📦 millillion/lasm

Lasm: Lean on the Web

lasm is the runtime that finally runs Lean code right inside your browser and Node.js. It bridges the gap between a rigorous mathematical programming language and the fast, sandboxed world of WebAssembly. Imagine writing a web server or a complex calculation in Lean, then deploying it to Cloudflare Workers without needing a heavy C compiler or native dependencies. It handles file systems, networking, and even HTTP requests directly from Lean, giving you the safety of formal proofs with the portability of the web. If you have ever wanted to run trustworthy, verifiable logic in a serverless environment, this project is your ticket to a safer, more precise JavaScript stack.

📰 https://news.ycombinator.com/item?id=50299004

🆔 @hackernewsgithubprojects

📦 auryg/krea-2-two-stage-sampler

Krea 2 Two Stage Sampler

Krea 2 Two Stage Sampler lets you mix two different AI models in the middle of an image generation. Usually, you pick one model and run with it. Here, you run a raw, base model for the first few steps to get a wild, varied sketch, then hand off to a turbo model for the final steps to sharpen the details. It’s like drafting in pencil and then inking in pen, all in one seamless pass. This saves time and often boosts quality, since you get the creative chaos of the raw model and the speed of the turbo finish.

🆔 @hackernewsgithubprojects

📦 snarktank/ralph

Ralph: The AI Loop That Finishes Your Code

Ralph is the autonomous coding loop that finishes your project by itself. Instead of a single chat session that forgets everything, Ralph spins up a fresh AI worker for each small task, letting them pick up exactly where the last one left off. It reads your requirements, writes the code, runs the tests, and only moves on when the work is actually done. If it gets stuck or needs to learn something new, it saves those notes to a file so the next iteration can use them.

🆔 @hackernewsgithubprojects

📦 sksarvesh007/antiglaude

Antiglaude: Run Claude Code on Gemini

Plug Claude Code directly into Google Gemini models using Antiglaude. This local bridge speaks the exact language your coding assistant expects, translating every request into a format Google can process instantly. It handles the messy parts like token refreshes and connection drops so you don't have to think about them. You get a live terminal dashboard to track your usage and switch models on the fly with a single command. It is the perfect way to test powerful reasoning models without changing your existing setup. If you want to mix and match AI engines without the headache, this is your gateway.

🆔 @hackernewsgithubprojects

📦 kait2en/kait2en-fedora

Run Fedora on Your T2 Mac

Kait2en lets you run full Fedora on Apple T2 Macs, unlocking hardware like the Touch Bar, Force Click, and Touch ID on standard Linux kernels. The project uses custom DKMS modules to bridge the gap between Apple's proprietary hardware and the open-source world, ensuring you get the latest security updates directly from Fedora without sacrificing functionality. It also includes a dedicated update tool that intelligently detects changes in the kernel or drivers, letting you apply updates seamlessly without breaking your setup.

📰 https://news.ycombinator.com/item?id=48944340

🆔 @hackernewsgithubprojects

📦 0xsero/video-edit

Video Edit: The Leak-Proof Video Editor

Video edit is the agent skill that finally stops your screen recordings from leaking secrets. It turns a messy, ninety-minute OBS capture into a tight, upload-ready YouTube video by using a transcript to decide exactly where to cut. The coolest part is how it scans your finished video with optical character recognition to guarantee no API keys or hostnames slipped through. It also catches awkward webcam moments so you never ship an embarrassing clip. Once the render is done, it runs a verification gate to prove the file is clean. If you record software demos, this is the safety net you have been missing.

🆔 @hackernewsgithubprojects

📦 zedlanguage/zed

Zed: The Language That Checks Itself

Zed is a new programming language where the compiler proves your code is correct before it even runs. Built specifically for the AI era, it automatically parallelizes your data flow so you get massive speed without writing complex threading logic yourself. It also features static verification that catches errors at the design stage, preventing bugs that would usually only show up during execution. The project is currently in early development, with a Rust-based toolchain handling parsing and evaluation while a separate certificate checker validates the logic. This approach ensures high reliability for complex AI workloads.

🆔 @hackernewsgithubprojects

📦 sentinelabs/verified-ida

Verified IDA: How to Trust AI Reverse Engineering

Verified IDA is the reverse engineering harness that finally ensures every AI claim is backed by hard evidence. It acts as a strict gatekeeper between a language model and a disassembler, forcing the AI to show its work before any code annotation is saved. Instead of accepting a guess, the system verifies that the model actually looked at the right bytes and that the database update persisted correctly. This is crucial because it stops artificial intelligence from making confident but incorrect assumptions about complex software. It turns a chaotic chat log into a verifiable technical record.

🆔 @hackernewsgithubprojects

📦 christopherowen/spark-ds41f

Running DeepSeek V4.1 Flash Without a Network Switch

A massive AI model that usually demands a room full of servers now runs on just three or four small desktop boxes connected directly to each other. This repository, spark-ds41f, turns that ambitious setup into a reliable, repeatable experiment by packaging the entire deployment into a single Docker container. Instead of relying on a central network switch to juggle data, these machines talk straight to one another, which cuts out a major bottleneck and simplifies the whole architecture. The project doesn't just show that it works; it provides the exact tuning steps and benchmark results so anyone can verify the performance themselves.

🆔 @hackernewsgithubprojects

📦 taikeid/steam-frame-full-keyboard

Type Like Magic in Steam Frame

Stop squinting at tiny virtual keys and start typing like a pro in your headset. Full Keyboard for Steam Frame is a native app that replaces the clunky default with a massive, fully functional board right in front of you. It includes dedicated copy and paste buttons, a numpad, and even voice dictation so you can literally talk your text into existence. The best part is that it supports thirty-seven languages with a swipe feature for quick words. No weird browser windows, just smooth, native input that feels like a real desktop. It is free, open source, and makes gaming on the Frame so much more comfortable.

🆔 @hackernewsgithubprojects

📦 drclcomputers/gosheet

GoSheet: The Spreadsheet That Lives In Your Terminal

GoSheet is the terminal spreadsheet that brings full desktop power to your command line. It runs entirely in your text editor, meaning no heavy graphical interface, just pure speed. The coolest part is its formula engine, which includes one hundred and twelve built-in functions, so you can do complex math, lookups, and data validation without ever leaving the prompt. It even reads and writes real Excel files, so you can crunch numbers right where you work. If you live in the terminal and hate switching windows, this is your lightweight, high-performance spreadsheet solution.

🆔 @hackernewsgithubprojects

📦 xinxinliu-ai/agenticroborl

Teaching Robots to Code: AgenticRoboRL

Boost a small robot’s success rate from eighteen to seventy-one percent by teaching it to code, exactly like you’d train a coding assistant. AgenticRoboRL takes the brain that plans a robot’s actions and improves it using real trial-and-error data from the machine itself. Instead of just watching videos, the planner practices in a digital simulator, learning from its mistakes and successes to get better at solving complex tasks. This approach lets a tiny, efficient model punch way above its weight, matching the performance of much larger, slower systems without needing extra memory or massive hardware.

🆔 @hackernewsgithubprojects

📦 kenryu42/cc-safety-net

CC Safety Net: Stop AI Agents from Breaking Your Code

CC Safety Net is the guardrail that stops AI coding agents from wrecking your computer. It inspects every command an agent plans to run, blocking destructive actions like deleting your entire project or stealing your private keys before they actually happen. This is huge because you can let AI help you code without constantly hovering over your shoulder, terrified it might make a catastrophic mistake. It is not a heavy sandbox; it is a smart filter that lets safe work flow through while catching the disasters. If you use tools like Claude Code or Cursor, this is the peace of mind you have been missing.

🆔 @hackernewsgithubprojects

📦 mandiant/gopacket

Gopacket: The Complete Go Port of Impacket

Gopacket is the single-binary toolkit that brings the entire power of Impacket to the Go language. It compiles sixty-three command-line tools and twenty-four libraries into one self-contained executable, meaning you never need to manage Python environments or install dependencies on your target system. This project solves the friction of running complex Windows and Active Directory protocol attacks by providing a static, portable tool that runs anywhere. For security professionals and developers, this means you can execute intricate network tasks without worrying about missing libraries or version conflicts. It is a complete, standalone replacement for a legacy suite, packaged into a simple, efficient file.

🆔 @hackernewsgithubprojects

📦 realidkroo/mochy-music

Mochy Music: The Android Player With A Twist

Mochy Music is an Android app that doesn't just play your files, but actively hunts down lyrics from over a dozen global services. This is the big surprise because it bridges the gap between local storage and online metadata. It solves the annoying problem of missing lyrics by automatically matching songs against massive databases. You get a sleek, modern player that feels alive. It is built for people who want their music to look and feel right. The interface is smooth and the feature set is deep. This is not just a music player, it is a music companion. It respects your library while enhancing it.

🆔 @hackernewsgithubprojects

📦 langchain-ai/design-agent

design-agent: Chat Your Way To Brand-Perfect Video

design-agent is the creative tool that turns a simple chat message into on-brand videos and graphics. It solves the problem of needing a dedicated designer for every small visual asset you need. By describing what you want in plain text, it generates motion graphics, slides, and charts that already match your company’s visual style. This removes the heavy lifting of manual editing and design consistency checks. You get a full media production pipeline running in the background of a conversation. It is a fascinating look at how far autonomous agents have come for creative tasks.

🆔 @hackernewsgithubprojects

📦 cauliflowermossgrape/idrive7-apps

iDrive 7 apps

The most surprising thing about iDrive 7 apps is that it turns the standard BMW infotainment screen into a sixty frames per second gaming console and performance dashboard. Most custom car displays rely on slow image updates that look choppy, but this project uses a specialized rendering engine to draw smooth, real-time animations directly on the car's graphics processor. You get tools like a virtual dyno for measuring power, precise drag timers, and even a playable version of Doom running in the middle of your dashboard. The repository also includes a development kit, so anyone can build and install their own custom applications.

🆔 @hackernewsgithubprojects

📦 leonxlnx/tastecode

TasteCode: The Design Hub for Coding Agents

TasteCode is a local desktop application that acts as a single window for managing multiple AI coding agents. The most surprising feature is its built-in Design Mode, which lets you visually inspect and edit web interfaces directly within the agent's workflow. Instead of jumping between separate tools for code and design, this app keeps your project state, terminal access, and visual changes in one place. It supports popular agents like Codex and Claude Code, ensuring your credentials stay on your machine. By combining coding orchestration with visual design editing, it solves the disconnect between writing code and seeing the result.

🆔 @hackernewsgithubprojects

📦 asklokesh/loki-mode

Loki Mode: AI Coding Proofs

Hand a task to an AI coder and get a finished pull request that includes a digital stamp of approval you can verify yourself without trusting a third party. Loki Mode is an autonomous software factory that runs on your own machine with your own API keys. You give it a GitHub issue or a simple spec, and it handles the entire coding process until a verified result is returned. The standout feature is the signed receipt attached to every job. It allows anyone to re-check the work offline to confirm the AI actually did what it claimed.

🆔 @hackernewsgithubprojects

📦 ltplus-ag/ifc-lite

IFClite: The Browser-Native Building Model Tool

IFClite is the browser-first toolkit that makes heavy building models feel light in your web app. It runs a Rust core compiled to web assembly directly in your browser, meaning no server is needed to parse or render complex architectural files. The standout feature is its geometry kernel, which calculates shapes with exact arithmetic to guarantee mathematical precision right on the client side. You can query specific data, like finding every load-bearing wall, without sending the file to a backend. This gives developers a fast, local way to handle industry standard building files.

🆔 @hackernewsgithubprojects