📦 z-yiwei/rectify-then-diffuse

Rectify Then Diffuse: Fixing AI Image Concepts

Rectify Then Diffuse treats complex image generation like a simple math problem by fixing the starting point before the noise removal begins. The project solves the common issue where AI tools blend two distinct ideas into one confused mess. It works by running a quick preview to spot overlapping features, then gently adjusts the initial image data so each concept claims its own space. This means you can ask for a red backpack and orange glasses, and get exactly that without the colors bleeding together. The approach skips heavy training, making it a clever, lightweight trick that keeps separate objects clear and distinct.

🆔 @hackernewsgithubprojects

📦 yaxin9luo/autodesign

AutoDesign: One Paper, Four Outputs

AutoDesign turns a single academic PDF into four distinct, editable artifacts. It generates a dense poster, a full presentation deck, an editorial web page, and even a narrated video. Instead of just writing code, it optimizes a reusable design system that learns from its own mistakes. It starts with your paper, then iteratively refines the layout, typography, and content until the results look professional. The best part is that everything stays editable, so you can tweak the slides or poster without starting from scratch. It essentially automates the entire afterlife of a research paper. Check it out if you need to make your work look as good as it reads.

🆔 @hackernewsgithubprojects

📦 nousresearch/hermes-bot-mode

Hermes Bot Mode: Create Your Own AI Agent Team

Hermes Bot Mode lets you run multiple distinct artificial intelligence personalities simultaneously, each with its own chat history and schedule. This desktop plugin transforms your agent profiles into a roster of named bots, complete with unique avatars and daily routines. The most surprising feature is bot-to-bot messaging, where agents can send messages to one another using a simple inbox system. You can type a mention in any chat to have your active bot hand off work to a specialist, wait for the reply, and report back. It works like a team of digital assistants collaborating in the background without needing extra servers or complex setups.

🆔 @hackernewsgithubprojects

📦 garystack/beyond-mmenv-scaling

Beyond-MMEnv-Scaling: Smarter Training Data for AI Vision

Beyond-MMEnv-Scaling is the research project that finally teaches AI vision models how to choose their training diet rather than just eating more of it. Most developers assume that throwing more visual environments at a machine learning model will automatically make it smarter, but this code proves that is usually a waste of time. Instead it uses two clever tricks. First it picks environments based on the actual skills they practice so the agent learns distinct abilities instead of repeating the same pattern. Second it arranges those tasks into a structured curriculum that slowly ramps up the difficulty.

🆔 @hackernewsgithubprojects

📦 harshkedia177/axon

Axon: The code knowledge graph

Axon is the code intelligence tool that turns your entire codebase into a searchable knowledge graph for both developers and AI agents. Instead of just reading flat text, it builds a visual map of every dependency, call chain, and execution flow in seconds. You can explore this map interactively in a web dashboard or let your AI assistant query it directly to understand exactly what will break before you make a change. It runs completely locally without any cloud dependencies, giving you a clear, structural view of your architecture. This approach saves you from blind edits and helps you spot hidden connections that standard search tools completely miss.

🆔 @hackernewsgithubprojects

📦 zzaiyan/geoseg-ov

GeoSeg-OV: Smarter Satellite Segmentation

GeoSeg-OV is the remote sensing tool that finally helps computers understand satellite maps across different places without retraining from scratch. Most AI models for analyzing aerial images get confused when the scenery changes, but this project uses structural hints from depth models to guide the recognition process instead of just matching pixels. It keeps the text understanding intact while letting the computer see where objects actually sit in space. This makes it surprisingly good at spotting land types like forests or roads in completely new regions you haven’t seen before. It is a clever way to bridge the gap between different geographic datasets.

🆔 @hackernewsgithubprojects

📦 zebinx/drivevla-m0

DriveVLA-M0

Autonomous cars can now remember their past mistakes to drive safer. DriveVLA-M0 is a research project that builds a memory for self-driving systems. Instead of just reacting to traffic right now, it stores detailed records of near-crashes and confusing road situations. When the car encounters a similar problem later, it quickly pulls up that old memory to correct its path. This failure-aware system helps vehicles learn from history, reducing accidents by anticipating trouble before it happens. It is a smart step forward for safer, smarter autonomous driving.

🆔 @hackernewsgithubprojects

📦 luo-z13/eo-wm

eo-wm

Satellite observations can now predict how vegetation degrades under extreme weather by treating the planet like a physics-driven video game. A new project called eo-wm uses a latent video diffusion model to forecast earth observations from sparse satellite data and weather patterns. By splitting weather data into baseline climatology, anomalies, and cumulative stress signals, the model creates realistic, probabilistic forecasts of environmental changes. It even includes benchmarks to test how plants respond to severe summer heat and drought. Ultimately, this approach turns raw climate data into highly responsive, visual simulations of our changing planet.

🆔 @hackernewsgithubprojects

📦 dosu-ai/decant

Decant: Your AI Session Dashboard

Decant is the local privacy tool that turns your Claude Code and Codex session logs into a searchable dashboard showing exactly where your tokens, cost, and agent time go. It runs entirely on your machine without sending any data out, letting you track spending, inspect context windows, and find which files your AI assistants actually touched. It gives you clear, tangible insights into your coding agent habits without the privacy risk of cloud-based analytics.

📰 https://news.ycombinator.com/item?id=49279140

🆔 @hackernewsgithubprojects

📦 jakubantalik/libraries

Libraries

Build beautiful interfaces without writing complex CSS animations yourself, because this library handles the heavy lifting for you. Think of it as a magic wrapper for your React components that instantly adds stunning visual effects. You get a traveling beam of light that glides around your buttons and cards, or a breathing halo that pulses softly behind your content. The best part is how smart it is, it automatically detects the shape of your elements and adjusts the glow perfectly. It even respects your system settings, turning off fancy animations for anyone who prefers reduced motion, which is incredibly thoughtful for accessibility.

🆔 @hackernewsgithubprojects

📦 deepseek-ai/awesome-deepseek-agent

Awesome DeepSeek Agent: The Ultimate Integration Guide

Awesome DeepSeek Agent is a curated collection of step-by-step guides that lets you plug DeepSeek models into your favorite coding and agent tools. Instead of hunting through scattered documentation, you get clear instructions for setting up DeepSeek-V4-Pro or Flash in twenty different applications like Cline, GitHub Copilot, and Cherry Studio. The project solves the headache of configuration by covering installation, API key setup, and initial runs in plain language. It is particularly useful because it highlights powerful features like a one million token context window and adjustable reasoning effort levels that many users miss.

🆔 @hackernewsgithubprojects

📦 jlcodes99/cockpit-tools

Cockpit Tools: The Multi-AI IDE Account Manager

Cockpit Tools is the universal account manager that finally unifies all your AI coding assistants into one single dashboard. Instead of juggling logins across Cursor, GitHub Copilot, Windsurf, and half a dozen other platforms, this tool lets you group every account into neat categories and switch between them with one click. The real magic happens with quota monitoring, where you can instantly see how many API calls you have left across all your services without visiting each website manually.

🆔 @hackernewsgithubprojects

📦 tamnguyenvan/screenarc

ScreenArc: Cinematic Screen Recording

ScreenArc automatically tracks your mouse clicks to generate smooth pan-and-zoom animations, turning ordinary screen recordings into professional, cinematic videos without manual keyframing. It captures your screen and audio, then uses a visual editor to let you trim clips, add a webcam overlay, and apply instant presets for a consistent look. You can easily switch between YouTube, TikTok, or Instagram aspect ratios and export high-quality video or GIFs. This open-source tool solves the headache of tedious video editing by handling the heavy lifting of camera movement for you, making it perfect for creators who want stunning tutorials with minimal effort.

🆔 @hackernewsgithubprojects

📦 criptogus/hermesoffice

HermesOffice: The Local AI Office Suite

HermesOffice lets you edit Word, Excel, and PowerPoint files entirely on your computer while an AI agent works alongside you in real time. Instead of sending your private documents to the cloud, this open-source suite runs locally, keeping your sensitive data safe from prying eyes. The coolest part is how it handles edits: when the AI changes your document, it only rewrites the specific blocks it touched, leaving the rest of your file perfectly intact. This means you get the power of artificial intelligence without breaking your existing layouts or losing any original data. It is a smart, secure way to create professional documents without sacrificing privacy or control.

🆔 @hackernewsgithubprojects

📦 grigio/network-monitor

Network Monitor: Live Network Traffic Viewer

Network Monitor gives you a live, real-time view of every active internet connection on your Linux system, showing exactly how much data each program is uploading and downloading. Built in Rust with a modern graphical interface, it uses powerful kernel-level tracing to capture connection details the moment they happen, avoiding the delays of standard system polling. You can watch live upload and download speeds, see which specific application owns each connection, and identify remote servers with easy-to-read text instead of confusing code.

🆔 @hackernewsgithubprojects

📦 oseghalep/cloud-cost-optimization-hub

Cloud Cost Optimization Hub

Cloud Cost Optimization Hub brings all your AWS, GCP, and Azure bills into one single dashboard so you finally know where your money is going. Right now, it uses mock data to show you exactly how a multi-cloud cost tracker looks and feels before you even connect your real accounts. You spin up a local version with a simple command, log in, and instantly see a clean interface tracking spend by provider and region. It is built with Go on the backend and a modern React frontend that just works.

🆔 @hackernewsgithubprojects

📦 hexrayssa/ida-cyberchef

IDA CyberChef Brings Browser Data Tools to Reverse Engineering

IDA CyberChef brings the famous browser-based data transformation tool CyberChef directly into the IDA Pro reverse engineering environment. Instead of copying and pasting binary blobs between your disassembler and a web tab, this plugin embeds the entire CyberChef interface inside IDA using a custom Python JavaScript engine. You can now chain operations like base64 decoding or XOR masking right next to your code view, reading selected bytes automatically and patching results back into the binary without ever leaving the analysis window. It saves massive context switching time by keeping all your data munging tools in one familiar place.

🆔 @hackernewsgithubprojects

📦 gna1280072/leepanel

Manage Linux Servers Without Installing Anything

Control your Linux VPS from a lightweight desktop app that runs entirely on your computer without installing a single line of code on the server. LeePanel connects via your existing SSH port so you never expose dangerous new ports to the internet or leave security vulnerabilities on the machine itself. You get a full terminal and file browser plus tools to install web stacks and manage databases all through a clean interface that stays completely off the server. This approach eliminates the risk of panel hacks and makes server management safe and simple for anyone.

🆔 @hackernewsgithubprojects

📦 ysng123/eg-fm

Energy-Guided Flow Matching: Smarter Image Generation

Energy-Guided Flow Matching delivers stunningly realistic images with a method that lets AI models learn from the inside out. Instead of just guessing what an image should look like, this project uses a clever technique called flow matching. It takes a photo and gently morphs it into noise while keeping track of exactly how to reverse that process. The magic lies in how the model learns to guide that noise back into a clear picture by following a specific energy path. This repository gives developers the actual PyTorch code to train their own models or use pre-built ones like PixelDiT.

🆔 @hackernewsgithubprojects

📦 austinrockman/reflector

Reflector: Your Sample Library That Actually Understands Harmony

Reflector is a free, local-first macOS application that lets your personal sample library speak your musical language. Instead of searching by filename or tag, it listens to the actual harmonic content of your audio files. You drop in a pad or a synth stab, and Reflector instantly finds other samples in your folder that will blend perfectly with it, even suggesting the right pitch to make them lock together. It learns the hidden compatibility between thousands of sounds, turning a messy folder of loops into a navigable musical instrument. All of this happens on your own computer, keeping your data private and your workflow fast.

🆔 @hackernewsgithubprojects

📦 hollyming/cazo

Cazo: The AI That Adapts Without Looking Back

Cazo is the memory-efficient AI trainer that adapts to changing conditions using only forward passes. Most AI models need to rewind and recalculate every mistake to learn, which eats up massive amounts of computer memory. This project flips that logic by using zeroth-order optimization to tweak the model’s settings on the fly without ever needing to reverse the process. This means it uses roughly eighty percent less memory than standard methods, making it perfect for running on devices with limited hardware or quantized models. It effectively helps computers adjust to noisy or distorted data in real time, keeping them accurate without breaking the bank on computing power.

🆔 @hackernewsgithubprojects