📦 crabbuild/compass

Compass: A Knowledge Graph for Your Codebase

Compass lets you turn a messy codebase into a searchable graph, letting you instantly find dependencies, trace impact, and understand architecture without needing vector databases or Python. Built in Rust for speed, it runs locally, keeping your data private and queries fast. The real magic is its versioned history feature, which captures exact snapshots of your code at every Git commit, allowing you to compare how the project evolved and spot breaking changes before they hit production. It is basically a time machine for your software structure, giving you precise, traceable answers instead of guessing.

📰 https://news.ycombinator.com/item?id=49178759

🆔 @hackernewsgithubprojects

📦 jarynclouatre/bindery

Bindery: Drop Files, Get Converted E-Books

Drop e-books and comics into a folder and watch them automatically transform into perfectly formatted files for your Kindle or Kobo, all handled by a single Docker app that runs quietly in the background. It combines two powerful conversion tools into one self-hosted service, so you never have to mess with complex command lines or manual settings. You simply put your digital reading material into a designated folder, and Bindery takes care of the rest, optimizing page layouts and shrinking file sizes without losing quality. A clean web interface lets you track progress, upload files directly from your phone, and tweak preferences without touching any code.

🆔 @hackernewsgithubprojects

📦 zadid6pretam/gotabpfn

Gotabpfn: Smarter AI for Complex Data Tables

Gotabpfn is the smart tool that finally helps artificial intelligence understand messy, complex data tables by reordering their columns for better clarity. Most AI models struggle when they face huge spreadsheets with hundreds of columns because the random order of information confuses them. This project fixes that by using a graph method to arrange your data features into the most logical sequence before the model even starts learning. It also shrinks that data into a compact format that fits easily into powerful foundation models, making prediction tasks much faster and more accurate.

🆔 @hackernewsgithubprojects

📦 primeintellect-ai/prime-agent

Prime Agent: The AI That Learns From Its Own Mistakes

Prime Agent is an open-source coding assistant that actually improves itself while you work. Instead of just answering your questions, it runs your code in a persistent Python environment, watching what happens and storing those lessons as durable memories. You can tell it to refine its own approach, and it applies small, evidence-backed updates to its working knowledge without wiping the slate clean. This means it remembers past mistakes and successful patterns, so it gets sharper with every session. It can also run complex, long-running tasks in the background, sending messages to its own helper agents to coordinate the work while you sleep.

🆔 @hackernewsgithubprojects

📦 xiaomirobotics/xiaomi-robotics-1

Xiaomi-Robotics-1 Explained

Xiaomi-Robotics-1 learned over one hundred thousand hours of robot movement just to master new tasks with almost no help. This repository contains the code for a foundation model that acts like a general-purpose brain for physical robots. Instead of teaching a machine to fold laundry, open drawers, or pack boxes from scratch, engineers train it on massive amounts of diverse, real-world video data first. The result is a system that can look at a messy kitchen and figure out how to clean it up, or adapt to a completely new room and object arrangement without being reprogrammed.

🆔 @hackernewsgithubprojects

📦 autom8ai/open-higgsfield-ai

Open Higgsfield AI: Free Cinematic Studio

Open Higgsfield AI packs over two hundred creative models into one free desktop app. You get full control over cinematic camera angles, generate video from images, and animate portraits with lip sync. Unlike closed platforms, this open-source tool lets you self-host everything so your data never leaves your machine. It works right out of the box on Mac and Windows. Download the app and start building professional visuals without paying a dime or worrying about vendor lock-in.

🆔 @hackernewsgithubprojects

📦 tr1dae/comfyui-minimaxh3_latentupscaler

MiniMax H3 Latent Upscaler

Upscale video resolution between MiniMax H3 sampling passes while keeping the audio clean. Most upscaling tools break audio when resizing, but this custom ComfyUI node handles the tricky NestedTensor data properly. It doubles the video resolution and then carefully remakes the audio noise based on your settings. You can lock the first pass audio completely, just lightly polish it, or let the second sampler fix it entirely. It even upscales reference images to match the new size so everything stays in sync. Just wire two samplers together with this node in between to get a sharp, coherent result.

🆔 @hackernewsgithubprojects

📦 herenn/infralens

Infralens Kernel Network Map

InfraLens turns your messy infrastructure into a clear live map by tracing network traffic directly from the operating system kernel. You get a real-time visualization of exactly which services talk to each other without touching any code or adding heavy helper containers. It works on Linux servers and inside Kubernetes clusters, identifying everything from database connections to DNS queries with almost no performance impact. The tool even uses artificial intelligence to automatically explain what each service does just by clicking on it. It is the fastest way to understand your architecture without rewriting your code or waiting days for reports.

🆔 @hackernewsgithubprojects

📦 faraz-portfolio/demo-2026-r3f-inspector

demo-2026-r3f-inspector

demo-2026-r3f-inspector is the interactive playground that turns the tricky parts of ThreeJS WebGPU development into a visual game. It lets you tweak geometry, lighting, and materials in real time using a familiar control panel instead of rewriting code every five seconds. The highlight is the built-in inspector that hooks directly into your React components, letting you adjust sliders and colors while the scene updates instantly. It feels like magic because you get immediate feedback on how those changes affect the rendering pipeline without restarting anything. This makes experimenting with new graphics features way less frustrating and way more fun.

🆔 @hackernewsgithubprojects

📦 cloudflare/cloudflare-os

Cloudflare OS

Cloudflare OS turns your company’s messy data into a secure, AI-powered workspace where every app runs in its own private sandbox, keeping your information safe while letting AI agents build tools on the fly. Instead of trusting a central server with your secrets, the system creates individual instances of software just for you, so a slide deck or a game never leaks data to the outside world. The coolest part is the Gatekeeper security layer, which lets AI agents plan their work in the background and then asks you to approve big moves like sending emails or updating databases all at once, rather than freezing up after every single step.

📰 https://news.ycombinator.com/item?id=49182551

🆔 @hackernewsgithubprojects

📦 optim-agent/optim-plans

Optim Plans

Optim-plans is the human-in-the-loop planning plugin that finally stops coding assistants from rushing into the wrong implementation. Instead of letting an AI agent blindly write code, this tool acts as a dual-ring safety net. First, it forces a planning-and-refining loop to turn vague ideas into clear, human-reviewed markdown plans while asking clarifying questions. Once approved, the executing-and-validating ring safely tests, audits, and verifies the changes inside a secure git workspace before anything is integrated. It is an incredibly smart way to give systems like Claude and Codex the explicit execution gates and safety controls they need to build software reliably.

🆔 @hackernewsgithubprojects

📦 dingduff/dingduff-public

DingDuff Public: Free Legal Research for Lawyers

DingDuff Public gives lawyers instant access to millions of court opinions and statutes right inside the Claude chat they already use. Built by attorneys for attorneys, this project acts as a connector that lets you ask legal questions in plain English and receive answers backed by real, verifiable citations from federal and state sources. Instead of memorizing complex search commands, you simply describe what you need, and the tool pulls the exact texts of case law, rules, and PACER filings to help you build accurate research memos.

🆔 @hackernewsgithubprojects

📦 attemorysystem/attemory

Attemory: AI Memory That Actually Remembers

Attemory is a retrieval engine that lets AI agents search their own long-term memory using attention, not just vector similarity. It indexes documents and code into reusable key-value state, then runs a local model to reason over that data and pull up the exact evidence needed. This approach cuts coding-agent token usage by nearly half while keeping search quality high. Instead of relying on compressed embeddings, Attemory lets the model read raw text directly, making it much better at finding specific details in huge context windows. It works locally on Linux and macOS, supporting CPU and GPU backends.

🆔 @hackernewsgithubprojects

📦 hermes-brasil/hermes-brasil

Hermes Brasil: AI Agent Skills in Portuguese

Hermes Brasil is the Brazilian community hub for Hermes Agent, offering Portuguese-language skills, guides, and integrations for the open-source AI agent by Nous Research. The repository features ready-to-use skills for tasks like B2B prospecting and kanban orchestration, alongside practical installation guides for production environments. It enables developers to easily expand their AI agent's capabilities with locally relevant resources and community-driven contributions.

🆔 @hackernewsgithubprojects

📦 accio-lab/realreplicabench

RealReplicaBench: Test AI Agents on Real Business Tasks

See how your AI agents actually perform when thrown into realistic, messy business workflows. This tool builds safe, reproducible clones of popular online services like Gmail, Slack, and Alibaba, complete with authentic files and state changes. Instead of simple coding quizzes, it lets you run complex, long-horizon tasks like auditing supplier invoices, managing procurement lists, or triaging customer complaints. You get to watch an agent navigate these high-fidelity replicas and handle multi-step chores that mimic real work pressure. It is the perfect way to stress-test automation skills without risking actual company data or breaking live systems.

🆔 @hackernewsgithubprojects

📦 wildminder/comfyui-dype

ComfyUI DyPE: Generate 4K Images Without Artifacts

ComfyUI DyPE lets your diffusion models generate crisp four thousand by four thousand images by dynamically adjusting positional settings during the creation process. Standard tools struggle with mega pixels, usually turning details into blurry messes or repeating patterns. This project fixes that by shifting the model focus from broad shapes early on to fine details later. It works as a simple plugin for popular AI tools and supports several major model types. You get high resolution without needing complex training. It is a practical way to push image quality further with minimal effort.

🆔 @hackernewsgithubprojects

📦 morishuz/delaunay32

Delaunay32: Blazing Fast 2D Meshes

Delaunay32 lets you instantly connect thousands of scattered points into a perfect, triangle-filled mesh without any messy glitches. While most tools struggle with floating-point errors when dealing with massive datasets, this clever C++ library secretly converts your coordinates into exact integers to guarantee perfect results every single time. You can throw in simple whole numbers or direct decimal floats, and it handles the heavy lifting in parallel using all your computer’s cores. The result is a triangulation that is not only incredibly robust against weird edge cases but also over ten times faster than its closest competitors for large point sets.

📰 https://news.ycombinator.com/item?id=49125532

🆔 @hackernewsgithubprojects

📦 sorryhyun/anima_lora

Anima LoRA: Fast Model Training

Anima LoRA lets you train custom AI image models on your own graphics card in minutes, not days. This open-source toolkit is built specifically for the new Anima diffusion model, which uses a modern architecture that is both faster and sharper than older tools. The real magic here is how it handles speed. It uses smart compiler tricks to shrink the memory footprint so you can train high-resolution models even on consumer-grade hardware that usually chokes on this work. Instead of just throwing more power at the problem, it carefully optimizes every step of the training loop.

🆔 @hackernewsgithubprojects

📦 pku-yuangroup/uniworld-view

UniWorld-View

UniWorld-View turns a simple video or single photo into realistic new camera angles without needing expensive equipment. Researchers from Peking University built this tool to solve a tricky problem: making a video look like it was filmed from a completely different spot. Instead of complex 3D modeling, the system uses advanced video generation to predict what the scene looks like from new viewpoints. You can even control exactly where the camera moves, allowing for precise adjustments. It ranks highly on industry leaderboards because it handles everyday objects and clear motion surprisingly well. This open-source code lets developers experiment with view synthesis directly on their own machines.

🆔 @hackernewsgithubprojects

📦 sespoir/reground

ReGround: AI That Double-Checks Its Eyes

Teaches vision models to catch their own mistakes. When a computer program tries to answer a hard question about a picture, it sometimes guesses wrong after too many steps. ReGround fixes this by letting the model pause and look again. If it gets unsure, it emits a special signal to re-examine the original image before giving a final answer. It is like having a second pair of eyes. The system trains itself to recognize when it needs a closer look and then re-runs the visual check automatically. You get better answers without changing the core model architecture. It just adds a smart self-diagnosis loop that actually works.

🆔 @hackernewsgithubprojects