📦 coldteadotai/abide

Abide: The Rule Enforcer for AI Coders

Stop letting your AI coder ignore your strict project guidelines. Abide hooks directly into tools like Claude Code to audit every single line of code your agent writes. It uses a specialized decision model to check your specific rules, like 'use Yup for validation,' in just three hundred milliseconds. If the agent breaks a rule, it gets an instant, automatic prompt to fix the error before moving on. This tool turns your text-based instructions into hard, technical enforcement, catching mistakes that standard linters miss. It is the difference between hoping your AI follows instructions and actually making it obey them.

🆔 @hackernewsgithubprojects

📦 openai/tunnel-client

Tunnel Client: Local AI, Private Access

Tunnel Client is the secure bridge that lets private AI tools talk to ChatGPT without touching the internet. Most local AI servers are locked behind firewalls, making them invisible to cloud assistants. This tool fixes that by creating a hidden, encrypted tunnel from your private machine to OpenAI's servers. You can now use your own local data and code with ChatGPT or Codex while keeping everything safely offline. It is the perfect way to enjoy powerful AI features without compromising your data privacy. If you want to connect your local AI to the cloud, this is your safe, private path.

🆔 @hackernewsgithubprojects

📦 mcncarl/yichen-skills

Yichen Skills: The AI Toolkit for Creators

Yichen Skills is the skill collection that turns messy content creation into a clean, automated pipeline. Maintained by a serial entrepreneur named Yichen, this open-source toolkit connects AI agents to real-world tools like Obsidian, X, and WeChat. It handles the heavy lifting, such as uploading long-form articles directly to X drafts, exporting private WeChat archives into usable data, and slicing posts into ready-to-post video clips. Instead of manually copying text and formatting images, the system automates the entire workflow from writing to publishing. This is a powerful way to reclaim hours of manual work. If you create digital content, this repository is your shortcut to a smarter, faster daily routine.

🆔 @hackernewsgithubprojects

📦 penglonghuang/chinese-novelist-skill

chinese-novelist-skill

Generate a complete, multi-chapter Chinese novel from scratch. This tool solves the hardest part of writing, which is actually finishing the book. It starts by asking a few simple questions about your story idea, then automatically builds a plot outline and character profiles. The most surprising part is that it writes the entire book for you, checking every single chapter to make sure it is long enough and makes sense. If a chapter is weak, it automatically rewrites it until it is good. It is not just a text generator; it is a full production workflow that remembers your writing style for next time.

🆔 @hackernewsgithubprojects

📦 continuum-ai-corp/orcabonsai-27b-uncensored

OrcaBonsai-27B-Uncensored

OrcaBonsai-27B-Uncensored is the runtime ablation technique that removes safety filters from compressed language models without touching the original file. Traditional uncensoring tools alter the model's internal math, which breaks the heavy compression that makes these tiny models run on your phone. This project instead applies a correction at the exact moment the model generates each word, leaving the downloaded weights completely untouched and bit-identical. It is a fascinating look at how you can change a model's personality on the fly while keeping the data efficient. The takeaway is that behavior is just a runtime adjustment, not a permanent edit to the file itself.

🆔 @hackernewsgithubprojects

📦 razorback16/openjev

OpenJev: Fast AI Decisions

Get fast, reliable yes-no answers from an AI model without any generated text. OpenJev is an open-source decision server that reads probabilities directly from a diffusion model to answer typed questions in milliseconds. It solves the hallucination problem by never generating free text, so answers cannot drift off script. This is great for routing support tickets or scoring customer sentiment instantly. The coolest part is that it speaks the same API as TypeSafe Jev, so existing tools just work. You get calibrated confidence scores and support for images too. It is fast, open, and built to be swapped in easily.

🆔 @hackernewsgithubprojects

📦 trungdq88/youtube-sponsor-detection

Sponsor Skip

Skip the sponsor reads on YouTube before you even hear them. This project uses a specialized model to scan video captions, pinpoint exactly where a paid promotion starts and ends, and jump straight past it. It isn't just a guess; it listens to the audio in real time to confirm the transition, ensuring you never miss a beat or lose actual content. Whether you use the Chrome extension or the simple web app, it turns those annoying ad breaks into zero seconds of waiting. It is a clever way to reclaim your time and keep your watch sessions focused purely on the video you actually wanted to see.

🆔 @hackernewsgithubprojects

📦 jerryzliu/agentplayback

AgentPlayback: Visualize Your AI Coding Agents

AgentPlayback is the local dashboard that finally shows you exactly how much your AI coding agents are costing you. If you use tools like Claude Code or Codex, you probably have a lot of hidden logs that show what happened, but you likely have no idea how much you are actually spending. This project reads those private logs and turns them into a simple visual timeline, so you can see precisely when your agents were working versus when they were just waiting for you to type back.

📰 https://news.ycombinator.com/item?id=49456949

🆔 @hackernewsgithubprojects

📦 pleaseprompto/smabar

The Dock That Builds Itself

Pin your favorite apps, folders, and websites to a sleek dock that sits right next to your system taskbar. But the real magic is that you can ask your coding agent to build a custom plugin for you, like a live bus schedule or a crypto ticker. smabar connects to your AI assistant so it can write the code, test it, and drop it straight onto your screen without you touching a terminal. It’s like having a developer friend who just works for you. If you want a desktop that adapts to exactly what you need, this is the way to do it.

🆔 @hackernewsgithubprojects

📦 dominikbucko/qwen38-flash-next-2x3090

qwen38-flash-next-2x3090

You can now run a massive two-hundred-and-fifty-six-thousand token context window on just two consumer graphics cards at a blazing peak of over eighteen-hundred tokens per second. The qwen38-flash-next-2x3090 project accomplishes this feat by pairing a specialized model checkpoint with a highly clever memory offloading system. Instead of forcing the entire model into expensive graphics memory, it strategically keeps a massive n-gram table and less-frequent experts in system memory, while keeping a dynamic, running cache of active experts right on your GPUs. By using a smart drafting system to speed up generation, it gives you lightning-fast performance without sacrificing quality.

🆔 @hackernewsgithubprojects

📦 incoai/splash

How Splash Makes Your Mac a Supercomputer

Splash runs massive AI models directly on your Mac, beating cloud servers in speed without sending data away. On a standard M5 Pro, it processes text twice as fast as the next best engine, returning your first word in less than three hundred milliseconds. The secret is that every single component is custom built for the specific model you load, creating a perfect fit that eliminates waste. You get a local tool that speaks the same language as your favorite coding agents, meaning your private projects stay on your machine while working faster than you ever thought possible.

🆔 @hackernewsgithubprojects

📦 githubnext/localjev

Run Jev Locally: The Surprising Bridge

LocalJev lets you run TypeSafe Jev decision-making entirely on your own computer. While the standard Jev service relies on a remote, proprietary backend, this open-source project bridges that gap by translating typed decision requests into a format your local hardware can process. It connects directly to local inference servers running on Macs, allowing you to make complex, structured decisions without sending sensitive data to the cloud. By running the engine locally, you gain full control over privacy and latency while maintaining compatibility with existing SDKs. It is a powerful way to experiment with autonomous decision logic right on your desktop.

📰 https://news.ycombinator.com/item?id=49766255

🆔 @hackernewsgithubprojects

📦 mxxm-t/mx-llama.cpp

mx-llama.cpp: Multi-GPU Inference in C/C++

mx-llama.cpp is a specialized fork of the famous llama.cpp project, built specifically to wring maximum performance out of multi-GPU setups using pure C and C++. While the original handles single cards well, this fork introduces a clever multi-stage tensor parallelism feature. This lets you split your model's layers across different groups of GPUs, pipelining the data so multiple cards work on different parts of the sentence simultaneously. This is huge for people running massive models like DeepSeek or Qwen locally without paying for a data center. It also includes custom GPU communication code that beats standard drivers on certain hardware.

🆔 @hackernewsgithubprojects

📦 yoosseph/pc-anatomy

PC Anatomy: A 3D Disassembly Journey

Take a desktop computer apart until you reach the silicon. PC Anatomy is an interactive 3D explorer that lets you dismantle an entire tower, dragging a slider to separate every fan, wire, and chip into a flat inventory. The real surprise is how deep it goes. You can zoom into a graphics card, then into its chip, then into the microscopic processing units that do the actual math. Every part you touch has a name and a plain explanation, so you learn how the machine really works without reading a manual.

🆔 @hackernewsgithubprojects

📦 kdbhalala/avdslim

avdslim

Your Android emulator is secretly eating eight gigabytes of your computer's memory just to boot up a fake phone. Avdslim is a simple command-line tool that slashes that number down to about one and a half gigabytes, making your laptop feel instantly lighter and faster. It works by telling the emulator to use your actual graphics card instead of a slow software renderer, and it quietly disables all those unnecessary background apps that drain power. The best part is a feature called bake, which saves a pristine snapshot of your slimmed-down phone so it boots up in just one and a half seconds.

🆔 @hackernewsgithubprojects

📦 btsouth/toolport

Toolport: One Port for Every AI Client

A local app called Toolport cuts AI context overhead by over ninety percent without sacrificing accuracy, turning a cluttered list of tools into a searchable library that loads only what you need. Instead of pasting connection details into every separate app, you connect your servers once and share them across all your AI clients through a single local gateway. This setup keeps your private keys safely inside your operating system’s keychain rather than scattered in config files. The system also lets you block dangerous actions or require your approval before they run, giving you real control over what your agents do.

🆔 @hackernewsgithubprojects

📦 theguysudo/enzo

Enzo: Your Private AI Workspace

Enzo is the self-hosted AI workspace that puts total control back in your hands. It runs entirely on your own infrastructure, letting you plug in your own API keys from providers like Groq or Google so you pay the model directly without any middleman markup or subscription fees. The standout feature is its agent builder, where you describe a task in plain English and the system drafts a complete operating manual for the agent, which then learns from your activity to improve over time. It also gives you access to over three hundred models through one simple catalog. No accounts, no hidden meters, just your keys and your data.

🆔 @hackernewsgithubprojects

📦 addyosmani/clarity

Clarity: Write Like You Talk

Take a coding agent and teach it to write like a human, not a robot. That is exactly what Clarity does. It is a skill that plugs into your development tools to help you draft, rewrite, or review prose with genuine clarity. The coolest part is interview mode. Instead of guessing what you mean, the agent asks you specific questions about your experience, your audience, and your argument. It then builds the piece using your actual words and examples, rather than inventing generic filler. It feels less like using an AI and more like having a brilliant editor who actually listens.

🆔 @hackernewsgithubprojects

📦 kivutar/goro

Goro

This entire MMORPG client is written in Go and runs on your GPU without a single C header. Goro recreates the classic two-thousand-eight Ragnarok Online experience using a modern Vulkan pipeline. It handles everything from character creation to complex guild management and pet hatching. Because it is pure Go, it compiles easily on any platform without messy external dependencies. It even includes tools to pack and unpack game resources. If you want a clean, hackable codebase that actually runs the game, this project is your new favorite weekend experiment.

📰 https://news.ycombinator.com/item?id=49767075

🆔 @hackernewsgithubprojects

📦 matheusht/redthread

RedThread: The AI Bodyguard

RedThread attacks your AI models to find the exact prompts that break them, then automatically builds and tests the fix. It doesn't just guess at security holes; it runs a full loop of generating attacks, scoring the damage, and creating specific guardrails to stop those exact exploits. The coolest part is that it finds the smallest possible trigger for a jailbreak, so you aren't guessing what went wrong. It proves the defense works before you deploy it, turning guesswork into solid proof. If you ship AI, this is how you keep it safe without the guesswork.

🆔 @hackernewsgithubprojects

📦 malerba118/element-mirror

Element Mirror: Real-Time Canvas Reflections

Element Mirror lets you project any live website element onto a canvas in real time, capturing everything up to sixty times a second. This is particularly cool for creating drag ghosts or blurred video backdrops without duplicating your code. Instead of cloning the DOM, it uses a shared capture system that records the actual pixels, shadows, and animations. This means a single source can feed multiple delayed mirrors, allowing you to build smooth motion trails that cost almost nothing extra. It is a clever way to keep visual effects perfectly in sync with your interface. The best part is that it handles the heavy lifting for you.

🆔 @hackernewsgithubprojects