187 subscribers
11.8K videos
12.4K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ mcg-nju/autotavern

AutoTavern

A computer program now plays full games of Hearthstone Battlegrounds entirely on its own, without ever touching the live game servers. This repository, called AutoTavern, recreates the entire game in code so researchers can test how well artificial intelligence makes split-second tactical decisions. Instead of just watching a bot play, you can feed it specific tricky scenarios to see if it truly understands the rules or just guesses. It solves the problem of needing a real human player to practice against, giving scientists a safe, repeatable sandbox to teach machines complex strategy.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ feimacode/open-design-agent-kit

Open Design Agent Kit: Professional UI for your AI Coder

Ditch the generic, flat code your AI assistant spits out by default. Open Design Agent Kit transforms your standard coding tools into professional-grade design engines, letting you generate interfaces that look polished and brand-ready. It works by feeding hundreds of specific design styles directly into your existing editor, so you get that high-end aesthetic without installing heavy desktop apps or juggling new API keys. The real magic is the variety: you can switch between the sleek look of Apple or the bold energy of Nike with a simple prompt. It’s essentially a massive library of visual rules that teaches your coder to think like a designer.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ oxnw/ai-phone

ai-phone: The AI That Calls People

ai-phone is the phone daemon that actually picks up the phone on your Apple Silicon Mac. It runs a full telephone agent locally, handling speech recognition, conversation logic, and voice synthesis without sending audio to the cloud by default. This solves the problem of having an AI that can genuinely place and receive calls, acting as a real assistant rather than just a text chatbot. It connects to standard phone systems, allowing it to book tables or handle inquiries with natural, low-latency responses. The standout feature is its fully local voice pipeline, meaning your audio data stays on your machine.

πŸ“° https://news.ycombinator.com/item?id=50268009

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ beenuar/aisoc

AiSOC: The AI That Audits Itself

Turn raw security noise into auditable decisions with AiSOC, an open-source security operations center that you can run entirely on your own hardware. It stands out because every time an AI agent investigates a threat, it records its exact reasoning and tool calls in a replayable ledger. This means you don't just get a verdict; you get a transparent trail showing exactly how the model reached its conclusion. It solves the trust gap between fast AI analysis and human oversight, ensuring that no automated action happens without your final approval.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ qf-studio/pilot

Pilot: The AI That Codes Your Tickets

Ship your backlog faster by letting an AI agent handle the actual coding. Pilot connects directly to your project tracker and takes a specific ticket, writes the necessary code, and opens a pull request for your team to review. It solves the bottleneck of waiting on developers for routine tasks, turning a simple issue into a concrete software change. You still keep control by reviewing the output before it merges, but the heavy lifting is done. It is a practical way to automate repetitive development work while keeping human oversight on the final result. Think of it as a tireless pair programmer that works from your task list.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ iamrohithrnair/emeraldian

Emeraldian: Your Obsidian Vault in the Terminal

Emeraldian renders your entire Obsidian vault directly in your terminal, including live math, diagrams, and images, without a database. It reads your plain markdown files exactly where they sit on disk, so your notes remain simple text files even while the app is running. The most striking feature is its built in AI assistant, which edits your vault using the exact same commands you use, meaning you can watch every action it takes instead of trusting a summary.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ botiverse/oar

One API For Every AI Coding Agent

OAR is the universal driver that treats every AI coding agent like a single, predictable tool. Instead of rewriting your app for each vendor, you write one program that speaks to all of them. The killer feature is live steering. You can interrupt a running agent, inject a new instruction mid-thought, and watch it adjust its plan in real time. This turns static chatbots into collaborative teammates. It also handles the messy logistics for you, like checking if an agent is logged in or how much quota you have left, all through one simple interface.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ krusty84/yadisk-health

Yadisk Health: Verify Your Cloud Files

Yadisk Health is the disk utility that quietly checks if your Yandex cloud files are actually still downloadable. Many users assume their data is safe, but sometimes files become unreachable due to server issues or account quirks. This Python tool solves that mystery by grabbing the first kilobyte of every file in your drive to confirm it is there and readable. It does not touch your data or delete anything, but it gives you a clear report on what is working and what is failing. You can run it with a simple window or from the terminal.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ jamesmontemagno/tiny-clips

Tiny Clips: The Menu Bar Recorder That Makes GIFs

Tiny Clips is the lightweight menu bar app that lets you turn any part of your screen into a polished video clip or animated GIF. It sits quietly in your system tray, waiting for you to highlight a specific region on your monitor. Once you do, it captures that exact area as a high-quality video or a lightweight GIF, handling the heavy lifting of compression and encoding in the background. This solves the common frustration of needing a quick visual demo without installing bloated editing software.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ cd1s/safarier

Safarier: The Browser That Hides in Plain Sight

Safarier runs Apple’s actual Safari engine, so websites cannot tell your custom setup apart from a standard Mac. Most tools fake your hardware with scripts that get flagged instantly, but this app uses the system’s native privacy shield to protect your identity naturally. It is built for people who need dozens of isolated accounts without juggling extensions. The built-in proxy routing automatically matches your language and time zone to your exit location, making each session look like it comes from a real, specific machine. If you are managing multiple accounts, this is the cleanest way to do it without getting caught.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ jacke-pp/open-yoki

Meet Open Yoki: Your AI Live Stream Host

Run a live stream where an AI host speaks with a cloned voice and moves a real-time digital face while reading chat and keeping a diary. Open Yoki solves the problem of high-maintenance broadcasting by handling the schedule, memory, and social media posting on a single server. The most surprising part is that this virtual host actually remembers returning viewers and writes personal notes about them in plain text files. You get a fully autonomous streamer who manages her own posts and interactions without needing manual input for every message. This gives you a reliable, low-effort way to broadcast content that feels personal and connected.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ zeabur-oss/zeabur

Zeabur: Your Own Kubernetes PaaS

Zeabur gives you a familiar, easy-to-use interface for deploying applications, but instead of renting a cloud service, it runs directly inside your own Kubernetes cluster. It acts like a layer of translation, taking your standard Kubernetes setups and presenting them as simple projects with clear names and visual maps. The most striking feature is how it handles problems. When a service crashes or a node runs out of memory, Zeabur does not just show raw error codes. It explains exactly what went wrong in plain, everyday language and tells you precisely what to do to fix it.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ lalalune/pumpfun-source

The Source Code of Pump.fun

pumpfun source is the reverse engineering project that fully reconstructs the hidden smart contracts of the popular Solana trading platform. This repository takes the compiled machine code from the live network and painstakingly rebuilds it into readable Rust source code. The most striking part is that it now matches ninety nine point five percent of the original functions, with three major programs reproducing their exact output. This transparency allows developers to understand exactly how fees and trades execute on the backend. It turns an opaque financial system into an open, inspectable codebase.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ saksham2001/pulseloopios

PulseLoop: The $20 Smart Ring Tracker

Turn a seven dollar Bluetooth ring into a personal health dashboard that actually talks to you. PulseLoop skips the vendor cloud and the monthly fee, connecting straight to the hardware to pull real vitals like heart rate and sleep data. The coolest part is the built in AI coach. It reads your metrics, runs the analysis, and answers your questions all on your phone, so your data never gets sold. You get the smart insights of a premium wearable without the subscription trap or the privacy risk. If you want your health data to belong to you, this is the project to watch.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ qybaihe/bla

BLA: The Shield That Confuses AI Hacks

Protect your software from AI spies without changing how your app actually runs. The tool called BLA inserts fake data and traps directly into your compiled code. When an artificial intelligence tries to analyze your program, it hits these decoys and gets stuck in a loop, wasting its processing power on nonsense. The result is a build that looks complex and confusing to the machine, but works exactly as intended for your users. It turns a potential leak into a dead end. This is a clever way to defend your work using logic rather than just walls.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ moessif/code-video-showcase

The Code Video Showcase

The Code Video Showcase renders every single pixel of a high-energy video using pure code, completely bypassing the need for generative models. It solves the problem of unpredictable AI results by letting you draw the screen frame by frame with HTML and Canvas, then stitching it together with FFmpeg. What makes this genuinely interesting is the built-in Python engine that synthesizes the music track from scratch. It mathematically calculates the exact beat timing so your visuals land perfectly on every downbeat. It is like writing a movie and scoring it entirely in text, giving you total creative control without the black box.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kishormorol/cli-faq-shortcuts

CLI FAQ Shortcuts: Stop Repeating Yourself

CLI FAQ Shortcuts is the agent skill that finally turns your repeated coding agent prompts into reusable slash commands. It reads your local history from Claude Code, Codex, and Cursor to find exactly what you keep asking, grouping similar requests by intent rather than exact wording. This solves the problem of typing the same long, complex request every day by creating short, memorable shortcuts that point to the right scripts and record past mistakes. It runs locally with standard Python, so no data leaves your machine and secrets are automatically redacted.

πŸ“° https://news.ycombinator.com/item?id=50283743

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ pfnet-research/pfpdf

pfpdf: Markdown to Print-Ready PDF

Pfpdf is the command line tool that turns your everyday Markdown notes into professional, print-ready PDFs. The standout feature is its deep support for Japanese text, which often breaks in standard converters because of how punctuation and spacing work. Pfpdf handles this correctly so your documents look polished, not glitchy. It supports math, code highlighting, and even bibliography citations, making it perfect for technical reports or academic papers. Just run one simple command and it handles the rest, pulling in fonts automatically so you don't have to install extra software on your computer.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ neuregex/freefield

Freefield: Open Source Higgsfield for ComfyUI

Freefield rebuilds the entire Higgsfield creative studio as a completely open source project, meaning you can run professional image, video, and audio tools locally on your own GPU instead of paying for a locked down subscription. The surprising part is that there is no hidden proprietary code; every single app is just a simple folder containing a standard workflow file and a list of open weight models you can inspect. This design lets anyone see exactly how a specific effect works, swap out the underlying models, or build their own custom tools without waiting for an official update.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kekzl/imp

Imp: Massive LLMs on Small GPUs

One thirty-two gigabyte graphics card now runs a model weighing over one hundred and twenty-three gigabytes at ninety-two tokens per second. This is Imp, a dedicated inference server built exclusively for the newest Blackwell chips from NVIDIA. It achieves this by squeezing massive models into tight memory limits through specialized quantization and memory management, effectively ignoring the usual size restrictions that stop most hobbyists. The project exposes standard OpenAI and Anthropic compatible endpoints, meaning your existing applications work immediately without rewriting a single line of code. It is the clearest signal yet that high-performance local inference is no longer limited to server-grade hardware.

πŸ“° https://news.ycombinator.com/item?id=50256679

πŸ†” @hackernewsgithubprojects