📦 frigadehq/yap

Yap

Your Mac can transcribe your voice faster and more accurately than heavy cloud models without ever sending your audio to the internet. A clever open source project called yap lives in your menu bar and lets you dictate text anywhere you can type. Just tap a shortcut, speak, and tap it again to paste the text directly into your active window. Instead of forcing you to download massive artificial intelligence models that hog your memory, it taps directly into the speech engine already built into macOS. It is incredibly lightweight, keeps your data completely private, and makes dictating emails or messages feel instant.

📰 https://news.ycombinator.com/item?id=49073834

🆔 @hackernewsgithubprojects

📦 kuangshiai/scivisagentskills

SciVisAgentSkills

Supercharge your AI coding assistants with specialized knowledge for complex scientific visualization. This repository provides pre-configured agent skills for industry-standard tools like ParaView, napari, VMD, and the Topology Toolkit. By linking these packages into your Claude Code or Codex setup, your AI agent instantly understands environment configurations, headless rendering workarounds, and tricky API patterns. For example, it can write self-contained Python scripts that run microscopy or bioimage simulations completely in the background, executing precise rendering loops to capture screenshots without ever opening a graphical interface. It is the perfect bridge for automating high-fidelity scientific data analysis.

🆔 @hackernewsgithubprojects

📦 kijai/comfyui-promptrelay

ComfyUI Prompt-Relay

ComfyUI Prompt-Relay is the animation helper that finally lets you write video prompts without manually calculating frame counts. Instead of guessing how to split up your timeline, you write your story in plain text, separating scenes with a simple pipe character or natural headers like Scene One and Scene Two. The tool automatically analyzes the text and distributes your video frames proportionally across each part of your prompt. You can even paste raw instructions directly from an AI text generator. It takes the mathematical headache out of video generation, letting you focus entirely on the storytelling.

🆔 @hackernewsgithubprojects

📦 lrzjason/comfyui-editutils

comfyui-editutils

comfyui-editutils is the ComfyUI extension that lets you edit high-resolution images with multiple reference photos without running into pixel shifts. If you have ever tried blending multiple reference images into a cohesive edit, you know how quickly layouts warp and colors drift. This clever tool organizes your pipeline into chains of customizable configurations for models like Qwen and Flux Two Klein. It lets you feed in unlimited reference images, handles the tedious task of scaling and padding them perfectly, and even lets you save and load your text conditioning states to skip repetitive encoding. It makes complex multi-image guided editing incredibly smooth.

🆔 @hackernewsgithubprojects

📦 pipenetwork/kimi-k3-mlx

kimi-k3-mlx

kimi-k3-mlx is the Apple Silicon port that finally lets you run and modify Moonshot's massive two-trillion-parameter model right on Mac architecture. This clever tool solves a massive hardware hurdle. Because the original model is a staggering five-point-six terabytes, it is impossible to load normally on consumer machines. This project introduces a streaming converter that handles the model layer-by-layer, alongside advanced expert pruning to slim it down. It even features a verified vision tower that is bit-exact to the original. It is the ultimate playground for running next-generation language models on Apple Silicon.

🆔 @hackernewsgithubprojects

📦 squeeze-evolve/squeeze-evolve

Squeeze-Evolve

Squeeze-Evolve is the multi-model orchestrator that finally scales up artificial intelligence reasoning without destroying your budget. Instead of running expensive models for every single step of a complex task, this clever system runs an evolutionary loop to grade and sort candidate answers. It automatically routes the easiest, high-consensus problems to dirt-cheap models and saves your most powerful, expensive models exclusively for the hardest, most confusing questions. It completely bypasses the need for costly external verifiers by using built-in confidence scoring to figure out which model is best suited for each step. You get top-tier reasoning accuracy at a fraction of the cost.

🆔 @hackernewsgithubprojects

📦 lookinsideapp/lookinside

lookinside

You can inspect and change your running Mac or iOS app interface details live on your screen. A new tool called lookinside acts like a web browser inspector but for native desktop and mobile applications. Instead of constantly rebuilding code just to tweak a margin or test a color, you link this tool with your running application to click through views, layers, and layout frames on the fly. It works with UIKit, AppKit, and SwiftUI, showing you layout details and live property modifications instantly. If you build interfaces for Apple platforms, this tool belongs in your debugging toolkit.

🆔 @hackernewsgithubprojects

📦 sgaabdu4/claude-code-tips

Claude Code Tips

You can stretch your Claude Code sessions from thirty minutes to over three hours using a clever five-layer optimization stack that cuts token usage by over ninety percent. This setup combines tools like Codebase Memory to trade massive file reads for a lightweight knowledge graph, and context-mode to virtualize and compress large terminal outputs into neat summaries. It also drops in Rust Token Killer to strip CLI boilerplate, Headroom to compress API payloads, and Caveman to stop Claude from using verbose filler words. Custom enforcement hooks even block Claude from falling back to lazy, token-heavy commands so you save budget automatically.

🆔 @hackernewsgithubprojects

📦 pacifio/atlas

Atlas

Atlas is the version control system designed specifically for managing coding agents at scale. Instead of juggling different artificial intelligence helpers in separate windows, this application lets you run major assistants like Claude Code, Codex, and a native built-in agent right alongside one another in a single workspace. It works like a central command center, tracking changes, managing files, and organizing agent workflows so you can compare their code edits and keep your projects perfectly organized. It is the ultimate platform for developers who want to coordinate multiple intelligent coding assistants without losing track of their codebase.

🆔 @hackernewsgithubprojects

📦 hello245m/free-stockdb

Free StockDB

Free StockDB is the local quantitative trading engine that brings high-performance stock analysis directly to your own machine. It acts as a lightweight local database and calculation engine for Chinese stock market data, tracking daily and minute-level charts without relying on slow external APIs. By caching everything locally and using highly optimized C++ code, it can calculate complex technical indicators like moving averages and MACD for fifty thousand records in just a few milliseconds. It synchronizes data incrementally through simple, secure mirror files, giving you a lightning-fast sandbox for backtesting without any corporate lag.

🆔 @hackernewsgithubprojects

📦 composio-community/awesome-codex-skills

awesome-codex-skills

awesome-codex-skills is the ultimate open directory that gives your artificial intelligence agents the power to interact with hundreds of popular web services. Instead of writing custom integration code for every single tool, this collection provides ready-to-use blueprints for linking digital assistants with everything from spreadsheet tools and mail servers to payment platforms. It makes it incredibly straightforward to build smart workflows that can browse the web, coordinate calendars, and update databases entirely on their own. It is a fantastic starting point for anyone looking to make their code-based agents significantly more capable and connected.

🆔 @hackernewsgithubprojects

📦 achimala/thelongsilence

The Long Silence

This space exploration game generates an entire galaxy inside a single browser tab using no external art assets. Every star, planet, ring system, and nebula you encounter in the long silence is procedurally generated from a seed and shaded by hand-written code. You pilot a survey vessel to chart silent worlds, scan mysterious resonators, and activate a folding jump drive. By baking massive procedural planets into cubemaps on the fly, the game runs beautifully without melting your hardware. It is a stunning, atmospheric space playground built entirely by artificial intelligence that you can play right in your web browser.

🆔 @hackernewsgithubprojects

📦 sami-uysal/awesome-open-ai-developer-tools

Awesome Open AI Developer Tools

You can replace your entire proprietary AI development stack with completely open-source tools using awesome-open-ai-developer-tools. This incredible repository is a curated directory and guide that helps you find open-source alternatives for every single layer of the AI stack, from coding agents and local models to vector databases and web browsers under agent control. What makes it brilliant is that every single tool listed answers three direct questions: what it does, what closed-source product it replaces, and why you should pick it. It is the ultimate roadmap for developers who want to escape vendor lock-in and run powerful AI pipelines entirely on their own terms.

📰 https://news.ycombinator.com/item?id=49071446

🆔 @hackernewsgithubprojects

📦 3441293738/creatorhub

CreatorHub

Take full control of your social media presence by running your own self-hosted content command center right from your desktop. CreatorHub gives you a single, unified web panel to automatically monitor, download, and publish content across major platforms like Douyin, Xiaohongshu, Kuaishou, and WeChat Channels. Instead of juggling a dozen apps, you can easily track creator profiles, auto-download high-quality videos or photo galleries, and even cross-post content between networks with customized titles and hashtags. Because everything runs locally, your database, accounts, and downloaded media stay safely stored on your own machine. It is the ultimate tool to streamline your creative workflow and keep your content moving.

🆔 @hackernewsgithubprojects

📦 reflex-dev/xy

Fast Python Charts with XY

Create interactive charts with millions of data points without freezing your browser. A library called xy solves the classic sluggish plot problem by utilizing a native Rust engine to process data. Instead of sending every single data point to your browser, it computes a smart, screen-bounded density surface, only loading the exact points when you zoom in close. It can even render ten billion points from OpenStreetMap flatly and instantly. It works directly in your notebooks, supports matplotlib code, and integrates into web apps without complex setups. Use it to build beautiful, highly responsive dashboards that handle massive datasets with ease.

📰 https://news.ycombinator.com/item?id=49085798

🆔 @hackernewsgithubprojects

📦 seanj1ang/design-judge-skills

design-judge-skills

The design judge skills repository is the ultimate set of smart assistant skills that finally takes the guesswork out of entering prestigious global design awards. It helps you navigate the entire journey by searching through a database of over twenty-two thousand real-world winning cases to find matching precedents, evaluating your work against criteria from major awards like Red Dot and IDEA, and drafting entry text directly from your project materials. Best of all, it audits your submission against official rules before you hit apply. If you want to stop guessing your design's potential and start submitting with data-backed confidence, this is the toolkit to install.

🆔 @hackernewsgithubprojects

📦 surge-ai/handbook

Handbook MD

Put your AI agents to the ultimate test by throwing them into the chaos of a real workday. This clever benchmark simulates the actual jobs enterprise workers tackle daily by dropping an agent into a live, cluttered environment. To succeed, the model must read a massive, complex company policy document, cross-reference it with messy spreadsheets, PDFs, and frantic Slack messages, and determine what actions are required or strictly forbidden. Every single task modifies its rules to block simple pattern-matching, making it so tough that even frontier models fail three-quarters of the time. It is a brilliant way to see if your AI can actually read and reason.

🆔 @hackernewsgithubprojects

📦 eyeline-labs/id-v2v

ID-V2V

You can now completely restyle a video's background and lighting while keeping the actor's exact facial expressions, eye gaze, and body movements perfectly intact. A new artificial intelligence project called id-v2v makes a shoot first, restyle later workflow a reality for filmmakers. By taking a source video and just a single stylized keyframe, it automatically carries your new artistic style across the entire sequence. If your edited keyframe is slightly misaligned, the system automatically corrects the pose mismatch from the second frame onward. It is a powerful way to transform video backgrounds and lighting without losing the human performance.

🆔 @hackernewsgithubprojects

📦 jchultarsky/mirador

Mirador: The Ultimate Minimal Terminal Dashboard

Mirador is an opinionated personal dashboard for your terminal that is designed to do exactly one job: sit in an open tab all day so you can glance at it without getting distracted. Unlike busy system monitors that constantly blink, shimmer, and fight for your attention, this tool deliberately dims every unfocused panel so only a single active item is at full brightness. Built entirely with Rust, it gives you world clocks, weather, interactive tasks, local calendar events, notes, stock watchlists, and live CPU metrics in a clean, customizable grid. Best of all, your data stays completely private in local files you own, requiring zero accounts, API keys, or background...

🆔 @hackernewsgithubprojects

📦 thejoshbrod/kernelforge

KernelForge

Optimize your PyTorch models automatically without writing a single line of CUDA or Triton code. KernelForge is a drop-in GPU kernel optimizer that profiles your model at the operator level to see where it is slow. It then hands those bottlenecks over to a smart language model to write a correct kernel, using Monte Carlo Tree Search to explore optimizations like loop unrolling and tiling until it beats PyTorch's baseline performance. You can run the entire optimization process on a remote GPU server over SSH and track its progress via a neat web dashboard. It is a brilliant way to squeeze serious speedups out of your specific hardware on a...

🆔 @hackernewsgithubprojects