📦 akil-x/r00tlib-catalog

The Free Tech Book Catalog

Rootlib Catalog is the open tech book index that finally puts hundreds of free textbooks in your pocket. Instead of hunting for scattered PDFs, this community project gathers verified copies of top titles in cybersecurity, artificial intelligence, and game development into one searchable list. It links directly to mirrors and discussion threads, so you can grab the knowledge without paying a dime. It is basically a massive, organized library built by developers for developers. If you are studying systems or security, this is your shortcut to serious reading material. Check it out and see what you have been missing in your study rotation.

🆔 @hackernewsgithubprojects

📦 andyhuo520/vibe-knowledge

Vibe Knowledge: Turning Facts Into Cinematic Videos

Transforming a single fact into a polished, cinematic video is the core magic of Vibe Knowledge. This project acts as a specialized instruction set for artificial intelligence, guiding it through the entire process of creating short educational films. It handles everything from researching and scripting to voice generation and visual rendering, ensuring every visual element is drawn in code with precise sources for every claim. The standout feature is its library of forty-four distinct visual styles, allowing creators to instantly switch between aesthetics like pixel art, blueprint diagrams, or traditional ink painting without changing the underlying script.

🆔 @hackernewsgithubprojects

📦 slkiser/opencode-quota

OpenCode Quota: Your AI Token Meter

Check exactly how much of your AI coding quota you have left right now. OpenCode Quota plugs into your terminal editor to track your token usage and remaining limits across dozens of different AI providers like Anthropic, OpenAI, and Google. It solves the confusing problem of switching between tools without knowing when you will hit a paywall or rate limit. The best part is that it runs completely outside the main chat, so it never slows down your prompts or eats up your valuable context window. You just type a simple command to see a clean breakdown of your spending and limits.

🆔 @hackernewsgithubprojects

📦 changhaoting1998-star/manufacturing-wechat-miniapp-starter

Manufacturing WeChat Mini Program Starter: The Shop-Floor Fix

Turn your factory floor into a live data stream without forcing workers to install another app. This starter uses the WeChat Mini Program to let employees log shifts, confirm pay, and report quality checks right from the phone they already use. It solves the messy problem of paper reports and delayed updates by sending verified data directly to your manufacturing system. The coolest part is how it protects everyone: it ensures only the actual person can clock in and keeps a clear, auditable trail of every single event. It is not a full system, but a clever bridge that makes your data honest and immediate.

🆔 @hackernewsgithubprojects

📦 pluviobyte/douyin-comments

Douyin Comments

Douyin Comments is the agent skill that captures the entire comment section of a single video by using your actual browser session to handle the tricky security signatures. Instead of trying to reverse engineer complex encryption or using fake data, it simply copies the real requests your page is already making to fetch data. This lets you pull every top-level comment and nested reply into a clean, readable text file without needing special software or risking your account getting blocked.

🆔 @hackernewsgithubprojects

📦 win4r/video-director

video-director

Your AI agent can’t watch a video, but video-director forces it to measure every frame. This Claude skill turns coding tools into a full film production pipeline. You write the animation in HTML or Canvas, and the system renders it to MP4. The real magic is the quality check. Two scripts scan your final file for invisible mistakes like a black first frame, unreadable text, or audio that is too quiet. It even verifies your data matches your source files. It’s a strict director that ensures your code looks exactly right before you publish. No more guessing if your animation looks good. You get verified, polished visuals from plain code.

🆔 @hackernewsgithubprojects

📦 wzc520pyfm/gen-ai-pose-image

Lanpose: Generate Whale Girl Art

Generate consistent character art by mixing and matching pose sketches and clothing from a massive library. Lanpose is a web tool that lets you pick a body pose and a costume, then uses an image model to render your chosen character in that exact outfit and stance. It is designed for the community whale-girl model Dafeiyu, but you can import other photos to change the face or clothes. The best part is that it plugs directly into the DeepSeek Harness, letting you command the AI to search and generate images without leaving your workflow.

🆔 @hackernewsgithubprojects

📦 keoyyo85/foundphone-studio

FoundPhone Studio: The AI Phone Story Builder

FoundPhone Studio is a browser-based framework that lets you build interactive, branching stories that play directly inside a realistic virtual smartphone interface. The project’s most interesting feature is that you can feed natural language descriptions, chat logs, and images to an AI tool, which then converts them into a structured, playable narrative without you having to manually code the phone’s UI. It solves the problem of creating complex, multi-ending mobile story experiences by providing a ready-made runtime with over forty app templates, including simulated messaging, calls, and social media.

🆔 @hackernewsgithubprojects

📦 lzyang2000/morphmimic

MorphMimic: One Brain for Many Robots

MorphMimic is the robotics framework that trains one shared brain to control three different humanoid robots at once. Instead of building separate software for every machine, it uses a single policy and world model that adapts to the unique physical traits of each body, from the Unitree G1 to the AgiBot X2 and the Booster T2. The coolest part is the direct VR teleop, where a headset tracks your movement and the robot copies it in real time without complex motion capture setups. It also handles hardware delays so the robots don’t stumble.

🆔 @hackernewsgithubprojects

📦 owls-on-wires/keplearn

Keplearn: Finding the Law of Physics in Your Data

Recover the exact mathematical law hiding inside a spreadsheet of measurements. Keplearn is a compact tool that takes columns of data and hunts for the simple formula connecting them, like finding Newton’s law of gravity in a table of numbers. Instead of just fitting a curve to the points, it searches for a clean, closed-form equation that actually explains the physics. It does this in seconds, often milliseconds, by intelligently guessing mathematical structures and checking if they fit. You get a real formula, not just a black box. If you have data and want the actual rule, not just a guess, this is the tool to try.

📰 https://news.ycombinator.com/item?id=50289590

🆔 @hackernewsgithubprojects

📦 mousebitelabs/game-boy-enhance

Game Boy Enhance

Rebuild your aging Game Boy Advance with crystal clear stereo sound. This open source hardware design replaces every worn out part of your original console except the processor and memory. It fixes the muffled audio found in most retro handholds by adding a dedicated sound chip that delivers crisp, rich audio through your headphones. The board also runs cooler and draws less power than standard modifications, giving you hours of extra play time without sacrificing performance. All design files are available for anyone to build, making it a perfect project for hobbyists who want to rescue damaged units from the landfill.

🆔 @hackernewsgithubprojects

📦 vercel-labs/agent-desktop

How Agent Desktop Sees Your Computer

Agent Desktop is the computer-use tool that finally lets AI agents operate your real desktop apps without guessing from pixels. It reads the actual structure of your windows through the operating system’s accessibility tree, giving the agent a clear map of every button and field. Instead of relying on unstable screen captures, it uses stable references to click and type safely, ensuring actions stay reliable even if the interface changes slightly. This makes automation far more predictable and less prone to breaking. It works across Mac, Windows, and Linux, turning complex screen interactions into simple, verifiable steps.

🆔 @hackernewsgithubprojects

📦 flupkede/codesearch

CodeSearch: The Offline AI Codebase Brain

An AI coding agent can now read an entire company of software repositories at once without sending a single byte to the cloud. CodeSearch is a lightweight server written in Rust that plugs into tools like Cursor and Claude Code to answer questions about your codebase using plain English. It solves the problem of agents getting lost in large projects by chunking your code into logical pieces and searching for meaning, not just keywords. Because it runs entirely offline on your own computer, it keeps sensitive data safe while letting you ask complex questions like where is this function used across five different projects.

🆔 @hackernewsgithubprojects

📦 lalipa2003-arch/jailbreakhub

JailbreakHub: The Prompt Vault

JailbreakHub is the research hub that catalogs exactly how to bypass current AI safety filters. It solves the problem of outdated information by tracking the latest, verified prompt injection techniques for major models like Claude, Gemini, and DeepSeek. The most interesting part is the Multi-AI pipeline, which chains different models together to re-encode a request so one AI helps another break its own guardrails. This collection is a snapshot of how language models are currently being tested for weaknesses. It is not a tool for malicious use, but a clear map of the gaps in our digital defenses.

🆔 @hackernewsgithubprojects

📦 raph651/open-source-canvas

Open Source Canvas: The Graph Is the Studio

Your entire creative workflow runs on a single infinite canvas where every connected node is a working piece of your project. This open source tool turns a simple drag and drop board into a full studio for generating images and video. It connects directly to a local server on your own machine, meaning no data leaves your computer and you have total control over the process. The interface feels like a design tool, with clean connections between prompts, models, and final outputs. It is a rare project that combines the logic of a diagram editor with the power of local artificial intelligence.

🆔 @hackernewsgithubprojects

📦 n1neman/sapper-v2

Sapper V2: The AI Civilization

Sapper V2 is the autonomous security testing system that treats AI not as a single smart tool, but as a whole society. It takes a group of smaller, cheaper models and organizes them into a legion with a commander, generals, and soldiers, all working together to find vulnerabilities in software. The real magic is how these agents share knowledge through a layered memory system, allowing the group to learn from each other’s mistakes and successes without a human micromanaging every step. They won a major hacking competition by using far fewer tokens than their competitors, proving that collective coordination beats raw individual power.

🆔 @hackernewsgithubprojects

📦 dbreunig/nesformer

Running the NES on a Language Model

Play Super Mario Bros using a language model that actually executes the console hardware. This project, called Nesformer, compiles the entire NES CPU directly into the weights of a standard Qwen model. No training happened here; a compiler calculated every single weight to turn the model's internal memory into the chip's actual working memory. When you run a game, the model predicts the processor's execution log token by token, effectively acting as the brain of the retro console. It is surprisingly slow, taking minutes to generate a few seconds of gameplay, but the result is exact.

📰 https://news.ycombinator.com/item?id=50306442

🆔 @hackernewsgithubprojects

📦 datawhalechina/agentic-rl-lab

Agentic RL Lab: Train AI Agents for Pennies

Turn a paper on agent learning into a working experiment for less than the cost of a drink. Agentic RL Lab breaks down complex training methods like GRPO and Search-R1 using plain code and a remote cloud service. Instead of wrestling with eight expensive graphics cards or tangled engineering frameworks, you run these models on a single consumer GPU. The project focuses on one key idea: proving that the math works with just twenty training steps. This low-cost approach lets you verify real improvements in agent behavior without a massive budget. It is the perfect way to understand how language models learn to act, not just generate text.

🆔 @hackernewsgithubprojects

📦 ferluht/fm1-sampler

Turn Your Phone Into a Hardware Sampler with FM1 Sampler

Turn your phone into a full-featured, eight-track sampler by pairing it with a small piece of hardware called the M-VAVE FM-1. This project, named FM1 Sampler, handles all the complex audio processing on the phone while the hardware unit acts as a tactile control surface with physical knobs, buttons, and a tiny screen. The real magic here is the tape-style looper. You can record loops that all share a single moving pointer, meaning when you turn a knob to change the speed, every track speeds up or slows down together, just like spinning a physical tape reel. It’s a unique way to manipulate time in music without using a computer.

🆔 @hackernewsgithubprojects

📦 chris124567/cfsolve

How to Beat the Bot Check Without a Browser

Cloudflare Turnstile is the security gate that decides if you are a human or a script, and most solvers need a full web browser to get through it. CFSolve is a Rust library and command line tool that cracks this code by pretending to be a real iPhone running Safari. It does not open a window or render a page; instead, it performs a full reverse engineering of the challenge logic to answer every question directly. It reconstructs the exact timing, fingerprints, and network signals that a real browser would send, all without launching a single tab.

📰 https://news.ycombinator.com/item?id=50277379

🆔 @hackernewsgithubprojects

📦 joeblau/subvox

Read Your Silent Words with AirPods

Turn quietly mouthed words into text using only the motion sensors inside your AirPods Pro. Subvox is a Mac prototype that ignores audio entirely, relying instead on head and jaw movement to recognize a small set of silent phrases. It uses simple pattern matching and statistical tests to determine if the physical motion actually carries meaningful information, proving that you can communicate without making a sound. It is not a voice assistant, but a proof of concept for silent typing. The takeaway is that your head movement contains enough data to decode speech, opening the door to private, silent communication on your computer.

🆔 @hackernewsgithubprojects