144 subscribers
10.2K videos
10.8K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ mkultraware/accuretta

Accuretta: The Local AI Workspace

Accuretta is the local AI workspace that puts the entire power of a large language model directly on your own computer without any cloud dependency. It combines a chat interface with a practical developer environment, giving the model real access to your files, a live web preview, and persistent terminals so it can actually build things alongside you. The most impressive part is how it handles long, complex tasks by automatically managing its memory and verifying its own code edits, so it never forgets what it is doing. Because everything runs locally through a lightweight Python bridge, your data stays private and you retain full control over the hardware.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ nvidia-medtech/nv-reason-ct

NV-Reason-CT: The AI That Reads 3D CT Scans

NV-Reason-CT is the AI model that finally lets you chat directly with a 3D CT scan. Instead of squinting at flat images, it ingests a full 3D volume and uses a large language model to explain exactly what it sees in plain English. You can ask it to write a structured report, spot specific abnormalities, or answer detailed questions about a patient’s anatomy. It’s fascinating because it bridges the gap between complex medical imaging and natural conversation, making it easier for researchers to explore diagnostic possibilities. It’s not a replacement for a doctor, but it’s a powerful tool for understanding what’s happening inside a scan.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ basecamp/once-campfire-rust

Campfire in Rust: One Binary, 95 Times Faster

Campfire in Rust is the real time chat server that finally proves a single executable can match a full Ruby stack while running up to ninety five times faster. Basecamp rebuilt their Campfire app, which powers real time messaging, from a complex Rails setup into one lightweight binary written in Rust. The defining trick is that it speaks the exact same protocols as the original, meaning it swaps out Ruby, Redis, and a separate web server without breaking existing sessions or changing the user interface by a single pixel. It even reads the old database directly, so you can upgrade without migrating data.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ alextibtab/dungeons2_linux_fix

How One C File Fixes Minecraft on Linux

Minecraft Dungeons II refuses to launch on Linux because it demands a Windows-specific file that simply does not exist in that environment. This project builds a tiny, hand-written replacement for that file, allowing the game to start without touching the original code or shipping any of Microsoft's actual libraries. You run a small script once to sign into your Microsoft account, which saves a token locally so the game can verify you are who you say you are. It is a clever, minimal patch that turns a hard blocker into a simple file swap, proving that sometimes the best fix is just writing the missing piece yourself.

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

OmniEdu: The AI Tutor That Actually Teaches

OmniEdu is an open family of AI models built specifically to teach, not just answer. Unlike general chatbots that might guess their way through a problem, OmniEdu understands the curriculum. It knows exactly what a student should learn next based on their grade level and previous knowledge. This allows it to diagnose exactly where a learner is stuck and guide them with the right hint, rather than just handing over the answer. The project provides three different model sizes, so you can run the smaller versions locally on your own computer. If you are building educational tools, this is a rare find.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ junhan2/oh-my-fable

oh-my-fable: Your AI Agent Finally Works Like You Ask

Stop pasting messy notes into your coding agent and hoping for the best. This new tool takes your rough one-liner and instantly rewrites it into a clear, four-part instruction that actually works. It solves a real problem: AI models often stop halfway, rewrite entire files for tiny fixes, or just stop talking after a progress update. This plugin injects the exact working rules from Anthropic's own guides directly into your session, automatically. It detects if you are typing in a terminal or running in the background, and adjusts the rules so the agent stays on task without needing you to watch.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kindlingai/kindling-spark-os

Kindling Spark OS

A tiny operating system running next to your NVIDIA DGX Spark can give you four gigabytes of extra memory for your AI models. Kindling Spark OS is a minimal, read-only system that installs right beside the standard DGX OS on these specific boxes. It works by booting from a compact disk image that uses a special kernel setting to reclaim two gigabytes of memory, and then lends the other two gigabytes that the graphics driver leaves sitting idle. Because it stays read-only, the system resets itself to a clean state on every boot, keeping your hardware stable and identical across a whole fleet of machines.

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

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

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

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

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

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

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

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

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

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

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

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

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

πŸ†” @hackernewsgithubprojects