runs a smart, two-stage experiment on your machine to test only the most important combinations of knobs. It automatically detects your hardware, runs a small set of benchmarks, and hands you a copy-paste command for the fastest setup that still fits your memory. It even tells you the exact speed trade-off between maximum speed and maximum context length. You get a ready-to-use command for the specific way you run your model, like for multiple users or long-prompt agents. No more guessing which settings work best for your specific hardware and model.

🆔 @hackernewsgithubprojects

📦 thaakeno/comfyui-minimax-h3-studio

MiniMax H3 Studio: The Secret Weapon for AI Image Editing

Turn MiniMax H3 into a polished image workflow for ComfyUI with MiniMax H3 Studio. Instead of wrestling with complex model routing and reference conditioning, this tool gives you a single, intuitive interface to generate, edit, and refine stills. You can drop in up to nine reference images, assign specific roles like lighting or pose to each, and let the system handle the heavy lifting. The standout feature is Face Refine, which detects small or distant faces in your final output, rerenders them at a higher resolution, and blends them back in for crisp, detailed results. It even includes built-in benchmarking to compare speeds and quality.

🆔 @hackernewsgithubprojects

📦 aitabby/dockyard-dsh

One App for Every AI Coding Account

Dockyard DSH packs a native macOS app that lets you manage multiple AI coding accounts in one place, eliminating the need to switch between different browser tabs or login sessions. It runs locally on your Mac, using a secure vault to store your credentials and connecting directly to various AI providers like Claude and Codex. The real magic is its account pooling feature, which automatically cycles through your available accounts to avoid hitting rate limits during long coding sessions. It’s a clean, single-window solution that keeps your workflow focused and your AI access uninterrupted.

🆔 @hackernewsgithubprojects

📦 l5yth/potato-mesh

PotatoMesh: Your Community's LoRa Mesh Map

PotatoMesh is the local dashboard that turns scattered radio signals into a live community map. It takes raw LoRa traffic from your neighborhood and displays it as a real-time map showing where people are, who they are talking to, and how the network is connected, without relying on the internet or centralized servers. The project automatically links with other local groups, creating a wider network of community run nodes. It is perfect for seeing how local off-grid communication actually works in your own area.

🆔 @hackernewsgithubprojects

📦 roadmaus/comfyui-minimax-creator

One Node, Every Shot: MiniMax Creator

Create full video clips with synchronized sound using a single, self-contained node in ComfyUI. The MiniMax Creator eliminates the complex wiring of traditional workflows by handling everything from prompt writing to final rendering in one place. You can even extend that single node into a multi-shot timeline, letting you build longer narratives where scenes flow together with continuous audio and visual continuity. It runs entirely on local open weights, so your creative process stays private without needing API keys or cloud uploads. The node intelligently manages references, faces, and sampling settings, allowing you to generate high-quality, multi-shot videos locally.

🆔 @hackernewsgithubprojects

📦 harnessrouter/harnessrouter

HarnessRouter: Run AI Agents Locally

HarnessRouter puts professional AI coding agents directly onto your own hardware, letting you run tools like Codex and Claude Code without any cloud account. It works by spinning up a single Docker container that gives these agents a real workspace with terminal access and file systems, not just a chat window. You plug in your existing API keys, paste your prompts, and watch the agent write code, run commands, and debug errors live in a browser console. The project stands out because it implements an open standard for how these agents talk, meaning you are not locked into one vendor’s proprietary system.

📰 https://news.ycombinator.com/item?id=49335595

🆔 @hackernewsgithubprojects

📦 kevinywu/manosim

Simulating Real Human Hands with Physics

Human hands are soft, yet physics engines typically treat them as stiff, brittle objects that shatter on impact. Manosim solves this by converting detailed digital hand models into a format that rigid-body simulators can actually understand. The project takes a standard hand model and rebuilds it as a physical object with realistic weight, inertia, and smooth collision surfaces. This allows researchers to test how robots might interact with human hands using accurate physics, rather than simple geometric shapes. It bridges the gap between digital animation and physical reality. You get a realistic hand you can actually simulate, not just look at.

🆔 @hackernewsgithubprojects

📦 tiger3807861189/deepseek-v4-j-space-capability-realization-report

DeepSeek V4 J-Space Capability Realization Report

DeepSeek V4 is so powerful that its main problem is actually its own unpredictability. This new report from a developer named Tiger proves that a tool called J-Space can fix this by keeping the model focused without changing its core brain. Think of it like giving a brilliant but distracted expert a strict checklist and a memory aid. By organizing how the model thinks, checks its work, and remembers where it left off, the setup helps it finish complex coding and reasoning tasks without losing the plot. The results show it beats several top-tier competitors on tough benchmarks.

📰 https://news.ycombinator.com/item?id=49336380

🆔 @hackernewsgithubprojects

📦 lexmount/moli

Moli: The Browser That Saves AI Ten Megabytes

Moli is a headless browser built in Rust that runs on just seventy-three megabytes of memory while matching Chrome’s speed, solving a huge problem for AI agents. Instead of constantly rendering the visual world, it treats the page structure as the source of truth and only calculates visuals when you truly need a screenshot. This means your AI can crawl, search, and automate tasks in a fraction of the cost without the heavy overhead of a standard browser. It is a complete runtime that fits in your pocket, making it the perfect tool for anyone building automated web workflows that need to be fast and efficient.

🆔 @hackernewsgithubprojects

📦 ai-evals-course/evals-skills

How to Find AI Mistakes with Evals Skills

Evals Skills is the agent guide that finally turns raw AI outputs into actionable error insights. It stops you from guessing what went wrong and instead builds a custom review tool to help you find it. The standout feature is the error discovery mode, where you point an AI agent at your data and it designs a visual interface to help you spot mistakes. As you review samples and leave notes, the agent organizes your feedback into failure categories and suggests new items to review. This turns a chaotic manual process into a structured workflow that catches subtle issues you would likely miss alone.

🆔 @hackernewsgithubprojects

📦 outthislife/brooklyn-skills

Brooklyn's Skills: The Missing Instruction Set for Coding Agents

Brooklyn's Skills solves the problem of inconsistent AI coding output by providing portable instruction packages that force coding agents to follow strict engineering standards. Instead of constantly retraining your AI to clean up code or manage pull requests, you simply hand the repository to it. The standout feature is the babysit skill, which actively monitors your pull request until the build is green, handling failed tests and review comments automatically. This turns a chaotic development process into a disciplined workflow where the agent behaves like a senior engineer, ensuring nothing ships without proper cleanup and verification.

🆔 @hackernewsgithubprojects

📦 zouyuxuan122/deepseek-harness-eac

Deepseek Harness EAC: The All-In-One AI Desktop

Deepseek Harness EAC is the desktop app that turns a complex command-line AI tool into a simple double-click experience. It bundles the entire runtime, so you do not need to install anything else on your machine. Just click, and the app opens a native window for your AI agent. The coolest part is the built-in plugin marketplace, which lets you instantly install custom looks, memory tools, and even a live terminal right inside your chat. It is like giving your AI assistant a full workspace instead of just a text box. If you want to use this powerful AI without wrestling with code, this is your one-stop shop.

🆔 @hackernewsgithubprojects

📦 syv-ai/qwen38-27b-rtx3090

Qwen 38 27B RTX 3090

Running a massive twenty seven billion parameter AI model on a single consumer graphics card sounds impossible, but this setup proves otherwise. The project, called qwen38-27b-rtx3090, gets a Qwen 3.8 model humming on one RTX 3090, achieving speeds of over four hundred tokens per second when handling many requests at once. It solves a major bottleneck by using clever quantization tricks that free up enough memory to let the card actually do its job, rather than just sitting idle. You get a standard API interface that works with existing tools, allowing you to run complex pipelines or chat locally without needing expensive enterprise hardware.

🆔 @hackernewsgithubprojects

📦 radishxn/run-abroad

Run Abroad: Find Your Visa in 10 Seconds

Filter seventy-one international immigration pathways based on ten simple personal details. Run Abroad takes your age, education, language skills, and savings to instantly show which visas you qualify for, and exactly what you are missing to bridge the gap. This browser-based tool removes the guesswork from navigating complex global residency rules, saving you from hiring expensive advisors for basic fact-checking. You get a clear, honest list of realistic options, sorted by your specific goals and budget. It is the fastest way to map your next move abroad without the noise.

🆔 @hackernewsgithubprojects

📦 tiger3807861189/j-space-cognition-suite-v3.6

J-Space Cognition Suite: The AI Control Layer

The J-Space Cognition Suite is the cognitive control layer that stops AI from losing the plot on long tasks. It’s not a new model, but a set of text rules that manages what an AI keeps in mind, making sure it doesn’t forget your requirements halfway through a project. The coolest part is how it handles state drift, where the AI forgets its own goals after a few steps. By externalizing its thoughts into a simple ledger, it remembers exactly where it is and what it has already verified, so it can pick up right where it left off.

🆔 @hackernewsgithubprojects

📦 pg83/solo

Solo: The Static Linux Binary Trick

Ship one static binary and let it use your existing GPU driver, completely bypassing the need for containers or duplicate system libraries. This project called Solo solves a massive headache for Linux developers by allowing fully static applications to load native graphics drivers at runtime without dragging in a second C library. It works by building a bridge that translates standard system calls into your application's base runtime, meaning you get hardware acceleration without the bloated packaging overhead usually required. The result is a single, clean executable that talks directly to your machine's graphics card, making deployment surprisingly simple.

📰 https://news.ycombinator.com/item?id=49337618

🆔 @hackernewsgithubprojects

📦 zju-real/hugagentos

HugAgentOS: Agents That Learn Their Own Rules

HugAgentOS is an agent system that builds its own rulebook as it works. Instead of relying on a fixed set of instructions, it maps out the specific relationships between concepts in a domain and uses that map to reason. When it encounters a new problem, it updates its own framework to ensure future answers are grounded in verified facts rather than guesswork. This self-evolving approach turns a standard chatbot into a tool that actually learns the structure of your specific field. The result is an assistant that gets more reliable over time, making it a fascinating look at how we can build AI that truly understands context.

🆔 @hackernewsgithubprojects

📦 gkartist75/wan2gp-desktop

Wan2GP Desktop Launcher: Run Local AI Video Generation in One Click

Run a powerful local AI video generator with a single click, thanks to the Wan2GP Desktop Launcher. This Windows tool eliminates the complex manual setup required for Wan2GP by automatically handling Git, Python, and CUDA installations for you. It detects your specific graphics card to ensure the right hardware drivers are installed, then opens a clean window where you can launch the application instantly. The real value lies in its automated environment management, which saves developers hours of troubleshooting. Instead of fighting with command lines and version conflicts, this launcher creates a ready-to-use workspace that updates itself seamlessly, making local AI generation accessible and straightforward.

🆔 @hackernewsgithubprojects