📦 timgordontg/engrim

engrim: The Save Button for Your AI Code

Your AI coding assistant has a terrible habit of forgetting everything the moment you clear the chat, which is basically like paying for a brilliant intern who amnesically loses their notes every afternoon. Engrim fixes this by acting as a shared, local memory file that lives right on your computer. Instead of letting the agent forget why you chose a specific database or why you rejected a certain design pattern, this tool automatically saves those decisions into a tiny, readable file. The coolest part is that it works across different tools, so if you switch from one AI helper to another, your project context doesn't vanish.

📰 https://news.ycombinator.com/item?id=49594008

🆔 @hackernewsgithubprojects

📦 mrajaeim/image-pipes

Image Pipes: Build Vision Pipelines Visually

Image Pipes is the visual editor that turns computer vision coding into a drag-and-drop experience. Instead of writing scripts and guessing results, you connect processing blocks like resizing or blurring on a canvas to see exactly how your image changes in real time. The most surprising part is that once you are happy with your setup, it exports clean, standard Python code. This means you are never locked into the tool; you can take that code and drop it directly into your own projects. It is a great way to experiment with image processing without getting stuck in the code loop.

🆔 @hackernewsgithubprojects

📦 speridlabs/eneas

ENEAS: The AI That Tracks Objects With Words

ENEAS is the video segmentation tool that finds objects using plain English. It solves the headache of manually marking every frame by letting you describe what you see, like the person in the red jacket. The system then tracks that specific item across the entire clip, giving you a clean black and white mask for every single picture. This is great for anyone who needs precise object tracking without drawing boxes by hand. It turns a tedious manual task into a simple text command, saving you hours of work.

🆔 @hackernewsgithubprojects

📦 jdcodes1/facebook-marketplace-mcp

Facebook Marketplace MCP

Turn your AI assistant into a personal shopping scout by letting it search Facebook Marketplace directly. This tool bypasses slow browser automation by reading your existing Chrome login cookies on your Mac and speaking Facebook’s internal data protocol, just like the website does. It’s essentially a reverse-engineered shortcut that lets your AI find specific items, check prices, and monitor new listings in seconds rather than minutes. While it does require a Mac and carries the usual risks of automating a social platform, the speed is surprisingly snappy. If you want your AI to hunt for deals while you sleep, this is the tool to watch.

📰 https://news.ycombinator.com/item?id=47712705

🆔 @hackernewsgithubprojects

📦 step-out/motion-omni

Motion-Omni: The AI That Moves While It Speaks

Motion-Omni is the dialogue model that finally moves its whole body while it talks. Instead of generating speech first and then guessing how to animate a character afterwards, this system predicts facial expressions, hand gestures, and limb movements in the exact same step that it produces the voice. This means a single computational pass creates a fully embodied response, making the character feel much more alive and synchronized than previous approaches. It represents a significant shift towards more natural human-computer interaction by linking language directly to physical movement.

🆔 @hackernewsgithubprojects

📦 liyue-aigc/seedance-2-5-video-director

Seedance 2.5 Video Director: The AI Director's Playbook

Seedance 2.5 Video Director is the prompt toolkit that turns vague video ideas into precise, copy-ready instructions for AI video tools. Instead of guessing what an AI understands, you feed it your raw concept, reference images, or even a bad previous prompt, and it acts like a professional director to organize the chaos. It handles the tricky stuff, like locking a character's face so it doesn't change between shots or ensuring a seamless transition between two clips. It doesn't generate the video itself, but it builds the exact text you need to get the result you want, saving you from endless trial and error.

🆔 @hackernewsgithubprojects

📦 everettfish/holo-card-studio

Holo Card Studio

Describe a character and Holo Card Studio builds a fully interactive three-dimensional collectible card for you. The system generates layered digital art, constructs a physical model in Blender, and exports it into a live web page where the holographic foil actually reacts to your screen angle. This turns a simple text prompt into a dynamic digital object you can spin, flip, and adjust in real time, preserving your specific style and typography. It is a clever way to bridge static design tools with live web technology. Watch the light bend as the card moves. That is the magic you get to keep.

🆔 @hackernewsgithubprojects

📦 layer6ai-labs/cfms

Causal Foundation Models: No Training Needed?

Predict causal effects on new data without training a single new model. This is the coolest part. Causal Foundation Models let you estimate how a treatment affects individuals by simply showing the network a small example dataset. It uses in-context learning to figure out the causal relationship on the fly. You skip the expensive retraining phase entirely. Instead, you just load your data and get instant predictions. This repository gives you the quickest path to doing exactly that. It includes a quickstart notebook and a sandbox to test three different models side by side. You can even run benchmarks against traditional methods to see how they stack up.

🆔 @hackernewsgithubprojects

📦 superxslam/tartanimu

TartanIMU: One Model for All Robots

TartanIMU is the single model that tracks any robot or human using only an inertial sensor. Usually, tracking algorithms need to be built separately for each type of movement, like a car or a dog. This project changes that by training one network on over one hundred hours of data from cars, quadrupeds, drones, and humans. It learns to predict three-dimensional velocity just from acceleration and rotation data. This means one set of weights can handle all these different bodies without needing specific settings for each. If you work on robotics state estimation, this is the universal positioning tool you have been waiting for.

🆔 @hackernewsgithubprojects

📦 alchaincyf/loop-engineering-orange-book

Loop Engineering: Stop Prompting, Start Building

Stop typing every single instruction into your AI assistant and start designing a system that runs itself. That is the core idea behind Loop Engineering, a new free guide from HuaShu that explains how to move beyond manual prompting. Instead of you being the human in the loop, you build a structure that wakes up on a timer, spawns its own helper agents, checks their work, and remembers what happened last. You build it once, and it keeps working without you hovering over the keyboard.

🆔 @hackernewsgithubprojects

📦 xflare-bot/pokemonlive

Pocket Battle Lab: AI-Generated Pokemon Battles

Pocket Battle Lab is the browser game that generates your Pokemon animations on the fly. It runs a standard turn-based battle where the rules engine handles all the damage and status effects, while artificial intelligence creates fresh, anime-style video clips for every single attack. Instead of looping the same old pre-recorded files, the system plans a short cinematic storyboard and renders it right there in the battlefield while the previous move is still playing. This local prototype proves that you can build a fully playable battle without ever opening a video editor. It is a fascinating look at how far we can push real-time content generation for retro-style games.

🆔 @hackernewsgithubprojects

📦 seunggeunkimkr/genuine-any-order

How AI Writes Code Any Way It Wants

Genuine Any Order is the code generation model that refuses to write programs strictly from left to right. It is built to prove that artificial intelligence can think about code structure just like a human would, deciding where to start and how to fill in the blanks. The system actually grows its own sequence of words as it works, rather than sticking to a fixed length, which lets it tackle complex Python scripts with surprising flexibility. This matters because it shows that machines can reason about the shape of a solution before they even finish writing it.

🆔 @hackernewsgithubprojects

📦 sf-stav/velogb10

veloGB10

NVIDIA’s DGX Spark has a hard ceiling of about two hundred and fifty-five gigabytes per second, and veloGB10 squeezes every drop out of it. This is a Rust inference engine built specifically for that hardware, letting you run massive language models at speeds that rival much bigger clusters. The coolest part? It uses multi-token prediction to guess several words at once, verifying them in a single flash. Because the math is identical to separate guesses, the result is perfectly lossless, not just an approximation. It even lets two machines work together to make one request faster, not just to fit the model.

🆔 @hackernewsgithubprojects

📦 alibaizhanov/mengram

Mengram: AI Memory That Learns From Mistakes

Mengram gives AI agents a memory that actually learns from its own mistakes, not just a log of what happened. It splits memory into three types: facts, events, and workflows. The coolest part is the procedural memory. When an agent fails at a task, like a deployment crashing because it forgot a step, Mengram doesn't just record the failure. It automatically updates the workflow to include the missing step so the agent never makes that mistake again. It’s like giving your AI a notebook where it writes down its own lessons learned. This means your agents get smarter over time without you having to manually tweak their instructions.

🆔 @hackernewsgithubprojects

📦 virtualluoucas/structab

StrucTab: The Smart Way to Read Tables

StrucTab is the table-parsing framework that finally understands the layout of complex spreadsheets. It stops treating a table image as a simple picture and instead breaks the job into three distinct steps: counting rows and columns, mapping out merged cells, and then generating the actual code. This approach fixes a common problem where models guess the structure and get it wrong, leading to messy, broken data. By using a smart scoring system that checks these steps separately, it ensures the output is accurate and structured properly.

🆔 @hackernewsgithubprojects

📦 disler/fixing-smartass-opus-5

Fixing Smartass Opus 5

Turn your smartest AI coding assistant into a precise engineering partner with a single markdown file. This project stops the model from burying simple answers under layers of fluff, fake enthusiasm, and unnecessary formatting. Instead of repeating the same verbose tics every time, the system prompt enforces a strict operating contract that demands clarity and cuts the noise. You get direct, actionable answers that respect your time and your output limits. It is a practical fix for anyone tired of scanning through pages of text just to find one useful sentence. Stop paying for tokens you will never read and start building with an agent that actually works.

🆔 @hackernewsgithubprojects

📦 breko861-hash/sol-luna-codex-orchestrator

Sol Luna Codex Orchestrator

Orchestrate AI coding agents without wasting money. Sol Luna Codex Orchestrator lets a main AI plan while cheaper workers handle specific tasks. It stops the expensive brain from doing grunt work. Instead, it sends small jobs to quick, low-cost models. This cuts costs and speeds up development. You get smart decisions without paying premium rates for everything. It is a simple template for efficient coding. Stop overpaying for AI. Use the right brain for the job. Try it and save cash.

🆔 @hackernewsgithubprojects

📦 mardlib/ensoniq-eps-16-plus

Ensoniq EPS-16 Plus: The 1990s Sampler, Reborn

The Ensoniq EPS-16 Plus emulator runs the original 1990s operating system on modern Mac hardware. Instead of simulating the sound with a modern sample player, this project builds a digital replica of the physical circuitry. It presents the authentic software to a virtual machine that mirrors the original chips, buttons, and floppy drives. This means the instrument behaves exactly like the vintage hardware you remember, complete with its specific quirks and workflows. You get the full, unaltered experience of the classic sampler without needing the aging original equipment. It is a precise technical recreation that preserves the unique character of this iconic machine for today’s musicians.

🆔 @hackernewsgithubprojects

📦 vavo/lora-pilot

One Container For All AI Training

A single Docker container can now run three separate Stable Diffusion training systems side by side without crashing. That is the core idea behind Lora Pilot, a prebuilt environment that solves the headache of managing conflicting software versions for custom AI model training. Instead of installing each tool separately and hoping they work together, this project bundles the trainers, visualizers, and image generation tools into one shared workspace. Everything saves to the same folder, so your work survives restarts and you never have to reconfigure paths.

🆔 @hackernewsgithubprojects

📦 lostb1t/remux

Remux: The Media Server That Doesn't Need Downloads

Remux streams movies directly from torrents without ever downloading the file to your hard drive. It is a self-hosted media server written in Rust that speaks the same language as Jellyfin, meaning your existing apps work with it immediately. The project combines local files, remote sources, and torrent streaming into a single library, so you can browse and play content without juggling multiple services. Because it handles the streaming process internally, you get instant playback with full support for subtitles and audio tracks. This approach keeps your storage clean while still giving you access to a vast array of media.

🆔 @hackernewsgithubprojects