📦 chenxiaolong/basicsync

BasicSync: Syncthing for Android

BasicSync lets you run Syncthing on your Android phone without draining your battery or burning through your data plan. The clever part is that the app stays intentionally minimal, so it does not clutter your phone with extra settings. You simply set the rules for when syncing should happen, like only on Wi-Fi or when charging, and then let the background service handle the rest. For configuration, you just open a local web page on your phone to manage your folders. It is a smart way to keep your files in sync without worrying about your phone’s hardware, making private backup actually easy to use every day.

📰 https://news.ycombinator.com/item?id=49218439

🆔 @hackernewsgithubprojects

📦 fiorastudio/buddy

Buddy: The Virtual Pet That Saves Your Coding Sessions

Take control of your coding sessions with Buddy, a virtual pet companion that turns dry terminal feedback into a persistent, personality-driven experience. Instead of generic code reviews, Buddy watches your reasoning patterns and gently calls out shaky assumptions before you commit them, acting like a friend who actually checks your work. It remembers every session using local storage, so your companion grows, levels up, and develops a unique mood based on how much you interact with it. You can even rescue old buddies from other tools, giving them a permanent home that survives app updates.

📰 https://news.ycombinator.com/item?id=47792606

🆔 @hackernewsgithubprojects

📦 albertozurini/echo-dot-2-playground

Echo Dot 2 Playground

Echo Dot 2 Playground is the clever hack that turns an old Amazon speaker into a private, cloud-free AI assistant. Instead of your voice data drifting off to Amazon's servers, this project strips out all the proprietary bloatware and installs a lightweight language model that lives entirely on the device. It sounds wild for such an old gadget, but it actually works by hacking the underlying audio system to catch wake words and then uses a tiny neural network to understand your commands right there on the chip. You get all the convenience of voice control without anyone listening in or tracking your habits.

🆔 @hackernewsgithubprojects

📦 skmp/dreamster

Dreamster: Run Dreamcast Games on MiSTer

Dreamster lets you play original Sega Dreamcast games on your MiSTer FPGA hardware, using a custom launcher that temporarily swaps out the main system process. It wraps up polly2-rtl and minicast into a single Python tool, so you can load your game library from the SD card or an external drive without rebuilding the FPGA every time. The project is still experimental, meaning it takes a bit of a risk by killing the MiSTer process to take over the console and then restarting everything once you are done. This approach is clever but tricky, so you need to be ready for some instability.

🆔 @hackernewsgithubprojects

📦 76696265636f646572/airwave

Airwave: The Shared Radio for YouTube

Airwave is the shared internet radio that finally lets everyone listen to the exact same track at the exact same time. Instead of each person playing their own separate stream, this self-hosted tool grabs YouTube, SoundCloud, or MixCloud links and creates one single live audio feed for the whole group. You just paste a playlist, share a link, and all your friends or family members tune in to hear the same song together. It even talks to Sonos speakers so the music plays across your whole house in perfect sync. No accounts needed. Just pure, shared listening that actually stays together.

📰 https://news.ycombinator.com/item?id=47715699

🆔 @hackernewsgithubprojects

📦 benjiyaya/minimax-h3-prompt-agentskill

MiniMax H3 Prompt Agent Skill

Transform your messy video ideas into professional-grade prompts with the MiniMax H3 Prompt Agent Skill. This clever tool takes your rough concepts and attached media, then automatically structures them into the exact format needed for MiniMax H3 video generation. It handles five different modes, from text-to-video to image-anchored sequences, and enhances your brief with cinematic details like camera movement, lighting, and sound design. You get a clean, ready-to-paste prompt that preserves your dialogue and maintains character consistency across shots. It is a massive time-saver for anyone using ComfyUI or Hermes Agent. Stop guessing how to format complex video instructions and start generating precise, high-quality scenes with confidence and ease.

🆔 @hackernewsgithubprojects

📦 v4bel/zapscape

Zapscape: KVM Escape

Zapscape is the security research that finally breaks the virtual machine prison on x86 processors. It is a detailed documentation of a vulnerability that allows a guest operating system to escape its sandbox and execute code with full administrative privileges on the host machine. This works by exploiting a tricky memory management bug where the system accidentally reuses a corrupted piece of memory during a cleanup process. The creator provides a proof of concept that demonstrates how a single virtual machine can take over the physical server running it. This matters because it shows that even with nested virtualization enabled, the isolation between cloud tenants is not guaranteed.

📰 https://news.ycombinator.com/item?id=49198843

🆔 @hackernewsgithubprojects

📦 agricidaniel/skill-forge

Skill Forge: Build AI Agents for Claude Code

Build production-grade AI agent skills from scratch without wrestling with complex documentation. Skill Forge lets you design, scaffold, and publish high-quality Claude Code skills using a simple, structured workflow. It solves the headache of creating reliable, reusable AI tools by guiding you through planning, building, and reviewing your skill with clear templates and automated checks. You get to turn vague ideas into structured, functional skills that actually work well, complete with quality scores and easy publishing steps. It is a clever way to standardize how you create these powerful AI assistants, making the whole process much less chaotic and far more repeatable.

🆔 @hackernewsgithubprojects

📦 nikodemon80/comfyui-h3-motion-context

ComfyUI H3 Motion Context

Chain MiniMax H3 video clips so motion and audio genuinely continue across joins instead of restarting from scratch. This project patches ComfyUI to let your next clip pick up exactly where the last one left off, keeping the same direction, speed, and even the exact same audio waveform rather than generating a similar sound. It solves the annoying problem of disjointed cuts by lifting a technical restriction in the original code that blocked intermediate frames. The real magic is in the audio handling, which forces the model to continue the actual recording rather than imitating it, creating seamless transitions that feel natural.

🆔 @hackernewsgithubprojects

📦 gen-verse/skill-entropy-rl

Skill-Entropy RL

Skill-Entropy RL is the open-source toolkit that finally trains large language models to switch between different thinking styles without breaking a sweat. Most AI models struggle when a task requires hopping from coding to logic or math in one go, because they learn to treat every problem as a single, flat skill. This project solves that by teaching the model to recognize when it is switching skills and rewarding it for planning that transition smoothly. It uses a special reward system that scores the model’s ability to juggle these changes, not just the final answer.

🆔 @hackernewsgithubprojects

📦 zhouhao1024/awesome-self-evolving-coding-agents

Awesome Self-Evolving Coding Agents

Awesome Self-Evolving Coding Agents is the curated research library that maps how artificial coders are learning to fix their own mistakes without human help. Instead of just writing code once, these systems analyze their errors, adjust their own logic, and grow smarter with every attempt. This repository gathers the latest academic papers, testing benchmarks, and foundational studies that make this possible. It is a vital guide for developers wanting to understand the shift from static tools to autonomous engineers that improve over time. Check it out to see the future of self-improving software in action.

🆔 @hackernewsgithubprojects

📦 zethwang/agentopsd

AgentOPSD: Smarter AI Learning

AgentOPSD is a reinforcement learning trick that finally helps AI agents learn from their own mistakes without needing extra help. Most AI models struggle when playing long games because they only get a final score, leaving them confused about which specific moves actually mattered. This project solves that by tracking the difference between what the AI thought it knew and what it actually did at every single step. It recursively updates a belief state to pinpoint exactly those pivotal turns that changed the outcome. This turns sparse feedback into dense, useful lessons.

🆔 @hackernewsgithubprojects

📦 xoreaxeaxeax/asm-hall-of-shame

The Slowest CPU Instruction Ever Measured

Make a single line of code take over a minute to finish. This repository is a quirky leaderboard that tracks the absolute slowest possible CPU instructions on modern processors. Instead of optimizing for speed, it intentionally engineers catastrophic slowdowns to see just how terrible performance can get. The number one spot uses a trick where one processor core tries to load a massive chunk of data from a surprisingly slow piece of hardware memory while several other cores aggressively pound on different parts of that same hardware to create a massive traffic jam.

📰 https://news.ycombinator.com/item?id=49214098

🆔 @hackernewsgithubprojects

📦 within-yao/envace

EnvACE: AI World Rehearsal

EnvACE lets an AI model practice solving problems by imagining the entire interaction before actually taking action. Instead of relying on an external simulator or real-world tool calls during training, this framework teaches the model to play two roles at once. First, it acts to generate a response. Then, it rehearses by predicting exactly how the environment would react to that specific action. By training this internal world model, the AI learns to predict its own future consequences, allowing it to run multiple imagined trial runs in parallel, summarize the best approach, and then commit to a single real execution.

🆔 @hackernewsgithubprojects

📦 veris-ai/riley-agent

Riley Agent: Test Voice AI with Real Banking Data

Riley Agent is the open-source benchmark that finally lets you compare every major voice AI platform using the same realistic banking support scenario. It solves the messy problem of testing voice assistants by giving you a consistent, simulated customer service workflow where an AI agent named Riley helps users manage fake credit cards. Instead of wrestling with different setups, you can drop in implementations from giants like OpenAI, Google, or AssemblyAI and watch them handle the exact same conversations with synthetic bank data.

🆔 @hackernewsgithubprojects

📦 gen-verse/past-bench

How Agents Actually Learn From Mistakes

PAST-Bench tests if personal AI agents can genuinely improve over time by learning from past mistakes. Instead of grading isolated tasks, it runs agents through long sequences where early experiences are supposed to help them handle later challenges better. The repo includes a clever framework called Hermes+ that adds specific memory and routing tools to help agents remember and reuse what they have learned. It essentially asks whether an AI remembers its previous failures and uses that knowledge to act smarter next time, rather than starting from scratch every time you talk to it.

🆔 @hackernewsgithubprojects

📦 msp-xen/ae-uav

AE-UAV: The First Air-to-Air Event Camera Drone Dataset

AE-UAV is the first air-to-air event camera drone dataset that turns jagged tracking labels into smooth, continuous motion paths. Most video datasets only check if an object is inside a box every few frames, but AE-UAV captures billions of raw sensor events and maps a perfect, curve-fitted trajectory across every single microsecond. This means researchers can evaluate drone tracking systems at any speed without guessing what happened between frames. It features nearly two hundred flight sequences captured from one drone chasing another, complete with thermal and RGB video for extra context.

🆔 @hackernewsgithubprojects

📦 aweai-team/calibforge

CalibForge: AI Terminal Calibration

CalibForge transforms how artificial intelligence learns to use command lines by filtering out tasks that are either too easy or impossible to solve, leaving only the perfect middle ground for training. Instead of dumping thousands of random coding challenges on a model, this project uses an adversarial process where different AI agents try each task and only the ones with mixed results survive. This creates a curated dataset of five thousand precise terminal exercises that force the learner to actually think, rather than guess. By training on this calibrated data, models see massive performance jumps on software engineering benchmarks because they are learning from genuine difficulty.

🆔 @hackernewsgithubprojects

📦 fudan-generative-vision/dynetrion

Dynetrion: The AI That Simulates Protein Movement

DyneTrion is the generative model that finally captures how proteins move and change shape over time. Most AI tools only guess what a static molecule looks like, but this project simulates the actual physical dance of atoms across different time scales. It solves the headache of predicting how complex biological structures shift and flex in real life. By training on massive datasets of molecular dynamics, it creates smooth, realistic animations of these tiny machines working. This matters because seeing the motion helps scientists understand diseases and design better medicines. It turns confusing data into clear, playable video clips of biology in action.

🆔 @hackernewsgithubprojects

📦 mbbill/mind-expander

Mind Expander

AI coding tools write fast code but explain it through exhausting walls of text. Mind Expander changes that by instantly turning your Rust or TypeScript codebase into an interactive, infinite-canvas browser diagram. Instead of reading long markdown summaries, you and your AI agent work on the exact same visual graph of modules, dependencies, and refactoring plans. It translates complex relationships and system architecture into a clear, source-backed visual tour you can click through. It is like having a GPS map for your system architecture that actually links back to your live files, making code reviews and refactoring plans incredibly simple to verify.

📰 https://news.ycombinator.com/item?id=48281337

🆔 @hackernewsgithubprojects