📦 qkal/canny

Canny: The Agent Bouncer

Canny stops AI coding agents from claiming work is finished without actual proof. It hooks into tools like Claude Code to keep a strict record of every file change and command run. The real magic happens when an agent tries to declare a task complete. Canny checks if you actually ran the tests. If you skipped them, it blocks the finish and forces you to fix what failed. It catches secrets and removed tests before they cause trouble. You get a reliable guard that keeps your code honest without slowing you down. Try it today to keep your AI coding agent accountable.

🆔 @hackernewsgithubprojects

📦 coddingtonbear/icloud-md

icloud-md: Your Apple Notes as Real Files

icloud-md is the command-line tool that turns your Apple Notes into real Markdown files you can edit on any computer. Usually, your notes are locked inside a specific app, but this tool pulls them down as plain text documents on your hard drive. You can open them in your favorite code editor, make changes, and push those updates back up to the cloud. It even handles conflicts automatically if you edited the same note on your phone. The best part is that your notes become simple files you can search, back up, or version control like code.

📰 https://news.ycombinator.com/item?id=49069224

🆔 @hackernewsgithubprojects

📦 heygen-com/hyperframes-community-skills

The 3D Caption Trick for AI Video

HeyGen just let the community build video effects that used to require expensive motion graphics software. Inside the HyperFrames Community Skills repository, developers can install specific tools that make text float in three dimensions around a person talking to the camera. The most impressive skill places words at different depths so they wrap around the speaker, hiding behind their head and popping out in front. It feels like a movie trailer effect, but it runs right on your computer without heavy render farms. Because it is community maintained, you can grab just the specific tool you need rather than downloading a whole suite.

🆔 @hackernewsgithubprojects

📦 tenuo-ai/tenuo

How Tenuo Keeps AI Agents In Line

Tenuo is the authorization layer that guarantees AI agents can never do more than they were strictly told to do. When you hand a job to an AI, you hand it a signed ticket that lists exactly which tools it can use and what limits apply to the arguments it can pass. The surprising part is that this ticket shrinks as work gets passed to other agents, meaning a helper can never gain more power than its boss. If an agent gets hijacked by a prompt injection, it is still locked out of forbidden actions because the check happens on the server side, not inside the model.

🆔 @hackernewsgithubprojects

📦 nihui/qwenimage-ncnn-vulkan

Qwen Image NCNN Vulkan

The Qwen Image NCNN Vulkan tool runs a massive seven billion parameter image generator on your laptop without needing Python or PyTorch installed. It is a portable command line executable that uses the Vulkan API to handle the heavy lifting on your graphics card, whether that is an Intel, AMD, or NVIDIA chip. You simply type a description and it paints a picture, or you can hand it a photo and ask it to change the clothes. The coolest part is that it can take up to ten reference images and blend them into one new scene, all while keeping the background transparent.

🆔 @hackernewsgithubprojects

📦 nassim-arifette/jevgrep

JevGrep finds code by behavior, not keywords

JevGrep lets you search code by asking what it does, rather than guessing the exact file name or variable name. This tool is built specifically for coding agents, helping them locate tricky behaviors scattered across a project without wasting context on irrelevant files. You can ask a simple question like where session expiry is handled, and JevGrep scans your repository using a specialized model to score every eligible fragment of code. Instead of a vague summary, it returns the actual source excerpts with precise file paths and line numbers, allowing the agent to read exactly what matters.

🆔 @hackernewsgithubprojects

📦 shaohua-pan/encore

Encore: 8-Minute Video + Audio Generator

Create eight-minute videos with perfectly synchronized sound using the research project called Encore. This tool generates long-form media one short five-second segment at a time, but it stitches them together so the character and voice stay consistent for minutes. It uses a technique called adaptive signal routing to ensure that every new clip blends seamlessly into the previous one, solving the common problem where AI videos drift or change identity over time. You can start with just a single image and a text prompt to produce a continuous take. It is a powerful way to make longer, coherent stories rather than just short clips.

🆔 @hackernewsgithubprojects

📦 achimala/jev-paint

Jev Paint turns data uncertainty into digital art

A tiny local web app turns raw statistical uncertainty into actual paintings. It is called Jev Paint. Instead of just showing numbers, it asks an AI model how confident it is about every single pixel in a description. It then turns that hesitation into brush strokes, texture, and color. The less the model is sure, the rougher the paint looks. The more it is sure, the smoother the surface becomes. It runs entirely in your browser with a tiny local helper to handle security rules. You type a prompt, it paints, and you get a unique visual result. It is not a data chart.

🆔 @hackernewsgithubprojects

📦 achimala/jevinci

Jevinci turns math into paintings

Jevinci turns the raw statistical uncertainty of a language model into actual painted artwork. It is a local web app that fetches the probability distributions for every pixel in a grid and renders them using physical painting techniques like impasto lighting and pigment strokes. Instead of showing a dry chart, it uses the model's confidence levels to determine color depth, texture, and relief, creating a visual representation of how the machine thinks. You run a tiny local server to connect your browser to the service, then type a prompt to generate unique, textured pieces that fade in as they render.

🆔 @hackernewsgithubprojects

📦 saadwazir/medcagd

How MedCAGD Maps Eyes with Less Code

MedCAGD is the medical image tool that spots tiny details without the heavy computational cost. It takes standard photos of retinas and pinpoints the intricate network of blood vessels, which is usually a headache for computers because the lines are so thin. The clever trick here is a decoder that gates the data flow, meaning it only looks at pixels that actually matter for the structure. This keeps the model light and fast, proving you can get sharp, accurate segmentation without needing a massive cluster of servers. It is a neat, efficient way to handle complex medical imaging that any developer should study.

🆔 @hackernewsgithubprojects

📦 taeold/djev-run

Djev Run: Playing Snake with an AI on a GPU

Deploy a specialized AI model on Google Cloud Run that answers questions and plays games in your browser. The project takes a large language model and hosts it on a high-end graphics card, turning it into a service that can control classic games like Snake and Tetris. The most striking part is how fast it starts up; by streaming the massive model files directly into memory while the system boots, it cuts the wait time from four minutes down to just forty-seven seconds. You get a server that costs three dollars an hour but scales to zero when idle, so you only pay when you are actually using it.

🆔 @hackernewsgithubprojects

📦 alibaba-damo-academy/clinhallu

ClinHallu: The Truth-Teller for Medical AIs

ClinHallu exposes exactly where medical AI models lie, identifying whether errors stem from misreading images, forgetting facts, or flawed logic. Built by Alibaba DAMO Academy, it tests these models on real medical scenarios using a clever technique called replacement. By swapping in correct data at specific steps, researchers can isolate the source of hallucinations. This matters because a wrong answer in medicine isn’t just a bug; it’s a risk. The project provides the tools to find out if your AI is truly reliable before it touches patient care. If you work with medical AI, you need to know if your model sees clearly, knows its facts, and thinks logically.

🆔 @hackernewsgithubprojects

📦 magiccreator-ai/awesome-gpt-6-astra

The GPT-6 Astra Demo Hub

There is a curated collection called Awesome GPT-6 Astra that gathers real, working demos of the new model in action. It features original projects where creators built games, designed three-dimensional assets in Blender, coded live websites, and produced video content. This is not a list of vague prompts or unverified claims. Instead, you get a verified directory of concrete workflows, complete with links to the original posts, creator credits, and live results if available. The team maintains strict standards to ensure every entry is a genuine, reproducible project rather than a repost.

📰 https://news.ycombinator.com/item?id=49596337

🆔 @hackernewsgithubprojects

📦 lunaaispace-eng/comfyui-degrid

ComfyUI DeGrid

A two-pixel checkerboard pattern is silently baked into every image generated by Qwen and Wan VAEs. ComfyUI DeGrid erases this invisible grid before your upscaler mistakes it for real detail. The node uses a phase-locked detector to find the exact lattice and a notch filter to remove only that specific artifact. It automatically calibrates the strength for each image, ensuring smooth areas stay clean while protecting genuine texture like skin pores or fabric weave. If no grid is detected, the image passes through completely untouched. This simple node fixes a subtle flaw that amplifies during sharpening, giving you cleaner results without manual tuning or extra dependencies.

🆔 @hackernewsgithubprojects

📦 egoist-machines/lodedb

LodeDB: The Tiny Vector Database That Fits in Your Pocket

LodeDB is the embedded vector database that fits your entire search index inside a single pocket. It solves the bloat problem by compressing your data so tightly that a store holding over seventeen thousand documents takes up less space than a single high-resolution photo. You get this compactness without sacrificing speed, thanks to a specialized engine that processes multiple searches at once using your graphics card, making it thousands of times faster than standard tools. It acts as a drop-in replacement for your existing memory layer, meaning you can swap it in with a single command without rewriting your code.

📰 https://news.ycombinator.com/item?id=48668208

🆔 @hackernewsgithubprojects

📦 inclusionai/ming-image

Ming Image: Editable Design Layers from Text

Generate fully editable visual designs directly from text. Ming Image creates complete layouts for interfaces, posters, and infographics, but its standout feature is layer decomposition. It takes a single flat image and splits it into separate, transparent layers. This means you can grab just the text, the background, or a specific graphic element independently. It solves the major problem of editing flat designs by turning static pictures into flexible, multi-layered assets. No need to redraw everything from scratch. You get precise control over every part of the design. It is a powerful tool for anyone who needs to tweak specific elements without starting over.

🆔 @hackernewsgithubprojects

📦 patlux/pi-commandcode-provider

Pi Command Code Provider

You can plug eighteen different AI models, including Claude, GPT, and DeepSeek, directly into your Pi coding agent using a single plugin. Pi Command Code Provider acts as a bridge, letting you pick any model from the Command Code API without managing separate keys or complicated setup. It handles the connection automatically, so you can swap between different thinking styles on the fly. This is perfect for developers who want flexibility without the headache of juggling multiple subscriptions. If you use Pi, this is the easiest way to access top-tier models right in your terminal.

🆔 @hackernewsgithubprojects

📦 mindbox77/zxdesk

A Full Desktop for a 1982 Computer

A full graphical desktop with draggable windows, menus, and a working calendar fits inside forty-eight kilobytes of RAM on a computer from 1982. This project, called ZX Desk, proves that a machine with a three and a half megahertz processor can handle overlapping windows and a file manager. The author wrote this in Z80 assembly to recreate the feel of a classic desktop environment, but without emulators. It runs on real hardware, meaning every single byte of memory is accounted for. The real magic here is the engineering required to make dragging a window smooth on such slow hardware.

📰 https://news.ycombinator.com/item?id=49766676

🆔 @hackernewsgithubprojects

📦 ganyuanran/aegis

Aegis: The Safety Net for AI Coding

Your AI coding agent just stopped guessing at your code and started proving it works. Aegis is a method pack that turns your coding assistant into a disciplined engineer, ensuring it checks your project’s real baseline before making changes and only marking work complete when it has fresh evidence. In rigorous tests, this simple rule reduced unsafe outcomes from thirteen percent to zero. It doesn’t force heavy process on simple tasks, but for complex work, it demands proof before saying done. If you want to stop babysitting your agent and start trusting its results, this is the safety net you need.

🆔 @hackernewsgithubprojects

📦 amal-david/awesome-jev

Awesome Jev: The Curated Hub for Typed AI Decisions

Discover forty-four real-world projects built with Jev, a tool that answers questions about data with yes or no probabilities instead of writing text. This curated collection solves the problem of finding out what people are actually using this unique technology for. It is useful because it links directly to the source code and includes a gallery of demos. You can see Jev choosing browser actions, scoring log entries, or even playing chess against a shared board. The repository helps you understand where a dedicated classifier fits better than a large language model. It is a great starting point for anyone curious about how structured decision-making works in modern applications.

📰 https://news.ycombinator.com/item?id=49802160

🆔 @hackernewsgithubprojects