📦 arahim3/mlx-dspark

mlx-dspark

Your Mac can now run DeepSeek's advanced speculative decoding technology to generate local text up to sixty percent faster without losing a single drop of quality. The mlx-dspark project brings both DeepSeek's DSpark and z-lab's DFlash architectures natively to Apple Silicon using Apple's MLX framework. Instead of waiting for a large language model to think up every word sequentially, this tool uses a tiny, hyper-fast draft model to guess ahead, which the main model verifies in a single parallel pass. It even serves an OpenAI-compatible API with continuous batching and prefix caching, making your local offline assistant feel incredibly snappy.

🆔 @hackernewsgithubprojects

📦 howdymary/autopredict

autopredict

Build and backtest smart trading agents for prediction markets like Polymarket, and let them automatically improve their own strategies over time. This clever little Python framework scans live market data and runs historical backtests, but its coolest feature is a self-improvement loop that actually tests and refines your trading rules. It rolls out strategy tweaks, grades them against real historical outcomes, and only saves the new version if it legitimately beats the old one. There is no fake data or magic default formulas here, just an honest tool to help your code learn how to trade better on its own.

🆔 @hackernewsgithubprojects

📦 ruc-datalab/deepanalyze

DeepAnalyze

An open-source artificial intelligence system can now act as your personal data scientist, managing complex data projects completely on its own. This new project, called deepanalyze, automates the entire data science pipeline, from preparing raw files to training predictive models and generating polished, professional reports. Instead of forcing you to clean data and write repetitive code, it autonomously explores structured spreadsheet tables, nested files, and plain text documents to find insights. It runs python code in sandboxed environments to verify its work, meaning you get fully validated analysis. It is a powerful way for anyone to turn messy folders of raw files into clear, visual research reports instantly.

🆔 @hackernewsgithubprojects

📦 larashero3-dotcom/writing-dna-skill

writing-dna-skill

Artificial intelligence can copy any writing style consistently by breaking down texts into structured, reusable blueprints instead of just guessing the tone from a few examples. The writing-dna-skill repository provides a comprehensive system that analyzes at least twenty sample articles across six distinct layers, separating style from mere text. It extracts a writer's specific vocabulary, sentence rhythms, structural templates, core thinking frameworks, and even visual formatting guidelines. This structured blueprint is then saved as a single master file that an AI agent can reread and reference before drafting new pieces, ensuring the output perfectly mirrors the original writer's voice, depth, and presentation.

🆔 @hackernewsgithubprojects

📦 ostris/comfyui-krea2-ostris-edit

comfyui-krea2-ostris-edit

The ComfyUI custom node extension that finally brings reference-based image editing to the Krea 2 model. While Krea 2 is normally a text-to-image generator, this tool patches the model so it can actually consume reference images alongside your prompts. It encodes your images through a vision-based text encoder and feeds them straight to the model at the very beginning of the generation. This means you can train a custom edit style, feed in a reference photo, and transform it using specialized edit adapters. It is the perfect bridge for anyone wanting to bend Krea 2 into a powerful, controllable editor.

🆔 @hackernewsgithubprojects

📦 v4bel/januscape

Januscape

Crash any multi-tenant x86 cloud server directly from inside your virtual machine using a newly discovered exploit. The project, called januscape, showcases a critical guest-to-host escape vulnerability that lay dormant in the Linux kernel for sixteen years. By abusing a logic flaw in how KVM handles memory virtualization, a guest virtual machine can trick the host kernel into reusing memory structures with the wrong architectural roles, corrupting the host's memory state. This allows an attacker renting a single cloud instance to trigger an immediate host kernel panic, instantly taking down every other virtual machine on that physical machine.

📰 https://news.ycombinator.com/item?id=48807908

🆔 @hackernewsgithubprojects

📦 robbyant/lingbot-vision

LingBot-Vision

Lingbot-vision is the vision artificial intelligence model that maps boundaries and shapes directly from raw images without needing human-labeled training data. By focusing on the edges where objects meet, this system naturally grasps the physical layout of a room, including tricky reflective glass and deep spaces. It acts like a digital eye that groups pixels into coherent shapes, helping computer vision programs accurately measure depth, trace object contours, and track moving things in video. It is a incredibly smart way to give robots and cameras a spatial common sense, making visual AI dramatically better at understanding the physical world.

🆔 @hackernewsgithubprojects

📦 zimengxiong/tinytouch

tinytouch

tinytouch is the clever hardware project that lets you bypass Apple's pricey accessories to unlock your Mac with your fingerprint. Instead of spending a fortune on a branded keyboard, this DIY tool pairs a cheap microcontroller and a fingerprint reader with a lightweight helper app running on your computer. When you scan your finger, the little device securely talks to your Mac's Keychain and automatically types your password for things like system logins and terminal prompts. It is incredibly satisfying to use, surprisingly simple to build, and saves you serious cash. Grab a cheap microchip, load the code, and enjoy wireless fingerprint logins on a budget.

🆔 @hackernewsgithubprojects

📦 stas00/python-cookbook

python-cookbook

Skip the endless search for code snippets and master Python standard library tricks with python-cookbook. This repository is a practical, example-driven guide filled with daily recipes that every developer actually needs, covering everything from text wrangling and debugging to memory profiling. Instead of suggesting heavy third-party packages, it focuses on modern, built-in idioms like pathlib and subprocess. The best part is that every single recipe leads with why you should use it and highlights the silent gotchas that usually break your code. Check out this guide to write cleaner, faster, and more reliable Python programs today.

🆔 @hackernewsgithubprojects

📦 markovwangrr/iso-topology

iso-topology

You can now generate design-grade, three-dimensional isometric architecture diagrams straight from plain text files, eliminating the need to spend hours manually drawing boxes and aligning grids in Figma. This tool, called iso-topology, translates coordinate-free text layouts into gorgeous, two-and-a-half-D vector graphics that represent complex systems with clean visual depth. It solves the headache of outdated documentation by keeping your system diagrams committed directly alongside your codebase as plain, version-controlled text. The project even includes a built-in feedback loop so AI agents can automatically write, validate, and repair the diagrams before they render. It is the easiest way to keep your technical drawings beautiful and always up to date.

🆔 @hackernewsgithubprojects

📦 arbs-io/github-copilot-llm-gateway

github-copilot-llm-gateway

Your self-hosted AI models can now run inside GitHub Copilot Chat without constantly choking on broken tool calls or context limits. The github-copilot-llm-gateway is a clever VS Code extension that adds a robust resilience layer to smooth out the rough edges of local models like Qwen, Llama, and Mistral. Instead of failing when small or quantized models output sloppy JSON, this companion extension actively repairs malformed tool calls, manages context budgeting, and routes raw reasoning blocks perfectly into Copilot's interface. It gives your self-hosted setup the ultimate stability boost, bringing flawless agentic coding right to your local network.

🆔 @hackernewsgithubprojects

📦 manak-hash/linkbreeze

LinkBreeze

LinkBreeze is the self-hosted link-in-bio platform that lets you bypass monthly subscription fees while keeping full ownership of your data. Think of it as a private, open-source alternative to Linktree that you can launch on your own server with a single Docker command. It packs a fast, built-in admin panel where you can drag and drop unlimited links, schedule when they appear, embed media widgets from Spotify or YouTube, and collect subscriber emails. Best of all, it gives you privacy-first page analytics and customizable themes with zero tracking cookies, loading your personal page in under three hundred milliseconds.

🆔 @hackernewsgithubprojects

📦 loganbooker/sesquilsr

SesquiLSR

Standard latent upscaling destroys image detail, forcing you to use massive denoise settings just to fix the blurry mess. A clever open-source project called sesquilsr solves this by using a tiny three-million parameter model that upscales directly inside the latent space. Instead of relying on crude math, it uses learned downsampling to scale your images to any fractional size up to two-times with incredible perceptual detail. It runs in under six milliseconds, bypasses slow round-trips to the image decoder entirely, and plugs right into ComfyUI. It is the perfect, lightning-fast bridge to prep your AI generations for a clean second pass.

🆔 @hackernewsgithubprojects

📦 lagunaswift/rockyvoice

RockyVoice

Transform your everyday AI assistant into Rocky, the beloved Eridian alien engineer from Andy Weir's sci-fi novel Project Hail Mary. This clever repository lets you install a custom persona skill for Claude Code and Hermes, replacing standard responses with Rocky's signature speech style of small words, no contractions, tripled words for big feelings, and questions that always end with the word question. Even better, it includes a local web application powered by Hume AI voice cloning, letting you hear Rocky speak your code fixes and answers out loud in real time. It is a brilliant way to bring your favorite space friend directly into your terminal.

🆔 @hackernewsgithubprojects

📦 thecodearcher/limen

Limen

Compose your perfect authentication stack in Go without any bloat. Limen is a modular authentication library designed to let you plug in only the security features you actually need, from passwords and OAuth to two-factor auth. Unlike traditional all-in-one libraries, its architecture isolates every single authentication method into its own separate Go package. This means your application stays incredibly lightweight because you never compile unused dependencies into your final binary. It even includes reactive TypeScript client SDKs for popular frontend frameworks. It is a wonderfully clean and modern approach to securing your Go applications.

📰 https://news.ycombinator.com/item?id=48823067

🆔 @hackernewsgithubprojects

📦 seu-paisys/embodied.cpp

embodied.cpp

Run heavy robotic brain models directly on everyday hardware without losing speed. If you want to deploy advanced AI models that let robots see, plan, and physically act in the real world, you usually need massive cloud setups. This project changes that by packaging these complex models into highly efficient files that run natively on standard computer processors and local graphics cards. It handles the translation between camera sensors and robot joints in lightweight code. You can test your models in simulation or load them straight onto a physical robot arm, bringing local, intelligent automation to standard hardware.

🆔 @hackernewsgithubprojects

📦 brobert-in-aus/scail-auto-extend

scail-auto-extend

scail-auto-extend is the ComfyUI custom node that finally lets you generate SCAIL-2 videos of any length in a single queue without manual math. Normally, the model limits you to eighty-one frames, forcing you to manually build duplicate node sections, bypass frames, and math out overlap anchors just to extend a clip. This clever node automates the entire loop at runtime by slicing your video into perfect chunks, anchoring the overlaps, matching colors to prevent drift, and stitching the final video together seamlessly. It turns a frustrating multi-step bottleneck into a simple, one-click background process. Give it a spin to effortlessly scale up your video generations.

🆔 @hackernewsgithubprojects

📦 haitaowutju/brainjanus

BrainJanus

BrainJanus is the neural translation model that finally links brain activity, vision, and language together in a single system. By mapping complex brain signals like fMRI scans into a shared digital vocabulary, this project allows a computer to translate what you are looking at directly into images or text, and even run the process completely in reverse. Instead of needing different custom software for every individual task, this setup handles visual reconstruction, brain captioning, and brain signal synthesis all at once. It makes translating complex neural activity into everyday human communication and pictures incredibly simple and unified.

🆔 @hackernewsgithubprojects

📦 almanaccode/codealmanac

codealmanac

Build a living, breathing reference manual for your AI coding agents to stop them from making the same silly mistakes over and over. This project helps you create a dedicated local wiki that captures critical context your raw code leaves out, like architectural decisions, hidden gotchas, and complex business flows. By feeding this structural map directly to your AI assistants, you prevent them from hallucinating or breaking delicate parts of your system. It is a brilliant way to keep your autonomous developers fully aligned with your real-world constraints. Give your AI agents the missing instructions they need to write smarter code.

🆔 @hackernewsgithubprojects

📦 carloluisito/omnidesk

OmniDesk AI Terminal

OmniDesk is an elegant desktop terminal that wraps artificial intelligence coding tools like Claude Code directly into a high-performance workspace. Instead of juggling dozens of messy terminal windows, this app organizes everything around your actual coding repositories, giving you a dedicated activity bar and a session rail to navigate. You can instantly switch between a single focused terminal or a live grid view that displays all your active sessions side by side. It even manages your git worktrees behind the scenes so you can safely test changes. It is the ultimate command center for developers who want to run multiple local AI sessions without the chaos.

🆔 @hackernewsgithubprojects

📦 jeakwon/ai-engram

ai-engram

ai-engram is the Python library that finally makes LLM unlearning as simple as subtracting a matrix. Instead of running expensive training loops or backpropagation to make a model forget specific facts, this tool uses a clever, training-free approach based on covariance. It isolates the exact weights responsible for the target data and subtracts them in a single, closed-form step. You just collect forward-pass statistics on what to forget and what to keep, compute the difference, and the model instantly unlearns the target info while preserving everything else. It is incredibly fast, native to Hugging Face, and completely bypasses gradient descent.

🆔 @hackernewsgithubprojects