📦 shanghua-gao/rsi-jev

AI Agents That Retire Their Own Failed Models

Build a model that answers questions in a single lightning-fast pass without generating text. That is exactly what RSI-Jev does. Instead of a human tweaking settings, a loop of AI agents proposes new ideas and tests them on the computer. If an experiment fails, the agent records why it did not work and moves on. If it succeeds, that version becomes the new standard. The project keeps every failed attempt in the open, so you can see the exact path from a weak start to a strong result. It is a self-driving research lab that improves itself by its own measurements.

🆔 @hackernewsgithubprojects

📦 kamra-pms/kamra-pms

Kamra: The Hotel Software That Works For You

Run your entire hotel without paying per-room rent, thanks to Kamra. This free, open-source property management system handles check-ins, housekeeping, and even restaurant orders, all in one place. But here is the real kicker: it lets an A.I. agent actually work your front desk. You can connect a tool like Claude to book rooms, check availability, and audit nightly totals. The catch? The money math is locked in code, so the A.I. never guesses your taxes or rates. It is a full control center that stays yours, forever. If you run a hotel or rental, this is the software you own, not rent.

🆔 @hackernewsgithubprojects

📦 openroboto-ai/jev-robot-control

Jev Robot Control: The $0.02 Apple Test

A new language model called Jev just picked up an apple and placed it on a plate in a physics simulator for less than two cents, while a much more expensive model spent nearly six dollars to do the same thing. This repository, Jev Robot Control, pits three different A.I. brains against a virtual robotic arm to see who can actually move a real object. The models do not see video; they only read numerical data about the robot's position and guess the next small movement to make.

🆔 @hackernewsgithubprojects

📦 alexknowshtml/claude-auto-handoff

Claude Auto Handoff: The End of Context Anxiety

Claude Auto Handoff is the session manager that finally gives your AI a proper memory stick instead of a shrinking brain. It watches your context usage, and right before things get messy, it pauses the conversation to write a detailed, structured summary of exactly where you left off. It then wipes the slate clean and boots up a fresh, fully charged session that reads that note and jumps straight back into the work. This kills the annoying mid-task summarization lag and keeps your coding flow running on full steam. No more fighting the memory limit, just smooth, continuous productivity that feels like magic.

🆔 @hackernewsgithubprojects

📦 lolipopshock/pi-clm

pi-clm: The AI Agent That Edits Its Own Memory

A coding agent now holds a live file representing its own short-term memory, allowing it to rewrite, delete, and reorganize its past thoughts just like a human editing a document. This tool, named pi-clm, solves the problem of context windows filling up and crashing long sessions by letting the model decide exactly what to keep and what to discard. It acts as a self-managing librarian for the computer, ensuring the agent stays sharp without human intervention. By treating conversation history as editable text, it gives developers a transparent way to see how an AI thinks, organizes, and prunes its own understanding of a complex task.

🆔 @hackernewsgithubprojects

📦 imbutus/comfyui-minimaxdirector

Directing Video Like a Director

Stop cramming everything into one giant text box and hoping for the best. With MiniMax Director, you lay out your video like a real editor, arranging shots, camera moves, and dialogue right on a timeline. This tool takes your visual plan and compiles it into the exact structured prompt the MiniMax H3 model needs to understand. It automatically handles the tricky math of frame counts so your clip length is always valid for the sampler. You get to see the final prompt update live as you tweak your shots, meaning no more guessing if the AI understood your vision. It turns a chaotic prompt into a precise, professional shot list.

🆔 @hackernewsgithubprojects

📦 spacestate1/namco22-decompile

namco22-decompile

Classic nineties arcade games are running natively on modern computers thanks to a dedicated recreation effort. The namco22-decompile project has painstakingly decompiled the original program code for Namco System 22 arcade hits like Prop Cycle, Rave Racer, Tokyo Wars, and Dirt Dash. By translating the software back into clean C code and matching it against original hardware behaviors, developers can now compile and play these experiences directly on Linux and Windows. It side-steps traditional emulator overhead to offer features like native widescreen support, custom resolutions, and integrated controller mapping. All you need are your own original game ROM files to jump straight in.

🆔 @hackernewsgithubprojects

📦 tomforsyth1000/dashr

DASHR: The Future of Real-Time Animation

A single executable now renders complex, skin-deformed heightfields in real-time DirectX, solving the heavy computational cost of dynamic terrain animation. This project, called DASHR, allows developers to visualize fluid, mesh-based ground deformation without the lag typical of standard graphics pipelines. It is particularly useful for anyone testing advanced physics or environment rendering on Windows, as it provides a complete, working demo that bypasses complex setup requirements. The code is straightforward and accessible, making it a practical tool for experimentation rather than just a theoretical concept. If you are curious about how modern graphics engines handle dynamic terrain, this repository offers a clear, functional example of the technology in action.

🆔 @hackernewsgithubprojects

📦 tuzhechen2005/opus-video-skills

Opus Video Skills: AI-Coded Video Creation

Your entire video, from the first frame to the final musical note, is generated purely through code without any traditional media files. This project called Opus Video Skills teaches an artificial intelligence assistant to create complete, polished motion graphics entirely from scratch. It solves the heavy lifting of video production by letting you type a simple prompt and having the system handle everything else. The software automatically draws every scene, animates the text, and even composes the background music in sync with the visuals. It is interesting because it treats video creation like writing a computer program rather than editing clips.

🆔 @hackernewsgithubprojects

📦 patchy631/jev-as-judge

Jev-as-a-Judge: Testing AI Refund Replies

Test whether an AI support bot is lying about refunds using a single, auditable evaluation run. This project, called Jev-as-a-Judge, solves the problem of trusting automated customer service by replaying a frozen set of tricky support chats against a language model judge. It is interesting because it prioritizes transparency, recording every raw answer and model version so you can see exactly how the verdict was reached. Instead of just giving a pass or fail, it breaks the reply down into specific checks for factual grounding and honesty. This makes it a practical, offline-friendly tool for anyone wanting to verify AI behavior without building a complex infrastructure.

🆔 @hackernewsgithubprojects

📦 yfyeung/prunedctc

Pruned CTC: Smarter Speech Training

Pruned CTC is the training tool that finally stops your computer from running out of memory when teaching speech models to recognize thousands of different words. The real surprise here is that it calculates the exact same correct answer as standard methods but uses far less space. Instead of storing a massive table of every possible word for every moment in time, it only looks at the specific words you are trying to learn right now. It does this by breaking the calculation into tiny pieces and throwing away the heavy data as soon as it is done.

🆔 @hackernewsgithubprojects

📦 vincemakes/kiso

kiso: The AI Agent That Remembers Everything

The most surprising thing about this AI agent is that it actually survives getting killed. Most coding assistants you run in your terminal vanish the instant your laptop crashes or you close the window, losing all your work in the process. This project solves that by writing every single step of the conversation to disk as it happens. So if your computer dies mid-task, you can just tell it to resume, and it picks up exactly where it left off without repeating any steps that already worked. It is essentially a durable memory for your AI helper, ensuring that a power outage doesn't wipe out hours of code.

🆔 @hackernewsgithubprojects

📦 jaydendavisnc/inkwave

Inkwave: The Browser Game That Builds Itself

Paint your team's color across a wet plaza while swimming through your own ink to refill and dodge. That is the core of Inkwave, a four versus four turf war shooter that runs entirely in your web browser without needing any heavy install. The most surprising part is that every single piece of the game is generated by code. The characters, the sound effects, the music, and even the textures are all procedurally created in real time. There are no downloaded asset files to load, which makes the whole experience remarkably light for a full 3D shooter.

🆔 @hackernewsgithubprojects

📦 mem0ai/openmemory

OpenMemory: Keep your AI coding context

OpenMemory is the open source tool that finally stops your AI coding work from getting stuck when you switch tools. It lets you move your actual chat history between different AI coding assistants like Claude Code and Codex in one go. Instead of losing your progress, you simply pick up right where you left off with all your context intact. It works by reading your old sessions and writing them into the new tool so you never have to start from scratch again. You can choose exactly which conversations to move, keeping your workflow smooth without any manual copying.

🆔 @hackernewsgithubprojects

📦 tarquinen/opencode-vim

opencode-vim: Vim for OpenCode

Your OpenCode terminal just gained the editing power of Vim, meaning you can now navigate your entire chat history and edit prompts without ever touching your mouse. This plugin brings familiar keyboard shortcuts directly into OpenCode, letting you scroll through messages, copy text, and refine your inputs using standard commands. It solves the friction of switching between your cursor and keys by keeping your hands on the home row, which is a huge win for speed and muscle memory. If you use OpenCode daily, this small update makes your workflow significantly faster and more precise.

🆔 @hackernewsgithubprojects

📦 makevoid/motion-graphics-music-video-skill

motion-graphics-music-video-skill

Turn your audio tracks into high-quality, fully edited motion graphics videos with just a single text prompt. This clever Claude Code plugin coordinates an entire production crew directly from your terminal. It acts as an automated director that analyzes your song's beats, maps out character references to keep faces consistent across scenes, and coordinates video generation models to animate everything perfectly. Local scripts handle the heavy lifting, using Python for audio mixing and Swift on macOS for blazing-fast video effects. If you make music and want professional videos without opening a complex editing timeline, install this plugin and let the agent build a masterpiece for you.

🆔 @hackernewsgithubprojects

📦 ryleighnewman/inputconfig

InputConfig: Turn Any Controller into a Mouse

InputConfig turns any game controller into a full keyboard and mouse on your Mac, letting you play unsupported games or drive your desktop without touching a single key. You can map buttons to type whole words, move the cursor, or even trigger Siri Shortcuts, and it works with everything from Xbox pads to MIDI keyboards. The coolest part is accessibility: you can run your whole computer from just one stick, making it a lifeline for people with limited mobility. No drivers, no subscriptions, and no data collection, it just works.

🆔 @hackernewsgithubprojects

📦 jwuthri/selfjev

Selfjev: The AI That Just Says Yes Or No

A tiny language model can answer complex questions without writing a single word. Selfjev is an open decisions model that skips the usual chatbot style entirely. Instead of generating text, it runs a quick check through a four billion parameter brain on a single graphics card to give you a typed answer with a confidence score. You ask if something is true, which option is best, or rate a score, and it just outputs the result. No essays, no fluff, just the decision. It solves the problem of needing a fast, deterministic answer from an AI without the slow, expensive process of generating every token.

🆔 @hackernewsgithubprojects

📦 levy-street/pokemon-claude-red

Pokemon Claude Red: The Game Made Entirely of Code

Pokemon Claude Red is the browser game that proves you don’t need image files to make a pixel art masterpiece. It is a full remake of the original Pokemon Red, built by an AI that draws every sprite, tile, and musical note directly in code. There are zero image files here; the game calculates the visual look of everything on the fly. You get the complete story, all one hundred and fifty-one Pokemon, and the classic glitches, all running right in your web browser. It is a wild look at what artificial intelligence can do when you ask it to build a world from scratch.

🆔 @hackernewsgithubprojects

📦 peterfriese/system-one-foundation-models

System One for Apple Foundation Models

Plug structured logic directly into Apple's native AI framework to get instant, guaranteed answers. This library connects a decision model to the Foundation Models API, so instead of asking a chatbot to guess, you define strict rules and get a definitive result in under two hundred milliseconds. The standout feature is the ability to run this logic entirely on your phone without touching the internet, using the device's built-in neural engine to keep data private and latency near zero. It transforms fuzzy AI text generation into precise, typed code that developers can trust for critical tasks like email triage.

🆔 @hackernewsgithubprojects